audit-noise
Classify tracked markdown for five noise shapes — historical citations, ghost refs to ephemeral working-directory paths, "Why this file exists" preambles,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
Writing & research
14,701 results
book-distill
Distill a technical book (PDF or EPUB) into concept-organized skill reference files via a structured multi-session pipeline. Use when: 'distill this book',…
co-write
Run a co-writing session and generate titles and high-volume options with Pat Pattison's methods — the No-Free-Zone co-write protocol and feedback discipline,…
compress
Compress (tighten, shorten, trim) markdown files by dropping flavor — filler, hedging, articles — while preserving all content (directives, qualifiers,…
do-your-research
Re-anchor research and no-assumptions discipline mid-session, then self-audit and correct the current work. Use when: 'do your research', 'you're guessing',…
do-your-research-deep
Escalate research discipline to a heavy verification fan-out over a TYPED FULL INVENTORY of the session's claims — assumptions, asserted facts, concrete…
doc-architecture
Generate architecture documentation using arc42 or C4 model. Use for creating system context, container, and component diagrams with narrative.
explain
One-shot plain-language explainer — drops any concept, code, error, architecture, or the previous assistant response to genuinely plain words (concrete…
object-writing
Generate raw sensory material and images with Pat Pattison's methods — object writing (sense-bound, 90-second timed dives, Rusty's-collar/Kami-kazi), metaphor…
point-dont-copy
Re-anchor pointer-over-copy discipline, then audit the work in flight for copied content, internal-name coupling, and closed capability lists, and correct by…
practice
Build a songwriting practice habit with Pat Pattison's curriculum — the daily object-writing/craft routine and numbered exercises drawn from all four books…
research-deep
Dispatch deep external research to the heaviest isolated execution tier available — a workflow engine, a forked subagent, or inline as last resort — keeping…
teach
Interactive multi-session learning coach for general topics or repo-grounded concepts; also a single-session domain primer (primer action). Use when: 'teach…
youtube-digest
Watch YouTube videos, extract transcripts, harvest links, research claims, and synthesize repo-applicability recommendations. Use when: 'youtube',…
video-human
Makes a script, caption, post or video description sound like the creator instead of a chat model. Use when the user says humanize, sounds like AI, sounds…
changelog
Use for writing, reviewing, editing, or generating Meteor release changelog entries. Defines canonical file locations, naming rules, required section…
docs-gap
Use when analyzing release branch changes for missing user-facing documentation. Compares the release branch against devel, filters for user-facing changes,…
mdx
Creates content with MDX including Markdown with JSX, custom components, and frontmatter. Use when building content-heavy sites, documentation, blogs, or…
expired-patent-scout
Find recently expired patents relevant to specified brands, products, or technology areas and develop evidence-backed product opportunity leads. Ask for target…
patent-prosecution-agent
Use this skill for responding to patent office actions, examiner rejections, and patent prosecution. Triggers: "office action", "examiner rejection", "patent…
research-report
Summarize deep research results into markdown report, cover all fields, skip uncertain values.
contradiction-flag
Surfaces contradictory evidence - studies moving the same metric in opposite directions - rather than a smoothed answer. Use on "do the studies agree", "any…
insight-brief
Drafts the cited insight brief with the provenance and usage-rights record attached. Use to close every insight run: "draft the brief", "write it up for the…
research-retrieve
Retrieves and ranks prior research, panel extracts and campaign results relevant to the question. Use when the user says "what do we already know about…