all publishers

edwinhu

@edwinhu source repo

96 published skills

  1. ▌
    Readwise Prune · edwinhu
    Clean up stale Readwise Reader documents. Use when the user wants to declutter their reading library, remove old unread articles, or manage Reader inbox. Triggers on "clean up readwise", "prune reader", "delete old articles", "declutter reading list".
    26 repo stars
  2. ▌
    Replicate Paper · edwinhu bundle
    Use when a published empirical finance or accounting result has to be reproduced from data — 'replicate Table 2 of X', 'does this paper replicate', 'reproduce their main result', 'can we get their coefficient', 'our estimate doesn't match the paper', 'grind this replication', 'run an in-design search on this paper', 'apply the AGK rule to X', 'search inside their design until it hits or the leads run out', 'is this hit fragile'. Use proactively whenever a task compares our estimate to a printed coefficient, even if the user never says 'replicate'. NEGATIVE ROUTING: packaging code and data for someone else to rerun is replication-package; building a dataset or model with no published target is ds; the bare out-of-session loop mechanics are grind.
    26 repo stars
  3. ▌
    Prose Rules Econ · edwinhu
    The writing-econ agent's rule skills (writing-general, writing-econ, ai-anti-patterns) loaded through one skill on either launch path. Named by that agent's skills: and initialPrompt:; the registers themselves are agent-internal.
    26 repo stars
  4. ▌
    Blaw Edgar Search · edwinhu bundle
    Use when the user wants to search SEC filings or exhibits on Bloomberg Law — 'search EDGAR on Bloomberg Law', 'BLAW EDGAR search', 'find exhibits with this clause', 'which 8-Ks attach a consulting agreement', 'pull the Bloomberg Law results list', 'capture the BLAW results' — or needs exhibit-level phrase search with proximity operators that the SEC and WRDS full-text routes handle badly.
    26 repo stars
  5. ▌
    Prose Rules Legal · edwinhu
    The writing-legal agent's rule skills (writing-general, writing-legal, ai-anti-patterns) loaded through one skill on either launch path. Named by that agent's skills: and initialPrompt:; the registers themselves are agent-internal.
    26 repo stars
  6. ▌
    Prose Rules Review · edwinhu
    The writing-reviewer agent's rule skills (writing-general, writing-legal, writing-econ, ai-anti-patterns) loaded through one skill on either launch path. Named by that agent's skills: and initialPrompt:; the registers themselves are agent-internal.
    26 repo stars
  7. ▌
    Continuous Learning · edwinhu bundle
    This skill should be used when the user asks to 'extract patterns from this session', 'save what we learned', 'create a skill from this workflow', 'learn from this conversation', 'capture reusable knowledge', or wants to turn session patterns into reusable skills.
    26 repo stars
  8. ▌
    Typst Test Slide · edwinhu
    This skill should be used when the user asks to 'test a slide', 'isolate a slide', 'debug a slide', 'preview a single slide', 'test this slide', 'render one slide', or when you need to visually verify a single Typst slide from a presentation in isolation. Provides the exact file setup pattern to avoid access-denied and import errors.
    26 repo stars
  9. ▌
    Ds Rules · edwinhu
    The DS constraints C1-C6, V1-V9, A1-A6, E1-E7 as binding rule statements. Preloaded by the ds and ds-reviewer agents; load it before any data, table or figure work that is not running inside one.
    26 repo stars
  10. ▌
    Jev Rules · edwinhu bundle
    Use when a written rule should become a Jev rule check, or an existing one misbehaves — "turn this rule into a Jev rule", "add a rule check", "make this a Jev check", "calibrate this rule", "why does my rule not separate", "my rule fires on accepted work", "my rule never blocks", "the violating case scores 0.6", "park this rule", "wire this rule", "unwire it", "add a rule set for <workflow>", "add a real case for this rule". Use proactively whenever a reviewer or lens keeps re-judging the same checkable rule, even if the user never says Jev. NEGATIVE ROUTING: running the existing rules over a change is rule-check.ts inside the workflow, not this skill; whether a phrase is an AI tic is ai-tic; a skill or workflow edit that only consumes rule checks is skill-creator or workflow-creator.
    26 repo stars
  11. ▌
    Bib Manage · edwinhu bundle
    ALWAYS use when a manuscript's BIBLIOGRAPHY is the thing being fixed, or when a cite's PDF turns out to be wrong — 'link my bib entries to the PDFs', 'which sources am I missing a PDF for', 'audit my sources.bib', 'my bib entry has no file field', 'fetch the Federal Register PDFs', 'why can't pincite find this source'. WRONG FILE: 'is this PDF the published version or the preprint', 'this PDF is a book review, not the book', 'the file field points at the wrong paper', 'the PDF doesn't match the citation'. METADATA: 'reconcile my bib against Paperpile', 'these entries were extracted by a model, check them', 'fix the metadata in sources.bib', 'my bib has no DOIs and the fields look wrong', 'pull the real author/journal/volume from my library', 'where did this bib entry's metadata come from'. PAGE RANGES: 'does my bib have page ranges', 'my bib only has start pages', 'backfill the page ranges', 'pull the pages from the DOI', 'add DOIs to my bibliography'. Use proactively before any pincite run — pincite resolves
    26 repo stars
  12. ▌
    Elide Case · edwinhu bundle
    Use when a court opinion that is not in the casebook has to become a casebook-style excerpt for students — "add this case to the addendum", "elide this opinion for class", "cut this case down to four pages the students can read", "make a casebook excerpt of X", "this case isn't in Choi, put it in the reader", "excerpt the Howey analysis from this opinion", "the TM mentions a case we don't have", "I want to teach this new decision next week". NEGATIVE ROUTING: compiling an addendum whose readings are already written is teaching:generate-addendum; retrieving an opinion with no elision is workflows:courtlistener.
    26 repo stars
  13. ▌
    Prose Rules · edwinhu
    The writing agent's rule skills (writing-general, ai-anti-patterns) loaded through one skill on either launch path. Named by that agent's skills: and initialPrompt:; the registers themselves are agent-internal.
    26 repo stars
  14. ▌
    Batch Router · edwinhu bundle
    Use when the user says 'bulk LLM job', 'batch job', 'submit a batch job', 'run this prompt over all the documents', 'process thousands of PDFs', 'extract fields from every filing', 'code each filing', 'label / annotate these documents', 'hand-code these', 'have agents read each document', 'which batch provider', 'cheapest way to run this over N rows', 'spend my API credits', 'Claude or OpenAI or Gemini for this batch', or needs any per-row LLM extraction, classification or enrichment over many inputs.
    26 repo stars
  15. ▌
    Claude Batch · edwinhu bundle
    Use when the user says 'Claude batch', 'Anthropic batch', 'Message Batches API', 'submit a Claude batch', 'run this through the Claude API in bulk', 'use my Ultra API credits', 'spend the Claude credit before it expires', 'which Claude org has credit', or when batch-router picked an Anthropic account.
    26 repo stars
  16. ▌
    Openai Batch · edwinhu bundle
    Use when the user says 'OpenAI batch', 'GPT batch', 'OpenAI Batch API', 'submit an OpenAI batch', 'run this through GPT in bulk', 'use my ChatGPT Pro API credits', or when batch-router picked the OpenAI account.
    26 repo stars
  17. ▌
    Web Scraping · edwinhu bundle
    Use when "scrape this site at scale", "fetch N thousand pages", "how many workers should this scraper use", "am I hammering this server", "we're getting 429s / blocked / CAPTCHAs", "should we use a proxy", "Zyte", "ScrapingBee", "Web Unlocker", "residential proxy", "rotate proxies", "scrape with Web Unlocker", "query Bright Data", "Bright Data datasets", "Bright Data Web Archive / Wayback alternative", "FINRA BrokerCheck data", "SEC IAPD / adviserinfo data", "Investment Adviser Public Disclosure", "broker/adviser disclosure snapshots", "LinkedIn/Crunchbase/Glassdoor company or people dataset", or any use of the Bright Data API (datasets/list, Web Archive search/dump, Web Unlocker zones).
    26 repo stars
  18. ▌
    Gemini Vertex · edwinhu bundle
    Use when the user says 'gemini batch', 'Gemini Batch API', 'Vertex AI', 'Gemini on Vertex', 'Cloud Flex', 'upload files to Gemini', 'flex', 'flex tier', 'Interactions API', 'cheap async Gemini', 'grounded lookups at scale', 'Google Search grounding in bulk', or when batch-router picked Gemini — large-scale Gemini extraction, classification or enrichment through Cloud Batch, or a few documents (≤10) through Cloud Flex.
    26 repo stars
  19. ▌
    Afk · edwinhu bundle
    Use when the user says '/afk', 'afk', 'going to bed', 'I'm going to sleep', 'work autonomously', 'work on this overnight', 'don't ask me questions', 'while I'm away', or 'do whatever you think is best'. NOT for questions about overnight returns, rates or anything financial; NOT for asking how the mode works.
    26 repo stars
  20. ▌
    Work · edwinhu bundle
    Use when the user says "work this", "run a work loop", "do this properly", "take this through clarify plan and verify", "run it through the gate", "/work", or hands over a substantial change that has no domain workflow of its own and should be planned, approved and independently verified before it lands. NEGATIVE ROUTING: a code change or bug fix is /dev; a dataset, table, figure or number is /ds; long-form prose is /writing; a talk built from a research paper is /workshop; lecture notes or course slides are teaching:notes and teaching:slides; a skill, workflow or plugin in this repo is skill-creator, workflow-creator or plugin-creator. Each of those is this loop plus a domain gate, and work is only the fallback when none of them fits.
    26 repo stars
  21. ▌
    Grind · edwinhu bundle
    Use when work has to keep going with NO session alive — "run this in a loop overnight", "grind loop", "start the loop and go to bed", "keep iterating until the check passes without me", "a fresh agent every iteration", "loop on this for days", "the orchestrator session is burning tokens on status reports", "wake it only when the grid job lands", "what has the loop done so far", "stop the loop", "it keeps re-diagnosing the same dead item". Use proactively when a hill-climb needs many cheap passes over hours or days and each pass costs more to supervise than to run. NEGATIVE ROUTING: a stopping condition for a session that stays ALIVE — a Stop-hook hold, a cron heartbeat, an overnight brief — is the work hold; one delegated piece of work handed to another model and waited on is farm-out; starting a persistent interactive session is agent-spawn. This skill owns the out-of-session loop, the append-only journal that is its whole memory, and the shell gate that decides when a model call is worth spending.
    26 repo stars
  22. ▌
    Lexis · edwinhu bundle
    Use when the user says 'Lexis Public Records', 'Secretary of State entity status via Lexis', 'corporate filings', 'is this company revoked / in good standing in Nevada', 'judgments and liens', 'UCC lookup', 'Lexis bankruptcy search', 'FEIN lookup', or 'locate a business'. Also use when the user says 'get this case from Lexis', 'pull it off Lexis+', 'export the opinion from Nexis', or names Lexis/Lexis+/Nexis/Protege as a case-retrieval source. NEGATIVE ROUTING: case and opinion retrieval is NOT implemented here — use workflows:westlaw; Delaware entity status is not available on Lexis at all.
    26 repo stars
  23. ▌
    Pincite · edwinhu bundle
    ALWAYS use when a law review manuscript's footnotes need page numbers, or when a page number already in one looks wrong — 'add pincites', 'pincite this draft', 'the editors want pin cites', 'my footnotes have no page cites', 'fill in the at-page for these cites', 'find the page that supports this claim', 'check my pincites', 'what page does this source say that'. HAND REVIEW: 'review my pincites by hand', 'show me each footnote with its PDF', 'let me enter the page numbers myself', 'apply the pincites I entered'. STATUS: 'how many footnotes still need pincites', 'which cites are still missing page numbers', 'what's left to pincite', 'how many pin-cites are left'. WRONG PIN: 'the page number is wrong', 'this pin is off by a page', 'this pincite points at preprint pagination', 'why did this cite land on the wrong page'. Use proactively before any law review submission whose footnotes carry bare cites. NEGATIVE ROUTING: whether a PDF is the version of record, a preprint or proof, or the wrong document entirely i
    26 repo stars
  24. ▌
    Westlaw · edwinhu bundle
    Use when the user says 'get this case from Westlaw', 'export the case as Word', 'download the opinion', 'pull 87 F.3d 536', 'I need the Westlaw version', 'get me the real text of this case', or 'the OCR is garbled, get the publisher text'. NEGATIVE ROUTING: excerpting an opinion already in hand into a course reading is workflows:elide-case; free case law with no subscription is workflows:courtlistener. This skill only retrieves and exports from Westlaw.
    26 repo stars
  25. ▌
    Audit Archive · edwinhu
    Use when archiving footnote URLs to perma.cc during a Bluebook footnote audit - 'archive the links', 'perma the URLs', 'these links will rot', 'add perma.cc archives to the footnotes', 'the journal wants archived URLs', or reaching Phase 6 of a bluebook-audit run.
    26 repo stars
  26. ▌
    Audit Crossrefs · edwinhu
    Use when a manuscript's supra/infra cross-references need to stop being hand-typed numbers — 'my supra notes point at the wrong footnote', 'the cross-references broke after I added a footnote', 'convert supra notes to fields', 'make cross-references auto-update', 'fix the infra cites', 'sync the crossrefs after editing footnotes', 'tie the supras to the bibliography'. Load as Phase 7 of a bluebook audit, or standalone after any Word session that added or reordered footnotes.
    26 repo stars
  27. ▌
    Superhuman · edwinhu
    This skill should be used when the user asks to "check email", "read inbox", "send email", "reply to email", "search emails", "archive email", "snooze email", "star email", "add label", "forward email", "download attachment", "switch email account", "use snippet", "search contacts", "ask ai about email", "find email about", "what did someone say about", or needs to interact with Superhuman email client. For calendar, events, and scheduling use the morgen skill instead.
    26 repo stars
  28. ▌
    Ds · edwinhu bundle
    ALWAYS use for ANY substantive empirical task whose output is a dataset, table, figure or number - "analyze this data", "build the panel", "merge these datasets", "run the regression", "profile this dataset", "clean this file up for analysis", "make me a summary table", "pull the data and check X", "replicate this paper's table 2", "build the ETL pipeline", "/ds". Use proactively even when the user asks casually and never says "analysis". NEGATIVE ROUTING: grading empirical work that already exists is the ds-reviewer agent; writing the results up as prose is writing-econ; spreadsheet file mechanics - reading, writing or reformatting an .xlsx - is xlsx, while building, merging or modelling the dataset inside it is ds; a one-line lookup against a file already in hand is answered inline, since this skill runs a full clarify/plan/dispatch/human-review lifecycle.
    26 repo stars
  29. ▌
    Dev · edwinhu bundle
    Use when the user says "build this feature", "implement X", "add support for", "add a flag for", "fix this bug properly", "this is broken, fix it", "refactor X", "write the tests for this", "/dev", or hands over any code change that should ship with a real failing-then-passing test rather than a quick edit. Use proactively the moment a request implies changing code — before reading the codebase to understand the bug, since that reading is part of the run. NEGATIVE ROUTING: a change whose acceptance cannot be one command that fails now and passes later is /craft; a dataset, table, figure or number is /ds even when code produces it; a skill, workflow, hook or plugin manifest in this repo is skill-creator, workflow-creator or plugin-creator; a typo or one-line fix is done inline.
    26 repo stars
  30. ▌
    Hpc · edwinhu bundle
    Use when submitting jobs to UVA HPC (Rivanna/Afton), writing Slurm scripts (sbatch/srun/squeue), converting SGE to Slurm, running compute on any Slurm-managed cluster, or building WRDS data pipelines with polars on HPC. Triggers: 'submit to HPC', 'sbatch', 'squeue', 'slurm job', 'run on Rivanna', 'run on Afton', 'HPC array job', 'convert SGE to Slurm', 'polars on HPC', 'WRDS from HPC'.
    26 repo stars
  31. ▌
    Nlm · edwinhu bundle
    ALWAYS use for ANY NotebookLM work - "make me a notebook on X", "create a notebook", "add this PDF/source to the notebook", "what notebooks do I have", "make a podcast/audio overview of these", "generate a video overview", "study guide", "briefing doc", "FAQ from these sources", "outline from the notebook", "slide deck from these sources", "ask my notebook about X", "summarize the sources in there", or any mention of NotebookLM or `nlm`. Use even when the user says "make a podcast of these papers" without naming NotebookLM. NOT for open-web research reports - use deep-research instead.
    26 repo stars
  32. ▌
    Wrds · edwinhu bundle
    Use when "query WRDS", "pull SEC filings", "access Compustat/CRSP/ExecuComp/Capital IQ", "Form 4 insider data", "13F institutional ownership (Thomson)", "13D/13G blockholders", "ISS governance/compensation/voting/directors", "proxy advisor recommendations", "TAQ intraday/NBBO", "SDC M&A or new issues", "DealScan syndicated loans", "PitchBook PE/VC deals", "FISD corporate bonds", "municipal bonds / muni trades / MSRB RTRS / SDC municipals", "Form D/ADV", "fund formation", "FJC court data", "linking datasets / join keys (gvkey-permno via CCM, cik-gvkey via wciklink, DealScan-Compustat)", or any WRDS PostgreSQL query or SAS ETL on the WRDS grid (qsub/qsas/SGE).
    26 repo stars
  33. ▌
    Craft · edwinhu bundle
    Use when the user says "craft this", "run a craft loop", "do this properly", "take this through clarify plan and verify", "run it through the gate", "/craft", or hands over a substantial change that has no domain workflow of its own and should be planned, approved and independently verified before it lands. NEGATIVE ROUTING: a code change or bug fix is /dev; a dataset, table, figure or number is /ds; long-form prose is /writing; a talk built from a research paper is /workshop; lecture notes or course slides are teaching:notes and teaching:slides; a skill, workflow or plugin in this repo is skill-creator, workflow-creator or plugin-creator. Each of those is this loop plus a domain gate, and craft is only the fallback when none of them fits.
    26 repo stars
  34. ▌
    Dewey · edwinhu bundle
    Use when "query Dewey Data", "deweydata.io", "SafeGraph places/patterns/spend", "Advan foot traffic", "POI / points of interest", "mobility data", "dataplor", "Veraset", "PassBy", "crypto/Bitcoin ATM locations", "GovFiles", "business entity / Secretary of State registry data", "OpenCorporates alternative", "LinkUp job postings", "job-postings panel", "Exchange Data International / EDI", "WCA / RCAN corporate actions", "global corporate actions (dividends, splits, mergers, tenders)", or any pull from the Dewey Data academic marketplace (UVA/NYU Platform Subscription) via the deweypy/deweydatapy client, DuckDB, or the Dewey MCP server.
    26 repo stars
  35. ▌
    Setup · edwinhu
    Use when the user says "set up workflows", "workflows setup", "is workflows installed correctly", "verify my install", "check the workflows install", "why isn't my agent's guidance loading", "my agent dispatch got denied", "/setup", or asks whether this plugin's agents, their preloaded skills and the main-thread guard's allowlist actually resolve on this machine. Use proactively right after installing or updating the plugin — a preload that fails to resolve is logged to the debug log only, and the run reads exactly as if it had loaded. Machine-level and idempotent; offers one optional user-tier plansDirectory write, always behind a question. NEGATIVE ROUTING: setting up a course's teaching plugin is teaching:setup and checking the Codex CLI is codex:setup; actually upgrading to a newer plugin version is plugin-update — this skill only checks what is installed, it never installs.
    26 repo stars
  36. ▌
    Tuicr · edwinhu bundle
    Review a GitHub/GitLab PR, commit range, working tree, or file in the tuicr TUI — and read the user's annotations back out of the session — or answer questions about tuicr usage and config. Use when the user says "tuicr", "tuicr pr <N>", "review this PR", "review PR #N", "review with tuicr", "code review TUI", "review the working tree", "tuicr all files", "tuicr <file>", "address my tuicr annotations", "read my tuicr review", "what did I annotate in tuicr", "tuicr config", "tuicr keybindings". Use proactively when a finished change needs the user's eyes before it ships, even if they never say "tuicr". NEGATIVE ROUTING: inside a running /craft, /dev, /writing or /workshop loop, human review is that workflow's own phase — follow it rather than starting a bare tuicr session; and when the user wants CLAUDE to find the problems rather than annotate them themselves, that is /code-review or /security-review, not this skill.
    26 repo stars
  37. ▌
    Marimo · edwinhu bundle
    ALWAYS load before editing ANY .py file that contains @app.cell or marimo.App — 'edit this notebook', 'add a cell', 'fix the notebook', 'why is this cell not updating', 'my notebook won't run', 'convert this ipynb to marimo', 'turn my Jupyter notebook into marimo', 'start a notebook', 'export the notebook to HTML', 'run marimo', 'the cell says variable already defined', 'marimo edit'. Use even when the user just says 'the notebook' — hand-editing a marimo file breaks its cell signatures and DAG.
    26 repo stars
  38. ▌
    Crsp V2 · edwinhu bundle
    Use when "CRSP CIZ", "CRSP v2", "CRSP flat file format 2.0", "crsp.dsf_v2 / msf_v2", "StkDlySecurityData", "StkMthSecurityData", "StkSecurityInfoHist", "stocknames_v2", "DlyRet / MthRet / DlyPrc / MthPrc", "SHRCD or EXCHCD equivalent in new CRSP", "SIZ to CIZ migration", "CRSP data after 2024", "CRSP delisting returns", "CRSP cumulative adjustment factors", "CRSP index INDNO / INDFAM", or any CRSP stock/index query where the legacy SIZ column names no longer exist.
    26 repo stars
  39. ▌
    Look At · edwinhu bundle
    Use when the user asks to 'look at', 'analyze', 'describe', 'extract from', or 'what's in' media files like PDFs, images, diagrams, screenshots, or charts. Triggers include: 'what does this image show', 'extract the table from this PDF', 'describe this diagram', 'what's in this screenshot', 'analyze this chart', 'read this image', 'get text from this PDF', 'summarize this document', or requests for specific data extraction from visual or document files. Use for interpreted content, not literal file reading (Read tool).
    26 repo stars
  40. ▌
    Permacc · edwinhu bundle
    ALWAYS use when URLs in a manuscript need permanent archived copies — 'perma these links', 'archive the URLs in my footnotes', 'add perma links', 'the journal wants perma.cc cites', 'make sure these links don't rot', 'archive this site before it changes', 'snapshot these URLs', 'perma.cc', or when cite-checking a draft with web sources. ALSO use when perma returns 'you've reached your usage limit' despite an institutional account, or when asking which perma folder an account may archive into.
    26 repo stars
  41. ▌
    Writing · edwinhu bundle
    ALWAYS use for ANY substantial prose a human will read - "write the article", "draft this section", "outline the paper", "turn these notes into prose", "write up the memo", "draft the comment letter", "write the brief", "expand this into a chapter", "I need a few pages on X", "put this argument in writing", "/writing". Use proactively even when the user asks casually and never says "article" - do not start drafting paragraphs first. NOT for code, data work or course materials.
    26 repo stars
  42. ▌
    Bluebook · edwinhu bundle
    ALWAYS use for ANY legal citation question, even if the user never says 'Bluebook' - 'cite this case', 'how do I cite a statute', 'is this footnote formatted right', 'id. or supra here', 'cite a law review article', 'what signal goes here', 'format these footnotes', 'short form for this cite', 'block quote this', 'where does the ellipsis go', 'is this quote altered right', or writing or checking any citation or quotation in a legal manuscript. NOT for auditing a whole manuscript's footnotes (use bluebook-audit) and NOT for rendering these rules in Typst (use docx-typst).
    26 repo stars
  43. ▌
    Farm Out · edwinhu bundle
    Run ALL delegated agent work through the CLIProxyAPI wrappers. Use INSTEAD OF the Agent tool, subagents, the Workflow tool, and in-session agent teams — for any "delegate this", "run these in parallel", "fan out", "have an agent review/investigate/search", "use a subagent", "spawn a team", "get a second opinion", "run this workflow script", or any task you were about to hand to a background agent. Also use for explicit mentions of cliproxy, codex-code, gemini-code, claude-code, farm out, or delegating work to another model. NEGATIVE ROUTING: anything phrased as a new, background, separate or companion SESSION — 'spawn an agent', 'spawn a background claude', 'kick off claude in <dir>' — belongs to agent-spawn, which fires first and carries this work inside its prompt; messaging a session that already exists is agent-msg; designing, repairing or auditing a workflow is workflow-creator; and a craft, dev or ds dispatch goes through craft-dispatch.sh, never a hand-written farm.sh --workflow line.
    26 repo stars
  44. ▌
    Jupytext · edwinhu bundle
    ALWAYS use before touching a notebook as text or running one headlessly - "convert this notebook to a .py", "turn this script into a notebook", "get this ipynb into git", "the notebook diffs are unreadable", "keep the .py and .ipynb in sync", "run this notebook end to end", "execute the notebook with these parameters", "papermill", "jupytext", "add an R/Stata/SAS kernel", "share data between kernels". Use even when the user only says "just run the notebook" - never claim a notebook ran without executing and inspecting it.
    26 repo stars
  45. ▌
    Readwise · edwinhu bundle
    ALWAYS use for ANY query against the user's own reading library — "search Readwise", "find highlights", "what did I highlight about X", "get quotes from my reading", "search my annotations", "find that thing I saved about Y", "pull the full text of that article", "what do my notes say on this", "add my highlights to a notebook", "add tagged documents to notebook". Use even when the user never says "Readwise" but is asking about something they read or saved. NOT for web or academic search — this searches only their curated library.
    26 repo stars
  46. ▌
    Research · edwinhu bundle
    ALWAYS use for ANY request to find academic papers - "find papers on X", "what does the literature say about X", "is there research on this", "who has written about X", "find me cites for this claim", "literature search", "any papers in the journals I like", "top journals only", "recent work on X", "has anyone studied this". Use proactively before answering an empirical or doctrinal question from memory, and never run scholar/consensus/paperpile by hand in sequence - this skill parallelizes them. NOT for open-web report writing (deep-research).
    26 repo stars
  47. ▌
    Workshop · edwinhu bundle
    ALWAYS use when the deliverable is a research talk - Typst slides and teleprompter speaker notes built from a paper. Use when the user says "create workshop slides", "build the deck", "make slides for my paper", "presentation from this paper", "write the speaker notes", "I'm presenting this at a seminar", "turn the paper into a 40-minute talk", "I have a workshop next week and nothing to show", or "/workshop". Use proactively whenever a conference, seminar, job talk or brown bag comes up, even if the user never says "slides". NEGATIVE ROUTING: course lecture slides and lecture notes are teaching:slides and teaching:notes; grading a deck that is already built is the workshop-reviewer agent; a one-slide tweak on a deck that already exists goes to the workshop agent, since this skill runs a full clarify/plan/dispatch/human-review lifecycle; the paper's own prose is writing-econ or writing-legal.
    26 repo stars
  48. ▌
    Consensus · edwinhu
    ALWAYS use before running the `consensus` CLI or hitting consensus.app - "search Consensus", "consensus search", "find RCT papers", "randomized trials on X", "systematic reviews / meta-analyses of X", "clinical papers on X", "empirical papers in top journals only", "papers in these specific journals", "filter by journal quartile", "most-cited papers on X since 2018". Use even when the user names a filter (study type, journal, year range, citations) without saying "Consensus". NOT for a broad multi-source literature sweep - use the research skill, which calls this one.
    26 repo stars
  49. ▌
    Lseg Data · edwinhu bundle
    Use when "query LSEG/Refinitiv", "fundamentals or market data from LSEG", "ESG scores", "management guidance / guidance reports / GR", "RIC/ISIN symbology", "corporate governance or activism (poison pills, campaigns)", "M&A or IPO deals", "syndicated loans or project finance", "PE/VC investments", "joint ventures", "municipal bonds", "Lipper fund details", "stock screening (fscreen)", "Refinitiv news", "Workspace web client", "Codebook", or any use of the `lseg.data` Python API. (academic loan/PE data: prefer the wrds skill.)
    26 repo stars
  50. ▌
    Paperpile · edwinhu bundle
    Use when the user asks to "add paper", "paperpile add", "fetch PDF for", "find and add", "search paperpile", "find in paperpile", "paperpile search", "label paper", "trash paper", "download paper", "paperpile index", "edit paper metadata", "update paper title", "fix paper author", "paperpile edit", "find PDF online", "search google for PDF", "resolve PDF", "fetch PDF for citation", "get full-text for DOI", "resolve cite to PDF", or any request to manage their Paperpile library or resolve a citation to a local PDF.
    26 repo stars
  51. ▌
    Cite Check · edwinhu bundle
    ALWAYS use when a draft's citations need checking against what the sources actually say — 'check citations', 'check my cites', 'verify cites', 'cite-check', 'run citation review', 'are my citations grounded', 'does this source actually support that claim', 'does source X support claim Y', 'what does source X say about Y', 'did I cite that right', 'make sure the cites hold up before I send this'. Use proactively before a draft goes out. NOT for Bluebook formatting (use bluebook / bluebook-audit) and NOT for detecting citations that do not exist at all (use source-verify).
    26 repo stars
  52. ▌
    DOCX Typst · edwinhu bundle
    Use to BUILD a Word document from a TYPST source, CONVERT a Word manuscript into Typst, or bring a returned .docx back into the repo. Triggers: 'build the docx from the typ', 'typst to Word', 'send them a Word version of this paper', 'I have a Word manuscript, give me Typst', 'convert this docx to typst', 'move my paper off Word', 'start a Typst repo from this Word draft', 'my coauthor sent back the docx', 'they returned the Word file with edits', 'reconcile their edits with my source', 'merge the docx changes back', 'what did they change in the Word file', 'pull the comments out of the docx', 'get their comments from the Google Doc', 'is this file canonical', 'the source and the docx have diverged'. ALSO owns TYPST CITATION RENDERING: 'render Bluebook citations in Typst', 'supra note numbering', 'my supra notes point at the wrong footnote', 'footnote numbers do not renumber when I insert one', 'Id. and supra in typst', 'small-caps reporters in typst', 'hayagriva cannot do Bluebook', 'typst bibliography style
    26 repo stars
  53. ▌
    Bright Data · edwinhu bundle
    Use when "query Bright Data", "Bright Data datasets", "Bright Data Web Archive / Wayback alternative", "scrape with Web Unlocker", "FINRA BrokerCheck data", "SEC IAPD / adviserinfo data", "Investment Adviser Public Disclosure", "broker/adviser disclosure snapshots", "LinkedIn/Crunchbase/Glassdoor company or people dataset", or any use of the Bright Data API (datasets/list, Web Archive search/dump, Web Unlocker zones).
    26 repo stars
  54. ▌
    DOCX Render · edwinhu
    Use when an EXISTING .docx, .doc, .pptx or .xlsx has to become a PDF or PNG — 'convert docx to pdf', 'docx to pdf', 'render this Word doc', 'word to pdf', 'export docx as pdf', 'make a pdf of this docx', 'pdf from the docx', 'render the document to PDF', 'the PDF has the wrong page count', 'why did the layout reflow'. Use proactively before handing any Word document to a human as a PDF, and INSTEAD OF hand-rolling soffice/libreoffice, even when no one says 'render'. NEGATIVE ROUTING: NOT for editing docx content (use the generic 'docx' skill), NOT for building a docx from markdown (use 'law-review-docx' for Bluebook footnotes or 'law-econ-docx' for author-date), NOT for building one from a Typst source (use 'docx-typst'), NOT for a damaged docx (use 'docx-repair'), NOT for inspecting or diffing individual slides (use 'pptx-render').
    26 repo stars
  55. ▌
    DOCX Repair · edwinhu bundle
    Use to REPAIR a .docx damaged by a Google Docs or Word Online round-trip — the package/XML wiring, the footnote markup, leftover content controls, and heading styling. Triggers: 'Word won't open the docx / says it's corrupt', 'Google Docs export broken', 'fix the customXML error', 'recover unreadable content', 'phantom blank page', 'repair this docx'; AND 'footnotes broken after Google Docs', 'supra notes wrong after coauthor edits', 'cross-references point to the wrong footnote', 'bio footnotes show numbers instead of symbols (*, †, ‡)', 'author note shows 1 2 3 not star dagger', 'footnote numbering starts at the wrong number', 'separator line missing', 'doubled footnote marks (**, ††)'; AND 'boxes around text after Google Docs', 'content controls / doubled boxes around paragraphs', 'remove the boxes Word draws around headings', 'heading text isn't styled as a heading', 'headings look different / inconsistent heading formatting', 'blank/empty heading lines'; AND 'clean up Google Docs XML cruft', 'strip redun
    26 repo stars
  56. ▌
    PPTX Render · edwinhu
    Use when the user asks to "render pptx", "show pptx slide", "compare with pptx", "pptx to image", "export pptx slide", "original slide", "show me the original", "what does the pptx look like", or needs to extract a specific PPTX slide's content for visual comparison.
    26 repo stars
  57. ▌
    Data Context · edwinhu
    This skill should be used when the user asks to 'set up data analysis for our database', 'extract tribal knowledge about dataset', 'generate data skill', 'document this dataset', 'what does this column mean', 'create data dictionary', 'help me understand this data schema', 'capture domain knowledge about our data', or needs to create a reusable data context skill from dataset expertise.
    26 repo stars
  58. ▌
    De AI Revise · edwinhu bundle
    ALWAYS use when prose needs to stop sounding machine-written — 'de-AI this', 'make it sound less like AI', 'this reads like ChatGPT wrote it', 'remove the AI-isms', 'de-tic this draft', 'humanize the prose', 'fix the AI writing tells', 'less AI-sounding', 'this doesn't sound like me', 'too many em-dashes and tricolons', 'it reads robotic', 'just flag the AI tells in this'. Use as the standard AI-prose pass before any draft ships, even if the user only says 'clean up the writing'. NEGATIVE ROUTING: this is the skill that EDITS the draft, and it runs detect-only on the same scorers when asked to scan rather than fix; reading the tic tables or asking what counts as an AI tell is ai-anti-patterns; validating a candidate phrase against the human corpus or adding a linter rule is ai-tic; grading a whole draft against the domain register and prose-quality rules is the writing-reviewer agent; judging whether text WAS AI-written is nobody's job here — this renders no verdict on authorship.
    26 repo stars
  59. ▌
    Gemini Batch · edwinhu bundle
    Use when the user says 'run this prompt over all the documents', 'process thousands of PDFs', 'extract fields from every filing', 'bulk LLM job', 'submit a batch job', 'use the Gemini Batch API', 'upload files to Gemini', or 'this is too many to do one at a time' - any large-scale LLM extraction or classification over many files. ALWAYS load before writing Gemini batch code, including the small test run.
    26 repo stars
  60. ▌
    Using Skills · edwinhu bundle
    Injected verbatim into every session by hooks/session-start.ts. Nothing triggers on this description — both invocation paths are off below.
    26 repo stars
  61. ▌
    Writing Econ · edwinhu
    ALWAYS load BEFORE drafting, revising or grading FINANCE or ACCOUNTING journal prose — 'write the paper', 'draft the introduction of my JF submission', 'revise Section 3', 'polish the job-market paper', 'does this read like a finance paper', 'tighten the abstract', 'is this well written for JFE/RFS/JAR/TAR', 'should I write we find or the paper shows', 'do I cross-reference by Section or Part', 'is agents jargon'. Covers Journal of Finance, JFE, RFS, Journal of Accounting Research, The Accounting Review, JAE, CAR, RAST, and the working and job-market papers aimed at them. This skill carries ONLY what is additional to the base register: load `writing-general` alongside it — the diction, tic, vindicated-phrase and formatting rules live there and are assumed here. Do NOT load this for a law review article or legal scholarship (use `writing-legal`) or for a comment letter, memo, brief or professional email (`writing-general` alone) — importing a finance rule into either of those makes the prose worse.
    26 repo stars
  62. ▌
    Court Dockets · edwinhu bundle
    This skill should be used when the user asks to "get the complaint PDFs", "harvest court documents", "pull the docket", "download the opinions", "get filings from Lex Machina", "Docket Alarm", "Bloomberg Law docket", "Delaware Chancery filings", "who filed this case", or needs court filings, docket entries or written decisions out of a commercial legal database.
    26 repo stars
  63. ▌
    Courtlistener · edwinhu bundle
    Use when the user says 'CourtListener', 'Free Law Project', 'RECAP', 'PACER data', 'court opinions', 'get the opinion text', 'federal dockets', 'delch', 'Delaware Chancery opinions', 'state court opinions', 'demand futility opinions', 'judicial financial disclosures', 'oral arguments', or needs case law, dockets or opinion full text for empirical legal research. Also use when someone assumes CourtListener is federal-only, or hits a token or human-verification wall on it.
    26 repo stars
  64. ▌
    Deep Research · edwinhu bundle
    ALWAYS load before attempting a broad web-grounded research report - "deep research this", "do a deep dive on X", "comprehensive research on X", "thorough investigation of X", "write me a research report on X", "everything you can find about X", "I need background on this industry/market/regulation", "the academic sources came up empty, look wider". Use even when the user never says "deep research" but wants a synthesized multi-source report. NOT for finding academic papers or citations - use the research, consensus and google-scholar skills first; this is the paid last resort.
    26 repo stars
  65. ▌
    Goal And Loop · edwinhu bundle
    Use when a session's stopping condition is being written or repaired — "set the goal", "write the /goal line", "what should the goal be", "give it a goal before I go to bed", "write the brief for the spawned agent", "it stopped overnight", "it idled while I was asleep", "it asked me a question instead of continuing", "why did it stop", "is the goal actually set", "make it keep working", "run this unattended", "leave it running overnight". Use proactively BEFORE handing work to any session that will outlive the user's attention — a spawned agent, a background job, a craft dispatch left running, or this session at night. NEGATIVE ROUTING: composing a craft run's own goal is craft-dispatch.sh, which calls compose-goal.sh and needs no help; spawning the session is agent-spawn; delegating a task to a subagent is farm-out. This skill owns the WORDING of the stopping condition, the standing authority that travels with it, and the proof that it actually landed.
    26 repo stars
  66. ▌
    Headline Card · edwinhu
    Use this skill when the user asks to add news headline cards, 'Last Week Tonight'-style cards, headline slides, news quote slides, or media quote cards to a Typst presentation. Also use when the user wants to modify existing headline cards (add/remove cards, change quotes, swap logos, fix layout issues). Trigger on: 'add a headline', 'news card', 'LWT card', 'headline slide', 'quote card', 'media quote', 'add a quote from [publication]'.
    26 repo stars
  67. ▌
    Law Econ DOCX · edwinhu bundle
    Use this skill to BUILD a Word manuscript from LAW AND ECONOMICS markdown — author-date citations plus a reference list, double spaced throughout, Latin Modern typography — for the Journal of Law and Economics, Journal of Legal Studies, JLEO, ALER, or an econ-flavored job market paper. Triggers: 'build the L&E paper', 'law and economics Word template', 'JLE submission docx', 'Journal of Legal Studies format', 'JLEO manuscript', 'author-date Word document', 'econ job market paper in Word', 'Chicago author-date docx', 'make the submission docx for JLE'. NEGATIVE ROUTING: NOT 'law-review-docx' (Bluebook footnotes, TOC and small caps — different citation model), NOT 'docx-typst' (source is Typst, not markdown), NOT the generic 'docx' skill (edits docx content), NOT 'docx-render' (renders an existing docx to PDF/PNG only).
    26 repo stars
  68. ▌
    Readwise Chat · edwinhu
    Use when the user asks a QUESTION of their reading library rather than for a keyword lookup — 'ask readwise', 'chat about my highlights', 'what do my notes say about X', 'summarize my reading on X', 'what have I read about proxy advisors', 'compare what I've read about X vs Y', 'what's my take on X based on what I've read', 'pull together my highlights on X'. Use proactively for synthesis across many documents. NOT for finding a specific highlight by keyword — use readwise-search instead.
    26 repo stars
  69. ▌
    Readwise Docs · edwinhu
    Use when the user says 'add to reader', 'save this article', 'read this later', 'put this in Readwise', 'list my documents', 'what's in my reading inbox', 'archive that article', 'tag this document', or 'delete that from Reader' - anything that lists, saves, updates or deletes documents in the Readwise Reader library. NOT for searching highlights (readwise-search) and NOT for bulk cleanup of stale documents (readwise-prune).
    26 repo stars
  70. ▌
    Skill Creator · edwinhu
    This skill should be used when the user asks to 'create a skill', 'improve a skill', 'edit a skill', 'add a skill to a plugin', 'add enforcement patterns', 'add Iron Laws or fact rows', 'fix a skill description', 'audit skill enforcement', or needs to substantially create or edit any SKILL.md file — including a single skill inside a plugin. Use plugin-creator only for plugin-level work (manifest, hooks wiring, multi-component scaffolding).
    26 repo stars
  71. ▌
    Source Verify · edwinhu
    Use when the user says 'verify my sources', 'check the citations', 'fact-check the footnotes', 'are my cites real', 'did I make this cite up', 'does the source actually say that', 'check this quote against the source', or 'source check before I submit'. Use proactively whenever a draft's citations or quotations have not been checked against the actual sources. NOT for Bluebook formatting - use bluebook or bluebook-audit.
    26 repo stars
  72. ▌
    Visual Mockup · edwinhu bundle
    This skill should be used when the user asks to 'mockup the layout', 'sketch the diagram', 'show me the layout before coding', 'draft the positions', 'quick visual of the layout', 'matplotlib mockup', 'interactive mockup', 'drag and drop layout', 'draw a rough layout', 'prototype the diagram', 'let me arrange the nodes', 'mockup the chart before CeTZ', or when you're about to write a diagram with 4+ nodes or a CeTZ chart and want to confirm the visual with the user first.
    26 repo stars
  73. ▌
    Visual Verify · edwinhu bundle
    This skill should be used when the user asks to 'verify visual output', 'check how it looks', 'render and review', 'visual verify', 'check the slide', 'does this look right', or when any task produces rendered visual output (slides, charts, documents, UI).
    26 repo stars
  74. ▌
    Writing Legal · edwinhu
    ALWAYS load BEFORE drafting, revising or grading LAW REVIEW prose — 'write the article', 'draft this Part', 'revise my note', 'polish the law review piece', 'does this sound like a law review article', 'edit my seminar paper', 'is this Part well written', 'should I write This Article or This paper', 'do I cross-reference by Part or Section', 'is pursuant to legalese'. Covers T14 flagship articles, student notes, seminar papers and any legal scholarship carrying footnotes and Bluebook short forms. This skill carries ONLY what is additional to the base register: load `writing-general` alongside it — the diction, tic, vindicated-phrase and formatting rules live there and are assumed here. Do NOT load this for a finance or accounting journal submission (use `writing-econ`) or for a comment letter, memo, brief or professional email (`writing-general` alone) — importing a law review rule into either of those makes the prose worse.
    26 repo stars
  75. ▌
    Bluebook Audit · edwinhu bundle
    This skill should be used when the user asks to 'audit footnotes', 'check Bluebook formatting', 'audit citations', 'run footnote audit', 'check my footnotes', 'bluebook audit', or needs systematic Bluebook compliance checking of a law review manuscript.
    26 repo stars
  76. ▌
    Google Scholar · edwinhu
    This skill should be used when the user asks to "search Google Scholar", "find academic papers", "scholar search", "lookup papers", "find citations", "academic search", "search for papers by author", "find journal articles", "get BibTeX", "cite this paper", "download paper", or needs to search Google Scholar for academic literature via the scholar CLI tool.
    26 repo stars
  77. ▌
    Notebook Debug · edwinhu
    ALWAYS use when an executed notebook has to be checked or has gone wrong - "debug this notebook", "why did the notebook fail", "which cell errored", "read the traceback from the ipynb", "the notebook ran but the output looks wrong", "did all the cells run", "papermill/jupytext/marimo execution failed", "inspect the notebook outputs". Use proactively before claiming any .ipynb executed successfully — never assert a notebook works without checking its outputs for tracebacks.
    26 repo stars
  78. ▌
    Plugin Creator · edwinhu
    This skill should be used when the user asks to 'create a plugin', 'scaffold a plugin', 'set up plugin structure', 'new plugin', 'edit the plugin manifest', 'wire plugin hooks', 'validate plugin structure', 'audit my plugin's enforcement', or needs plugin-level work spanning multiple components. Use proactively whenever plugin.json, marketplace.json or hooks/hooks.json is being edited, even if the user never says 'plugin'. NEGATIVE ROUTING: never invoke plugin-dev:create-plugin, plugin-dev:plugin-structure or plugin-dev:plugin-validator directly — this skill is the wrapper that adds the enforcement audit they lack. Creating or editing a single skill, even inside a plugin, goes to skill-creator; designing, repairing or auditing a multi-phase workflow goes to workflow-creator.
    26 repo stars
  79. ▌
    Law Review DOCX · edwinhu bundle
    Use this skill to BUILD a formatted Word document from LAW REVIEW / legal MARKDOWN drafts — Bluebook footnotes, TOC, small caps, styled tables and vector figures. Triggers: 'build the law review document', 'make the Word version of my article', 'turn my markdown draft into Word', 'export the article to docx', 'compile/finalize the draft', 'make the submission docx for the law review', 'apply the law review template', 'the figure is blank in Word', 'fix the widows in the compiled PDF'. Use proactively once a legal markdown draft is finished and a Word file is implied but unnamed. NEGATIVE ROUTING: NOT 'law-econ-docx' (author-date citations plus a reference list, for JLE/JLS/JLEO/ALER — different citation model), NOT 'docx-typst' (source is Typst, not markdown), NOT the generic 'docx' skill (edits docx content), NOT 'docx-render' (renders an existing docx to PDF/PNG only), NOT 'docx-repair' (fixes a cloud-editor-damaged docx).
    26 repo stars
  80. ▌
    Pattern Capture · edwinhu bundle
    This skill should be used when the user asks to 'find repeated feedback', 'what do I keep correcting', 'capture this pattern', 'DRY my prompting', 'stop repeating myself', 'turn this into a check', 'automate this correction', or when the same type of feedback has been given 3+ times across sessions.
    26 repo stars
  81. ▌
    Readwise Search · edwinhu
    ALWAYS use when the user wants something out of their own reading library — "what did I highlight about X", "search my highlights", "find in readwise", "my notes on X", "did I save anything on Y", "what have I read about Z", "find that quote I saved", "pull quotes from my reading", "who was it that said X". Use proactively before answering from memory whenever the user refers to their own reading or annotations. NOT for conversational summarizing across highlights (readwise-chat), listing or saving Reader documents (readwise-docs), or cleanup (readwise-prune).
    26 repo stars
  82. ▌
    UI JSON Capture · edwinhu bundle
    Use when the user asks to 'scrape Lex Machina', 'capture Bloomberg Law results', 'get all the search results', 'export more than the row cap', 'the export only gives me 1,000', 'pull the whole docket', 'grab every page of results', 'capture the JSON behind this page', 'page through this site and save the data', or wants the full result set out of an authenticated research UI (Lex Machina, Bloomberg Law, Westlaw, Docket Alarm, UniCourt) whose export is capped or absent. Also use when a site's results are clearly JSON-backed but there is no documented API.
    26 repo stars
  83. ▌
    Writing General · edwinhu
    ALWAYS load BEFORE writing or revising any serious prose a human will read — 'write the memo', 'draft the comment letter', 'draft this section', 'polish the brief', 'revise this email', 'tighten the introduction', 'is this well written', 'review my prose', 'fix the writing here', 'make this sound less like AI', 'should I say we or the paper'. This is the BASE register: the Strunk-derived diction rules, the prohibited-construction tic table, the vindicated phrases and the formatting rules that hold for every domain, plus the register for prose that is neither a law review article nor a journal submission (comment letters, memos, briefs, white papers, board memoranda, professional email). Load it before the first sentence is written, not after. For a T14 law review article or legal scholarship carrying footnotes, load `writing-legal` ALONGSIDE this one; for a finance or accounting journal submission or job-market paper, load `writing-econ` alongside this one — those two carry only what is ADDITIONAL to this bas
    26 repo stars
  84. ▌
    AI Anti Patterns · edwinhu bundle
    ALWAYS load before finalizing ANY written prose, and whenever text is suspected of being machine-written - "does this sound like AI", "make this sound human", "clean up the AI-isms", "did a bot write this", "check this draft before I send it", "review this for AI tells", "this reads like ChatGPT", "is this student paper AI-generated", or before handing back any draft, memo, email, or article you wrote. Use proactively even if the user never mentions AI writing.
    26 repo stars
  85. ▌
    Crsp Lseg Splice · edwinhu bundle
    Use when "CRSP is stale / out of date", "CRSP only goes through December", "my panel ends in December", "why do my returns stop", "extend CRSP to today", "fill forward CRSP with LSEG", "current stock prices for my CRSP panel", "up-to-date returns for permnos", "splice CRSP and LSEG", "CUSIP to RIC for a CRSP universe", "backfill the CRSP gap", or any request to carry a CRSP daily/monthly stock series past CRSP's last data date using LSEG/Refinitiv. Use proactively whenever a CRSP panel has to reach a date after CRSP's annual cutoff, even if the user never mentions LSEG — CRSP returns a short panel without erroring, and a naive concat fabricates the seam return. NEGATIVE ROUTING: a CRSP query that stays inside CRSP's coverage, or CIZ table and column names, is crsp-v2; LSEG session, quota, entitlement or general symbology questions are lseg-data; raw WRDS PostgreSQL access and connection patterns are wrds — this skill covers only the join between CRSP and LSEG.
    26 repo stars
  86. ▌
    Workflow Creator · edwinhu bundle
    Design, repair, or audit a multi-phase workflow. Use when the user says "create a workflow", "design a workflow", "scaffold a new workflow", "add a phase to this workflow", "improve/repair/redesign this workflow", "migrate this workflow", "audit this workflow", "why doesn't my workflow's gate work", "check this workflow's gate", "the gate passes when it shouldn't", or "/workflow-creator". Covers all three — fresh creation, corrective improvement, and read-only audit. Use proactively when a workflow's gate looks vacuous or wc-probe reports CLEAN over nothing, even if the user never says "workflow". NEGATIVE ROUTING: a plain SKILL.md with no phases, no craft dispatch and no computed gate goes to skill-creator, not here — this skill owns the artifacts that pass parameters to craft's workflow.js and are judged by wc-probe; plugin manifests, hooks wiring and multi-component scaffolding go to plugin-creator.
    26 repo stars
  87. ▌
    Obsidian Organize · edwinhu
    Use when the user says 'organize my notes', 'clean up the vault', 'tidy the vault', 'where should this note go', 'file this note', 'move these notes', 'rename this note', or 'the vault root is a mess' - and ALWAYS before creating a new note anywhere in the Obsidian vault, so it lands in the right PARA folder under the right name. NOT for searching notes or appending to the daily note - use the obsidian skill.
    26 repo stars
  88. ▌
    Fuzzy Name Matching · edwinhu bundle
    Use when linking or deduping datasets by entity NAME because no shared key exists — 'fuzzy match', 'fuzzy name matching', 'entity resolution', 'record linkage', 'match company or person names', 'match these on the firm name', 'just merge these on company name', 'dedupe entity names', 'name-based join', 'these two files have no common id', or any use of char n-gram TF-IDF, cosine similarity on names, `sparse_dot_topn`, or RapidFuzz at scale. Use proactively whenever a join is about to be keyed on a name string, even if the user never says 'fuzzy'. NEGATIVE ROUTING: identifier bridging that a real link table already covers (gvkey ↔ permno via CCM, cik ↔ gvkey via wciklink) is the wrds skill — come here only for identifiers that genuinely do not cross vendors; the surrounding merge, sample-coverage and pipeline work is ds, not this skill.
    26 repo stars
  89. ▌
    Marimo Serve · edwinhu bundle
    Use when several marimo notebooks should be reachable at once rather than one `marimo run` per file — 'serve my notebooks', 'host the marimo apps', 'run all the notebooks', 'give me a URL for these notebooks', 'share these dashboards', 'put this on the LAN', 'expose marimo on the tailnet', 'JupyterLab-but-for-marimo', 'let my coauthor click through these'. Also covers the editor-on-a-directory case. NOT for authoring or debugging one notebook (marimo) and NOT for pairing on a live kernel (marimo-pair).
    26 repo stars
  90. ▌
    Npx Ownership Panel · edwinhu bundle
    ALWAYS use before building anything that joins proxy votes to ownership — 'build the N-PX panel', 'proxy voting panel', 'how did index funds vote on this item', 'passive vs active voting', 'fund-level votes with ownership attached', 'voting by block', 'link ISS funds to CRSP', 'risk.voteanalysis_npx', 'N-PX votes by meeting/agenda item', 'institutional ownership per proposal', '13F or S12 holdings joined to votes', 'build the ownership panel'. Use proactively instead of writing a local pipeline — the panel already exists end-to-end on the WRDS grid. NEGATIVE ROUTING: querying the underlying ISS, Thomson or 13F tables directly, WRDS connection patterns, and the data-defect reference are the wrds skill; generic data building, merging and profiling with no proxy-vote leg is ds — this skill owns the assembled panel and its DAG, not raw table access.
    26 repo stars
  91. ▌
    Replication Package · edwinhu bundle
    ALWAYS use when code and data have to leave the machine as a self-contained archive for someone who did not write them — 'build the replication package', 'package this for counsel', 'send the workpapers', 'production archive for the opposing expert', 'replication archive', 'they want the code and data', 'put together what they asked for in the document request', 'make a workbook for the client', 'archive this analysis so someone else can check it', 'write the runbook', 'they need to be able to rerun the pipeline', 'document how the data was collected'. Use proactively whenever an expert report, a submission or a document request implies handing over the underlying work, even when the user only says 'zip it up'. NEGATIVE ROUTING: building the analysis itself goes to `ds`; a Word deliverable goes to `law-review-docx` or `docx-typst`; a single spreadsheet with no archive around it is plain `xlsx`.
    26 repo stars
  92. ▌
    Audit Check · edwinhu
    Phase 2: Run mechanical checks and Gemini formatted audit
    26 repo stars
  93. ▌
    Audit Report · edwinhu
    Use when a Bluebook footnote audit's findings need to be turned into a report the user can review before any corrections are applied - 'show me the audit results', 'what did the audit find', 'write up the citation problems', 'give me the report', 'which footnotes are broken', 'summarize the Bluebook errors'. Produces scratch/AUDIT_REPORT.md. NOT for running the checks themselves or applying fixes.
    26 repo stars
  94. ▌
    Audit Verify · edwinhu
    Use immediately after Bluebook corrections have been written into a DOCX, before archiving — 'verify the fixes', 'did the corrections apply', 're-scan the corrected docx', 'check the small caps got fixed', 'confirm the footnotes are clean now', 'run the verify phase'. ALWAYS run this rather than trusting that applied fixes landed; silent fix failures are common.
    26 repo stars
  95. ▌
    Audit Correct · edwinhu
    Phase 4: Apply corrections to DOCX
    26 repo stars
  96. ▌
    Audit Extract · edwinhu
    Phase 1: Extract footnotes from DOCX with formatting annotations
    26 repo stars