代码评审
自动化代码审查与分析
commit
Melvynx
Quick commit and push with minimal, clean messages
pstack
Sma1lboy
Rigorous engineering mode for nontrivial work in this repo — a set of named principles plus the leaf skills that apply them. Use when the user says "pstack", "go deep", "be rigorous", "认真做", or when a task involves architecture, a real bug, a refactor, or anything the user will not be watching. Ported from cursor/plugins pstack by Lauren Tan (MIT); see ATTRIBUTION.md.
thermo-nuclear-code-quality-review
Sma1lboy
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
hyperframes-cli
Sma1lboy
"HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, or remove-background, or when troubleshooting the HyperFrames build/render environment. Entry point for AWS Lambda cloud rendering (hyperframes lambda deploy / render / progress / destroy / policies)."
paper2code
issol14
연구 논문(PDF/arXiv URL)을 분석하여 실행 가능한 코드로 변환합니다. 논문 복제, 알고리즘 구현, 연구 재현 요청 시 자동으로 활성화됩니다. "이 논문 구현해줘", "paper2code", "논문 코드로 변환" 등의 요청에 반응합니다.
1k-code-review-pr
OneKeyHQ
Structured PR code review checklist for OneKey monorepo. Use when reviewing PRs to identify build issues, script problems, CI workflow gaps, and documentation inconsistencies. Focuses on actionable feedback with priority levels and specific fix suggestions. 代码审查. Code Review PR.
1k-dev-commands
OneKeyHQ
Development commands — yarn scripts for dev servers, building, linting, testing, and troubleshooting.
creating-development-plans
sammcj
Creates structured development plans with phased task breakdowns, requirements, and QA checklists. Use when the user explicitly asks to create a dev plan, development plan, or document development requirements.
1k-code-quality
OneKeyHQ
Code quality standards — lint (eslint/oxlint), type check (tsc), pre-commit hooks, and comment conventions. All comments must be in English.
self-review
lingzhi227
Automatically review an academic paper using the NeurIPS review form with three reviewer personas, ensemble scoring, and reflection refinement. Extracts text from PDF, runs structured review, and outputs actionable feedback. Use when the user wants to review a paper before submission or get feedback on a draft.
data-analysis
lingzhi227
Generate statistical analysis code with 4-round review. Select appropriate statistical tests, interpret results, and produce analysis reports with p-values, effect sizes, and confidence intervals. Use when analyzing experimental data for a paper.
paper-assembly
lingzhi227
Orchestrate the full paper pipeline end-to-end. Manage state propagation between phases (literature → plan → code → experiments → figures → tables → writing → review), support checkpointing and resumption. Use for assembling a complete paper from components.
social-media-review
Zal4DW
This skill should be used when the user asks to "review my social media", "check my socials", "how do I look on social media", "clean up my online presence", "is my Instagram/Twitter/Facebook okay for employers", or "social media audit". Provides a lightweight, approachable social media review through the eyes of a recruiter or employer. Especially useful for graduates, early career, and anyone re-entering the job market.
localseodata-tool
garrettjsmith
When the user wants to pull local SEO data — SERP results, local pack rankings, business profile data, reviews, citations, audits, geogrid scans, keyword research, AI visibility, competitor analysis, or any local search intelligence. This is the DEFAULT data tool for LocalSEOSkills. Trigger on any data request before considering other tools. Also trigger on "LocalSEOData," "LSD," "run an audit," "check my rankings," "pull reviews," "citation check," "keyword opportunities," "AI visibility," or "geogrid scan."
geogrid-analysis
garrettjsmith
When the user wants to analyze local ranking data using geogrid scans, interpret map pack rankings across a geographic area, or understand ARP/ATRP/SoLV metrics. Also use when the user mentions "geogrid," "rank grid," "local rank tracking," "Local Falcon," "grid scan," "map pack rankings," "ranking heatmap," or "where am I ranking." For broader local audit, see local-seo-audit. For competitor analysis, see local-competitor-analysis.
task-think
telegramdesktop
Orchestrate a multi-phase implementation workflow for this repository with artifact files under .ai/<project-name>/<letter>/ and fresh codex exec child runs per phase. Use when the user wants one prompt to drive context gathering, planning, plan assessment, implementation, build verification, and review iterations while keeping the main session context clean.
agenfk
cglab-public
Agile, measurable, and reliable workflow enforcement for AI-assisted engineering.
perl-validate
Jamie-BitFlight
This skill should be used when the user asks to "validate Perl script", "check Perl syntax", "verify Perl code", "/perl-validate", or mentions script validation, compile check, security review, or best practice compliance for Perl code.
codex
skills-directory
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
git
youlianvr
"Standardized Git operations: conventional commits, branch naming, workflow rules. Create commits with auto-detected type/scope, manage branches, run workflow operations. Use when committing changes, managing branches, or any git workflow task."
fable-loop
youlianvr
End-to-end workflow that describes the way Fable ran sessions - parallel evidence subagents when the host supports them, one committed plan, surgical execution with an intent gate, adversarial verification, honest outcome-first report. Use for non-trivial multi-step tasks when the user says "/fable-loop", "run the fable loop", or "do this the way Fable would". For the rules alone without orchestration, use fable-method; for the plain task cycle without subagents, use task-cycle; for large multi-phase projects, prefer the GSD workflow and use this inside phases.
code-audit
youlianvr
Use for authorized source-code security review and SAST workflows including Semgrep, CodeQL patterns, dangerous API hunting, and fix verification.
cross-eval
youlianvr
"/cs:cross-eval <memo> — Multi-model consensus on a board memo or strategy brief. Claude + Codex + Gemini cross-review with graceful degradation. Use when a high-stakes memo needs an independent sanity check before the boardroom — e.g. a bet-the-company pivot or fundraise terms."
brainstorming
youlianvr
"You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. Adapted 2026-08-09 for this workspace: design docs go to knowledge/findings/, handoff goes to executing-plans (not writing-plans)."