ericmjl
- 23 skills
- 0 followers
- 1 week ago last updated
- ▌ Video Script Writing · ericmjl bundleWrite and revise video scripts that hold viewer attention to the end and drive the desired action, grounded in retention and persuasion research (information-gap curiosity, Zeigarnik open loops, hook-concreteness studies, narrative transportation, speech-rate and scene-cut experiments). Use when the user asks for a video script, YouTube script, or explainer script; a founder, brand-story, or talking-head video; a landing-page, marketing, demo, or testimonial video; a video ad or VSL; or a short-form script (Shorts, Reels, TikTok). Also use when improving an existing script's hook, pacing, retention, or CTA, or when asked whether a script will hold attention. Covers hook tests, loop architecture, spoken-register drafting, production specs (cut rhythm, captions, words-per-minute bands, placement), and per-purpose playbooks with benchmarks.
- ▌ Publish To Google Docs · ericmjl bundleQuickly publish markdown notes to styled Google Docs using pandoc and a Word template. Use when creating Google Docs from markdown, applying branding to documents, or pushing content to Drive for sharing.
- ▌ Awesome Marimo Notebook · ericmjlBuild an awesome marimo notebook that brings a research paper or dataset to life — for competitions, tutorials, demos, or blog companions. Use when asked to "make an awesome marimo notebook," "build a notebook for this paper," "create a competition submission," or pair-program an interactive research explainer on molab.
- ▌ Epistemic Resourcefulness · ericmjlBreaks the cycle of repeated failed attempts by redirecting the agent to find the authoritative source of truth about a system's structure before trying again. Trigger this skill when: (1) the same command or query has failed 2+ times with variations, (2) output is garbled/binary and unreadable, (3) guessed field names, endpoints, or flags keep returning errors, (4) file/directory scanning is producing no useful signal. In short: if you're brute-forcing and it's not working, stop and use this skill.
- ▌ Mempalace · ericmjlUse the MemPalace CLI to persist, search, and manage AI memory across sessions. Triggers whenever the user asks to remember, recall, save, store, or retrieve information that should persist across conversations — including past decisions, preferences, facts about people or projects, conversation history, and any verbatim content the user wants preserved. Also triggers when the user mentions "palace", "wings", "rooms", "drawers", "knowledge graph", "AAAK", or when they want to search through historical context, traverse connections between topics, or check what their AI knows. Mirrors the MemPalace MCP server tools: each CLI command maps to an MCP tool with an equivalent trigger condition.
- ▌ Slack CLI · ericmjl bundleUse Slack CLI (`slack`) for app lifecycle and workspace operations including login/logout, create/init, run/deploy, manifest validation, trigger management, app install/uninstall, environment management, and diagnostics. Use when users ask to run or troubleshoot commands like `slack create`, `slack run`, `slack deploy`, `slack trigger`, `slack manifest`, `slack auth`, `slack activity`, `slack datastore`, `slack env`, or request help-first progressive discovery with `slack help` and `slack SUBCOMMAND --help`, plus version/documentation alignment and stale-skill refresh.
- ▌ Voss Advisor · ericmjl bundleAdvanced negotiation and communication advisor grounded in Chris Voss's tactical empathy methodology (Never Split the Difference, The Black Swan Group). Use this skill whenever the user needs help with any interpersonal situation involving influence, persuasion, or navigating difficult dynamics. This includes but is not limited to: analyzing conversations, call transcripts, or email threads; preparing for negotiations (salary, vendor, client, partner); drafting tactful responses; handling pushback, objections, or conflict; navigating difficult workplace conversations; preparing for performance reviews or raises; buying a car, house, or any big purchase; dealing with landlords, contractors, or service providers; resolving personal disagreements; practicing negotiation through role-play; or any situation where the user says things like "how should I respond to this", "they're pushing back", "I need to have a tough conversation", "how do I ask for...", "they ghosted me", "I'm not sure how to handle this person",
- ▌ Skill Creator · ericmjl bundleGuide for authoring Agent Skills with strong YAML `description` triggers, progressive disclosure, and bundled resources. Use when creating or updating a skill, running init_skill.py or package_skill.py, or improving a bland skill description so agents load the skill on the right user tasks.
- ▌ Atomic Commits · ericmjlBreak unstaged or mixed changes into small, atomic, logical git commits with Conventional Commit messages. Use when the user asks to commit, stage, or split changes — e.g. 'help me commit', 'commit my changes', 'break these into logical commits', 'what should I commit first', 'stage my changes', 'commit atomically', or 'make atomic commits'. Uses git diff, git add -p, and Conventional Commits (feat:/fix:/refactor:/chore:/docs:/test:/style:/perf:/build:/ci).
- ▌ Marketing Copy · ericmjl bundleWrite, review, and critique marketing copy using proven copywriting frameworks. Use when the user asks to write or generate sales copy, headlines, bullet points, email teasers, email sequences, sales letters, sales pages, landing page copy, social media ad copy (Facebook, Instagram, LinkedIn), product descriptions, Amazon listings, or webinar registration copy. Also use when the user asks to review, critique, audit, score, or improve existing copy. Frameworks include customer avatar definition (F.R.E.D.), headline formulas, the ultimate bullet formula (feature + benefit + meaning), PAS / benefit / before-after-bridge sales formulas, email subject-line patterns, offer building and risk reversal, stealth closes, hooks and angles, and swipe file methodology. Produces multiple variations by default.
- ▌ Remotion Video · ericmjl bundleCreate animated videos using Remotion from topics, product URLs, Google reviews, talking-head videos, CSV data, or channel/brand URLs. Supports 6 video types: educational explainers, product launch demos, testimonial/social proof, avatar video overlays, data visualization dashboards, and lower third overlays. Each follows a 2-step workflow: research/scrape/analyze then design and animate with spring animations, SVG diagrams, and count-up effects. Requires the Remotion best practices skill (install with `npx skills add remotion-dev/skills`). Use when the user asks to create a Remotion video, explainer video, educational video, product demo video, testimonial video, video with animated overlays, data visualization video, animated dashboard, lower third, transparent overlay, short-form vertical video for mobile, or multi-product video from a website.
- ▌ Scientific Eda · ericmjl bundleDefensive exploratory data analysis for scientific data (CSV, FASTA, etc.). Context-first, human-guided; one plot at a time, ask why before executing, append-only journal per session, scripts with PEP723 and uv run, WebP plots. Use when opening data files for EDA or when the user wants guided scientific data exploration.
- ▌ PDF Form Filler · ericmjl bundleFill flat PDF forms that have NO fillable fields (school enrollment packets, medical intakes, waivers, government paperwork) and reuse a prior year's filled PDF as the source of answers. Requires a vision-language-model coding agent (renders pages to images and looks at them); there is no non-VLM fallback. Use when: the user asks to fill out / complete / fill in a PDF form, especially recurring yearly forms (enrollment, renewal, intake) where a previously filled copy exists; when pypdf reports zero AcroForm fields but the form has lines and labels; when the user says 'agent, fill this form for me'; when transplanting prior answers onto a new PDF template; when reproducing a scanned or drawn signature as vector ink from an old PDF; or when a filled form's text overlaps lines or labels and placement needs verification against rendered pixels.
- ▌ Coherent Writing · ericmjl bundleImprove coherence in drafts through a five-pass sub-agent workflow: resolve cross-draft argument conflicts, fix within-paragraph logic (self-contradictions, sudden topic jumps, disconnects, unsignaled pivots), smooth section transitions, smooth paragraph-boundary transitions, and run a final coherence audit. Use when a user says things like 'make this coherent', 'tighten the flow', 'this feels choppy', 'this paragraph contradicts itself', 'fix the logic jumps inside this paragraph', 'the sentences don't connect', 'can you smooth transitions', or asks to revise prose in Markdown, notes, essays, blog posts, emails, or docs so ideas connect cleanly without adding new points.
- ▌ Typewriter Video · ericmjl bundleCreate VS Code-style typewriter animation videos with mechanical keyboard sounds. Supports 4 typing speeds, ghost text autocomplete, strikethrough corrections, emoji picker, file tab switching, syntax highlighting (6 languages), Chinese IME (pinyin + direct mode), inline images, image stacks, animated checkboxes, Excalidraw hand-drawn diagrams, 8 visual themes, 4 sound packs, and A-roll narration sync. Built on Remotion (React-based video rendering). Use when the user wants to create code typing videos, explainer B-roll, or typewriter-style animations.
- ▌ Design Driven Dev · ericmjl bundleGuide for design-driven development with prescribed folder structure. New features use full workflow (HLD → LLD → EARS). Bug fixes skip doc creation but verify intent coherence.
- ▌ Gh Daily Timeline · ericmjl bundleReports your GitHub activity for a specific day using the gh CLI, showing commits, issues, and activity timeline. Use this when you need to review what you accomplished on GitHub for a particular date.
- ▌ Agents Md Improver · ericmjlProposes updates to AGENTS.md so repo-local coding-agent instructions stay accurate, non-contradictory, and consolidated. Use when the user corrects the agent (e.g. do not do X, always do Y, from now on, remember this), asks to edit or sync AGENTS.md, CLAUDE.md, .claude/CLAUDE.md, or GEMINI.md, wants one canonical instruction file or to deduplicate agent docs, or flags conflicting or outdated repository agent rules.
- ▌ HTML Presentations · ericmjl bundleCreate single-file HTML slide presentations with vanilla JS/CSS. Themed (terminal.css, catppuccin, nord), keyboard-navigable, with inline SVG diagrams and animations. Use when the user asks for an HTML presentation, slide deck, or single-file slides without a framework.
- ▌ Ml Experimentation · ericmjl bundleConduct machine learning experiments from planning through evaluation and report writing. Use when running ML experiments, testing hypotheses, training models, or writing up results. Covers single-hypothesis scoping, fast iteration loops, targeted logging, JOURNAL.md protocol, data-backed diagnostic plots, and scientific report writing.
- ▌ Xarray Linked Data · ericmjl bundleDesign, build, and manipulate xarray data structures for highly linked, multi-dimensional data where measurements, derived estimates, and model outputs share coordinates and must stay synchronized. Use when: structuring laboratory/experimental/multi-assay data in xarray (Dataset or DataTree); designing coordinate systems for linked data; writing custom xarray indexes (custom Index subclasses, CoordinateTransforms, interval-based or N-D derived coordinate indexes); selecting/aligning/computing across linked xarray variables; linking data across experiments through shared coordinates or custom indexes; reading or manipulating xarray objects to help a user accomplish analysis goals; converting scattered CSV/Parquet/HDF5 workflows into unified xarray datasets. Covers: progressive data accumulation, coordinate design, sel/isel/where/align, groupby/rolling/ coarsen/resample, Dataset vs DataTree, custom index patterns (PeriodicIndex, RangeIndex, CoordinateTransform, NDIndex, DimensionInterval), and cross-experiment
- ▌ Gh Activity Summary · ericmjl bundleGenerate a plain-language activity report of your GitHub work for a given date range, including commits, pull requests, reviews, issues, and comments. Use this when you need to summarize what you've accomplished on GitHub for status updates, retrospectives, or tracking your work.
- ▌ Cybersecurity Review · ericmjl bundlePerform comprehensive cybersecurity code review across 9 security dimensions: injection prevention, authentication/authorization, secrets management, supply chain security (including CI/CD pipeline integrity), cryptography, secure configuration/API security (including SSRF), error handling/logging/resource safety, LLM/AI application security, and infrastructure/API protocol security (GraphQL, Kubernetes, WebSockets, OAuth 2.0, gRPC). Use when reviewing newly written code, auditing existing repositories, evaluating open source projects, or assessing pull requests for security vulnerabilities. Triggers include requests like "security review", "check for vulnerabilities", "audit this code", "cybersecurity review", "is this code secure", or "check this PR for security issues".