Research & Search

natsufox Bundle

Convert stored Tapestry artifacts into higher-level synthesis. Use when a user wants interpretation, consolidation, research notes, or analysis built on top of an already-ingested URL or note.

natsufox Bundle

Manage RSS/Atom feed subscriptions and refresh them into the Tapestry knowledge base. Use when the user wants to list, add, remove, or refresh subscribed feed sources by name rather than by URL.

odinmb Skill

Integrate external info (research, status changes, reference material, deliverables) into the ops repo's knowledge base. Drop files in .update/ or pass content inline.

odinmb Skill

Execute an approved ops plan — research, write, review, update state, archive. Use after /plan approval. Not for code.

odinmb Skill

Find new directions for an ops project — adjacent opportunities, strategic gaps, preparatory research. Use when known work is well-mined and you need to look outward.

panyuxin6 Bundle

Review code and machine-consumed implementation artifacts for defects, risks, quality, correctness, requirements, or standards. Use when the user requests an implementation review, findings, or a review conclusion, including focused reviews. Exclude prose-document review and requests only to read, explain, summarize, map, or trace implementation; neutral verbs such as check or inspect alone do not establish review intent.

pandemonium-research Bundle

Produces structured summaries of academic or technical papers. Fills a consistent template covering abstract, key contributions, method, results, limitations, and relevance. Calibrates terminology and depth to a named audience using the shared audience personas reference — so the summary is useful to the right reader, not just accurate.

pandemonium-research Skill

Explains complex technical topics in plain language calibrated to a named audience. Loads a shared audience personas reference to determine vocabulary level, assumed prior knowledge, and preferred explanation style — so the explanation lands for that specific reader, not for a generic one.

sentimperior666 Bundle

Run the TrialError session boot ritual at the start of a research-harness orchestrator session on a TrialError-scaffolded program — verifies the law pin, binds the account, and surfaces dangling launches, unread inbox, budget headroom, and the last handoff. Use this at the start of an orchestrator session, or when SessionStart reported it could not boot automatically.

sentimperior666 Bundle

Answer a research question against the ingested corpus, paper-qa-shaped — search, gather evidence with citations, draft an answer, then re-search on any gap before finalizing. Use this whenever the user asks a question that should be answered FROM the corpus (not from general knowledge), or asks for a literature summary/survey over what's already ingested.

sentimperior666 Bundle

Guided procedure to bring an existing (non-TrialError) research project into TrialError WITHOUT moving or restructuring it — inventory the foreign project, interview the user on what maps where, bridge via trialerror.toml [paths] + [paths].ingest_roots (or a directory junction or symlink when a true link is unavoidable), register sources, and validate with doctor + a search smoke. Use this when the user has an existing research project (papers, notes, a corpus, ledgers, a differently-shaped repo) organized their own way and wants to start using TrialError against it, or asks how to "import"/"switch to"/"migrate into"/"get started with" TrialError without losing or restructuring their existing files.

cygnusfear Skill

Use when conducting research, oracle investigations, or delphi consultations. Save findings as mai notes with proper tags and structure.

deanpeters Bundle

Pressure-test TAM, SAM, SOM, and other market estimates. Use for market definition, segmentation, provenance, reachability, pricing, conversion, timing, sensitivity, and decision relevance; not generic market research.

dirknicol Bundle

Use this skill when the user wants to plan, conduct, or synthesize customer research — interviews, surveys, win/loss, voice-of-customer, support ticket analysis, sales call mining, review analysis, or community listening. Triggers include any mention of 'customer research', 'customer interviews', 'voice of customer', 'VoC', 'win-loss', 'JTBD', 'jobs to be done', 'interview synthesis', 'research synthesis', 'review analysis', 'support ticket analysis', or 'qualitative research'. Implements a three-stage workflow: inputs (multi-source data) → AI processing + structure (transcribe, tag, cluster) → human synthesis (themes, decisions, recommendations). Reads `pmm-context.md` first. Outputs themed insight clusters with supporting quotes, a synthesis brief, and downstream recommendations. Do NOT use for quantitative-only market sizing or for persona artifact creation — `personas` skill handles persona output.

dufeiyang123 Bundle

Use when an active Subagent-Driven Evidencecraft Run has explicit user authorization for parallel execution and at least two dependency-ready Work Packages may be independent.

elizaos Bundle

Review and test current SlopDotCash/asi pull requests, finish mission-aligned open issues through pull requests, restore main workflow health, then hill-climb continual-RL benchmarks, produce measured research advancement, or fix a reproduced bug. Do not use for generic improvements, cleanup, or speculative polish.

elizaos Bundle

Independently evaluate whether a SlopDotCash/asi contribution delivers a reproducible hill climb, measured research advancement or refutation, or an actual reproduced bug fix. Reject generic improvements, cleanup, and trivial work.

erhwenkuo Bundle

Natural language queries to the knowledge graph. Search past reports, screenings, trades, research, and market context.

erhwenkuo Bundle

Deep research on stocks, industries, markets, and business models. Integrates Grok API (X/Web search) and yfinance for multi-angle analysis reports.

ethanaubuchon Skill

Use at the start of /research and other workflow recipes to establish vault grounding. Loads vault bootstrap (profile.md), checks inbox, and pre-warms project context if a topic anchor is implied. Repo/git detection lands with /plan and /implement.

ethanaubuchon Skill

Use during /research (or any recipe) to send 1-3 research queries in parallel — vault or web targets — and aggregate compressed findings. Routes each query to vault-researcher or web-researcher based on target. Hosts the cross-verify consent gate so any inline-research caller (/research, /design, /decompose) inherits source-bias mitigation without duplicating logic.

45ck Skill

research-question-refiner

45ck Skill

literature-theme-extractor

adamjali Bundle

Research a prospect, evaluate fit, draft a personalized cold email, preview it to yourself, send it via Resend, and track it in a bounded ledger. Use when the user asks to "research a company/prospect", "check out this lead", "draft a cold email", "send cold outreach", "outreach to this business", "deep dive on this prospect", "add to my prospect list", or "follow up". Config-driven: you set your sender identity, product, and ideal customer in references/config.md — the skill stays generic across industries.

alexferrari88 Bundle

Hermes-native deep research protocol for multi-source synthesis, verification, parallel subresearch, and decision-grade reporting using web_search, web_extract, browser fallback, delegate_task, and Python-backed scoring.

alibaba Skill

Run the evidence loop of one long-horizon GPU kernel optimization episode. Use this skill to reconstruct the incumbent, profile and localize a bottleneck, research progressively, plan one coherent direction, implement and repair, validate development correctness and performance, and record every decisive experiment in the episode journal.

chasepassion Skill

Helps users design, optimize, and review the structure and content of speeches, presentations, and persuasive communication in a wide range of high-stakes scenarios. Applicable situations include, but are not limited to: startup pitches and co-founder recruiting, research presentations and thesis defenses, job talks and academic interviews, product demos and investor pitches, lab meetings and progress updates, public speaking and TEDx-style talks, conference presentations and panel remarks, oral exams and qualifying defenses, expressing viewpoints and persuading others, upward reporting and performance reviews, and internal proposals and solution walkthroughs.

chemaw8 Skill

Estándar Kit Chema para investigar con fuentes — comparativas de proveedores o herramientas, estado del arte, normativas, mercado, "qué hay sobre X". Úsala al pedir "investiga", "busca información sobre", "compárame opciones de", "qué dice la industria de". Obliga a usar varias fuentes independientes, verificar afirmaciones clave contra la fuente original y citar con URL y fecha.

chemaw8 Skill

Estándar Kit Chema para repartir un trabajo entre varios agentes en paralelo — barridos amplios ("revisa los 24 proyectos", "todos los archivos de"), auditorías, migraciones, verificación de un entregable desde varios lentes, y material que no cabe en una ventana. Úsala ANTES de lanzar un workflow, un fan-out de subagentes o una corrida "ultracode", y también para decidir si NO conviene repartir. Frases gatillo "ultracode", "en paralelo", "reparte esto", "lanza varios agentes", "audita todo", "barre el repo", "revisa cada uno de", "compara estas 5 opciones", "es mucho material", "desde varios ángulos". Define la topología (quién lee y quién escribe), cuántos agentes, el contrato de cada uno y la verificación; el núcleo decide CUÁNDO delegar y con qué modelo. No sustituye a la skill del dominio: va junto con kit-research si es investigación con fuentes, y con kit-propuestas si se pidió council o evaluar una decisión — esas ponen el estándar del entregable, esta solo el reparto.

chgagne Skill

Use when working on a Digital Research Alliance of Canada (DRAC, Alliance, formerly Compute Canada) HPC cluster such as Narval, Rorqual, Fir, TamIA, Killarney, Vulcan, Nibi or Trillium — including ssh to *.alliancecan.ca failing with "Permission denied (keyboard-interactive)", sinfo/sacctmgr reporting "command not found" over ssh, submitting or monitoring Slurm jobs (sbatch, squeue, sacct, job arrays, GPU allocations), choosing between clusters, staging data into /project or /scratch, or jobs stuck PENDING.

chgagne Bundle

Use when finding related work a draft may have missed, checking whether a contribution has already been published, or mapping what a research area looks like. Triggers on "what related work did we miss", "has this been done before", "is our contribution novel", "map this field", "survey the literature on X", or a paper draft whose related-work section looks thin.

chgagne Skill

Use when working with a researcher on a long-running research project across many sessions — opening or closing a session, choosing a direction, method or scope, deciding whether to ask or act, planning what to run next, or writing up a result. Also when a published number failed to reproduce, a session ended with no record, a decision got made unilaterally, a write-up did not land, or the work has drifted from the research questions.

coderwanfeng Bundle

通过对话引导用户创建个人网站（博客/知识库/AI 导航/作品集/简历），选择技术栈、目标目录后一键生成项目并自动打开预览。Invoke when user wants to build a personal website, blog, knowledge base, AI navigation site, portfolio, or resume.

commonhuman-lab Skill

Binary analysis and reverse engineering workflow using checksec, strings, binwalk, radare2, ropgadget, and gdb for CTF and vulnerability research

conorbronsdon Bundle

Guest Circuit — Podcast-Appearance Research for Booking

conorbronsdon Bundle

Pre-investment research and deal-memo generation for angel investors. Use when asked to "diligence [company]", "research this startup for an investment", "build a deal memo", or to prep for a founder call. Runs parallel web research with strict citation rules and produces a nine-section memo that separates verified facts from claims. Never outputs an invest/pass recommendation.