Comments
Code comments and annotations
golang-swagger
by jangrui
"Golang OpenAPI/Swagger documentation with swaggo/swag — annotation comments (@Summary, @Param, @Success, @Router, @Security), swag init code generation, framework integrations (gin, echo, fiber, chi, net/http), security definitions (Bearer/JWT, OAuth2, API key), and struct tags (swaggertype, enums, example, swaggerignore). Apply when adding or maintaining Swagger/OpenAPI docs in a Go project, or when the codebase imports github.com/swaggo/swag, github.com/swaggo/gin-swagger, github.com/swaggo/echo-swagger, github.com/swaggo/http-swagger, or github.com/swaggo/files."
diff-review
by Mone-Lee
Use when the user types /diff-review or asks to review the current workspace diff in a local GitHub-style viewer with comments, Markdown preview comments, and minimal AI prompt copying.
sizing-a-ticket
by feigi
Use before implementing ticket — decides how much process work needs, returns light or heavy plus path to follow.
pr-review-and-document
by marxbiotech
This skill should be used when the user asks to "review PR and save results", "run PR review with documentation", "create PR review document", "review and document PR", "save PR review to docs", "document PR review", or mentions reviewing a PR with the intention of saving the review results. Executes comprehensive PR review using pr-review-toolkit with opus model and posts results as a PR comment.
receiving-code-review
by feng501
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
izanami
by zheref
Repeat a READ-ONLY task until a condition holds. Use when the maintainer invokes hatsu:izanami <task> until <condition>, or asks to watch, poll, or keep checking something until it changes. Observation only — it reads, reports and stops; it never writes to GitHub, never labels, never merges. For a loop that must act, use hatsu:izanagi, which requires an explicit iteration cap.
dispatch-guard
by netanel152
Add, move or change a guard in the inbound-message dispatch chain (app/services/dispatch_guards.py GUARD_CHAIN) or a step in the customer pipeline it falls through to. Use whenever a task adds a new keyword, a new UserStates holding state, a new pre-gate, or changes which branch answers a message first.
orch
by vanillagreencom
"PRIMARY AGENT ONLY. Load to orchestrate a Linear or GitHub work item from preparation through merge."
just-do-it
by matiHirCab
Forces the agent to stop overexplaining and immediately execute the requested task in a direct, implementation-first way.
waves-ship
by wavespestcontrolfl
Use for Waves implementation workspace safety, PR preparation, review remediation, authorized merge/deploy verification, and interrupted-task handoff. Apply only the stages authorized by the task. Do not activate merely because an audit or explanation mentions shipping.
learn
by ayaan4home-collab
Teach a topic for durable understanding by probing the learner, mapping dependencies, and deriving each idea from foundations.
cowen-critique
by magfrump
Critically review a draft (blog post, essay, article, op-ed, research note, or similar written piece) using the cognitive methods and reasoning patterns of economist Tyler Cowen. This goes beyond applying his known conclusions — it encodes how he actually breaks down arguments, the specific intellectual moves he makes (boring-explanation-first, invert-the-thesis, revealed preferences, market signals, cross-domain analogy, sub-claim decomposition, contingent assumptions, calibrated uncertainty), and the habits of mind that distinguish his analysis. Produces a structured Markdown critique. This is the DEFAULT critic for substantive intellectual feedback on a written argument — reach for it whenever a draft makes a claim that could be wrong and the user wants more than proofreading. Trigger phrases: "review this draft", "critique this", "pressure-test this", "poke holes in this", "what am I missing", "is this argument solid", "challenge my thinking", "play devil's advocate", "stress-test the argument", "give me a Cowen-style review", "what would an economist say about this", "is the reasoning sound", "where is this weak". Distinct from yglesias-critique (which targets proposed mechanisms — does the intervention achieve the goal) and ai-personas-critique (which dispatches multiple orthogonal lenses): this skill applies a single, consistent economist's lens focused on argument rigor and revealed-vs-stated reasoning. NOTE: This skill is typically invoked by the draft-review orchestrator, which provides a pre-built fact-check report. If a fact-check report is provided, use it as your factual foundation and do not redo basic fact verification.
secrets-scanner
by XGuang4010
"AI-driven secrets scanner with continuous learning. Uses gitleaks for detection, AI Agent for context-aware classification, and auto-generates filter rules from false positives."
code-review
by saajunaid
Automated code review for pull requests using specialized review patterns. Analyzes code for quality, security, performance, and best practices. Use when reviewing code changes, PRs, or doing code audits.
gitignore-profile-generator
by BennettPhil
Generate annotated .gitignore files by composing reusable target templates.
revet-quarkus
by revethq
Project structure and configuration guide for Revet Quarkus/Kotlin multi-module projects
furniture-design
by mhorvvitz
Design, visualize, and produce buildable plans for custom furniture — both freestanding pieces (tables, shelving, beds, desks) and built-ins (closets, wall units, kitchens, מזנונים, ארונות קיר) — from chat, sketches, or photos to a carpenter-ready package: dimensioned shop drawings, cut list/BOM, hardware schedule. Use for designing furniture, planning a built-in, turning a sketch or inspiration photo into something buildable, working out measurements/cut lists/joinery/hardware, modelling in SketchUp, or iterating with 2D drawings or a 3D view — even without saying "cut list" or "shop drawing." With the SketchUp MCP connector present, it drives it as the 3D backend (real .skp), deferring geometry mechanics to the bundled SketchUp skills. Defaults to metric / Israeli shop conventions (mm, סנדוויץ'/מלמין/MDF sheets, System 32).
review
by dracocephalum
Review a pull request, a branch, or a set of files against this repository's rules, or triage the review comments on a pull request - producing Conventional Comments with a verdict, posted, printed, or saved as a report.
hmm
by ryanlchan
Send LLM output to a browser-based feedback and commenting UI for review. Use when the user wants to annotate, comment on, or edit an LLM response with inline track changes and structured feedback export.
how
by mmdmcy
"Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for motivation."
attack-kitty
by lexijamesesq
Non-author verification expert — receives a thin mandate, fetches its own evidence via Linear MCP tools directly, judges independently, posts its verdict directly or returns it to the caller. Eleven mandate types under playbooks/. Invoked as a fresh spawn whenever work needs independent verification before it reaches Done or the operator. Triggers on a caller spawning @attack-kitty with a mandate, or programmatic invocation.
sflow-explain
by ashokraj2011
Explain one change, clause, test, line, gap or generation from cited, deterministic records.
reference-educational-template
by djankies
[REPLACE] Teach concepts and demonstrate patterns with examples. Use when [REPLACE with specific triggers].
butler-qa-pr-review
by Tzeusy
Use when working a GitHub PR for a Butler QA investigation or reviewer follow-up: unresolved review threads must be answered inline, PR text must contain no personal information or secrets, and the branch is not done until required GitHub checks are green.