Review & quality
19,000 rows, by stacks then stars
1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid
knownasnaffy/prompthound/dataset/case_01335 Skill
no license0★ repoRun a structured adversarial multi-agent review loop on any significant document. Spawns parallel Opus reviewers with different critical lenses, collects structured redlines, then guides farsight through agree/disagree positioning and v2 production. SELF-TRIGGERING: load this skill and run the complexity self-assessment whenever you are about to produce or have just produced any substantial document — score it and offer the review loop if it qualifies. Also load when the user says things like: 'use the review team', 'get the review team on this', 'spin up the reviewers', 'have the team look at this', 'red-team this', 'redline this', 'challenge this', 'critique this', 'tear this apart', 'poke holes in this', 'stress test this', 'pressure test this', 'sanity check this', 'validate this', 'get a second opinion', 'before we build/implement/ship this'.
knownasnaffy/prompthound/dataset/case_01341 Skill
no license0★ repoSafely apply OpenClaw config changes with automatic rollback and ack timeout guard. Use when editing ~/.openclaw/openclaw.json, restarting gateway, enabling cross-context routing, or any risky runtime
knownasnaffy/prompthound/dataset/case_01371 Skill
no license0★ repoBuild and run multi-agent content production teams on OpenClaw with single-repo architecture, symlink-based file sharing, role-specialized AGENTS.md, and automated review-fix-score loops. Use when: (1) Setting up a team of 3+ agents with writer/reviewer/scorer/fixer roles for content creation, (2) Creating a quality-controlled publishing pipeline, (3) Bootstrapping agent workspaces with symlinks and tool configs from scratch, (4) Running multi-round review→fix→score cycles until a quality threshold is met, (5) Debugging agent spawn permissions, tool-call loops, or symlink issues. Based on real production experience building a 6-agent content team (2026-03-30).
knownasnaffy/prompthound/dataset/case_01395 Skill
no license0★ repoUse when formatting references for journal submission, converting between citation styles (APA, MLA, Vancouver, Chicago), generating bibliographies for manuscripts, or ensuring consistent reference formatting. Automatically formats citations and bibliographies in 1000+ academic styles. Ensures reference accuracy, completeness, and compliance with journal requirements. Supports batch conversion and integration with reference managers.
knownasnaffy/prompthound/dataset/case_01410 Skill
no license0★ repoOrchestrate OpenClaw end-to-end R&D delivery in Feishu from requirement intake to closure using PM, developer, reviewer, and tester subagents. Use when handling研发任务 that need structured requirement parsing, project-context enrichment from Feishu history/wiki, coding + PR flow, read-only review/testing gates, bug-loop rework, and final owner notification.
knownasnaffy/prompthound/dataset/case_01532 Skill
no license0★ repoLLM streaming output formatter with auto buffer, format correction, sentence break optimization, markdown rendering, improve chat UX
knownasnaffy/prompthound/dataset/case_01534 Skill
no license0★ repoSystem safety and control-plane skill that prevents agent deadlocks and freezes. Provides non-LLM control commands to inspect task state, flush message queues, cancel long-running work, and recover safely without restarting the container. Use when implementing or operating long-running tasks, sub-agents, benchmarks, background monitors (e.g., Moltbook, PNR checks), or when the system becomes unresponsive and needs immediate recovery controls.
knownasnaffy/prompthound/dataset/case_01567 Skill
no license0★ repoGenerate changelogs from git commits. Supports markdown, plain text, and JSON output with date ranges and tag-based filtering.
knownasnaffy/prompthound/dataset/case_01605 Skill
no license0★ repoParallel multi-agent coding sprints using git worktree isolation. Unlike naive parallel agents that silently overwrite each other's work, Swarm gives each agent its own private copy of the repo (a git worktree + branch) so they cannot touch each other's files. A mandatory conflict planner runs before any agent is spawned — it analyzes your task list, flags tasks that would touch the same files, and serializes them automatically. Coordinator reviews each diff before anything lands on main. Use when given 2+ coding tasks on a repository. Trigger phrases: "run a swarm sprint", "parallel sprint", "use swarm for these tasks". Inspired by Anthropic's COORDINATOR_MODE architecture.
knownasnaffy/prompthound/dataset/case_01733 Skill
no license0★ repoDiagnose and recover broken Git state and worktree metadata with a staged, low-risk recovery flow. Use when Git reports detached or contradictory HEAD state, phantom worktree locks, orphaned worktree entries, missing refs, 0000000000000000000000000000000000000000 hashes, or branch operations fail with errors like already checked out, unknown revision, not a valid object name, or cannot lock ref.
knownasnaffy/prompthound/dataset/case_01748 Skill
no license0★ repoGenerate changelogs from git commits. Supports markdown, plain text, and JSON output with date ranges and tag-based filtering.
knownasnaffy/prompthound/dataset/case_01778 Skill
no license0★ repoStrict Conventional Commits v1.0.0, atomic commit discipline, and Trunk-Based Development guardrails for git work. Use when preparing a commit, staging changes, writing or revising a commit message, deciding whether to split changes, planning branch strategy for a feature/bug/fix, opening or reviewing pull requests, or after finishing any meaningful implementation unit.
knownasnaffy/prompthound/dataset/case_01792 Skill
no license0★ repoAI-powered code review that combines fast local static analysis with deep AI reasoning. Catches bugs, security vulnerabilities, performance issues, and style problems. Supports Anthropic, OpenAI, and Ollama models. Falls back to local regex analysis when offline.
knownasnaffy/prompthound/dataset/case_01842 Skill
no license0★ repoCheck coding-model API quality, capability fit, and drift with LT-lite and B3IT-lite. Use when Codex needs to verify whether an OpenAI/OpenAI-compatible/Anthropic endpoint can support first-token detection, logprob tracking, baseline-vs-current drift checks, or headless API quality smoke tests for coding CLIs, terminal agents, and OpenClaw-style workflows.
knownasnaffy/prompthound/dataset/case_01846 Skill
no license0★ repoConvert Mercurial (hg) repositories to Git. Use when migrating from Mercurial to Git, converting hg repos to git format, preserving history and branches during VCS migration, or when working with legacy Mercurial repositories that need to be moved to Git.
knownasnaffy/prompthound/dataset/case_01869 Skill
no license0★ repoRead chat history from a WeChat contact or group via macOS desktop client screenshot + agent OCR. Use when the user asks to read, view, check, or retrieve WeChat chat messages, conversation history, or recent messages from a contact or group. v2.0 auto mode tries fast locate + verify first; falls back to Agent-assisted mode only when verification fails. Requires macOS, WeChat desktop logged in, Accessibility permission, and cliclick. NOT for sending messages (use wechat-send).
knownasnaffy/prompthound/dataset/case_01901 Skill
no license0★ repoOpenAI Codex-native multi-agent swarm orchestration for parallel coding. Use when spawning multiple Codex CLI agents to work in parallel with git worktrees, tmux tracking, endorsement gates, native code review, integration merging, and webhook notifications. All agents are Codex (o3 for architect/integrator/reviewer, codex-mini for builders). Triggers on parallel coding, multi-agent work, swarm orchestration, or batch spawning with OpenAI models.
knownasnaffy/prompthound/dataset/case_01915 Skill
no license0★ repoFormat, minify, and lint SQL queries from the command line. Formats SQL with proper indentation and keyword casing, minifies by removing whitespace and comments, and lints for common anti-patterns (SELECT *, inconsistent casing, missing semicolons, trailing whitespace). No external dependencies — pure Python. Use when formatting SQL queries, cleaning up SQL files, minifying SQL for production, or checking SQL quality.
knownasnaffy/prompthound/dataset/case_01964 Skill
no license0★ repoProtects sensitive files (contracts, transaction data, personal/customer privacy) by performing deep content inspection for text and binary formats (PDF, DOCX, XLSX) before any read, search, or send operation.
knownasnaffy/prompthound/dataset/case_02035 Skill
no license0★ repo依托东方财富数据库,面向沪深京港美五大市场的上市公司/股票,生成业绩点评类输出(含财报分析、业绩解读)。 当用户明确提出业绩点评、财报分析、业绩解读需求,或出现「业绩点评」「财报点评」「业绩分析」「季报/半年报/年报点评」「财务分析」「盈利分析」「业绩解读」等表述时,应触发本 Skill。 用户点名具体公司/股票并希望获得业绩与盈利维度的分析评价时,应触发本 Skill。 即使用户未明说「业绩点评」,只要意图是对该公司财报或业绩作分析解读,也应触发。
knownasnaffy/prompthound/dataset/case_02043 Skill
no license0★ repoCreate KSVC-validated Twitter content from research PDFs. Content types: long threads, quick takes, breaking news, shitposts, personal commentary, victory laps. Triggers on "create content", "write thread", "make a post", "shitpost", or when working with PDFs in /Users/Shared/ksvc/pdfs. REQUIRED STEPS - (1a) Explore agents to scan PDFs, (1b) RLM for deep extraction, (1c) Cross-doc synthesis with rlm-multi, (2) KSVC holdings check (preliminary), (3) write data backbone, (4a) AUDIT with RLM verification, (4a.5) Gemini web cross-validation for FAIL/UNSOURCED inferences, (4b) Final holdings verification (ALL 7 models), (4c) Stylize with kirk-mode skill, (4d) humanizer pass, (5) save draft, (6) chart decision & generation.
knownasnaffy/prompthound/dataset/case_02097 Skill
no license0★ repoUse when formatting references for journal submission, converting between citation styles (APA, MLA, Vancouver, Chicago), generating bibliographies for manuscripts, or ensuring consistent reference formatting. Automatically formats citations and bibliographies in 1000+ academic styles. Ensures reference accuracy, completeness, and compliance with journal requirements. Supports batch conversion and integration with reference managers.
knownasnaffy/prompthound/dataset/case_02106 Skill
no license0★ repoGenerate, install, and manage Git hooks with pre-built templates. Includes hooks for linting staged files, enforcing conventional commits, blocking debug statements, preventing large file commits, auto-formatting code, requiring ticket references, protecting branches, running tests before push, and auto-installing dependencies after merge. Use when setting up git hooks, enforcing commit conventions, or automating pre-commit/pre-push checks.
knownasnaffy/prompthound/dataset/case_02107 Skill
no license0★ repoValidates JSON syntax across the workspace. Use this skill to check for syntax errors in configuration files, memory files, or data assets.
knownasnaffy/prompthound/dataset/case_02118 Skill
no license0★ repoAI-powered code review that combines fast local static analysis with deep AI reasoning. Catches bugs, security vulnerabilities, performance issues, and style problems. Supports Anthropic, OpenAI, and Ollama models. Falls back to local regex analysis when offline.
knownasnaffy/prompthound/dataset/case_02149 Skill
no license0★ repoOrchestrate OpenClaw end-to-end R&D delivery in Feishu from requirement intake to closure using PM, developer, reviewer, and tester subagents. Use when handling研发任务 that need structured requirement parsing, project-context enrichment from Feishu history/wiki, coding + PR flow, read-only review/testing gates, bug-loop rework, and final owner notification.
knownasnaffy/prompthound/dataset/case_02160 Skill
no license0★ repoPre-flight check for GPU cluster nodes — node validation before training, check cluster node health, is my GPU node ready. 26 health checks covering GPU, PCIe, RDMA/IB, Docker, IOMMU, NUMA, firewall, and more
knownasnaffy/prompthound/dataset/case_02161 Skill
no license0★ repoPersona-weighted pre-send email governance for AI systems. Produces APPROVE/BLOCK/REWRITE decisions, writes decision artifacts to the board ledger, and returns strict machine-parseable JSON.
knownasnaffy/prompthound/dataset/case_02162 Skill
no license0★ repoGit automation for OpenClaw workspace. Use when user needs to commit and push changes from /home/roger/.openclaw to the remote repository. Triggers on: git commit, git push, save changes, backup openclaw.
knownasnaffy/prompthound/dataset/case_02165 Skill
no license0★ repoFix and verify OpenClaw TTS media-route behavior in installed dist builds. Use when users report that tts.convert returns unusable audio URLs, media TTS MP3 routes serve HTML instead of binary audio, Bearer auth is not enforced on media routes, Range requests fail, or temporary TTS files are not cleaned up. Applies to hashed gateway-cli dist files and includes backup, patch, restart, and curl verification workflow.
knownasnaffy/prompthound/dataset/case_02198 Skill
no license0★ repoProfessional code review and Git commit workflow management. Use this skill when users mention 'push', 'commit', '提交', or any Git submission operations. Provides comprehensive pre-commit checks, code quality review, build verification, and Git workflow guidance following industry best practices.
knownasnaffy/prompthound/dataset/case_02220 Skill
no license0★ repoCheck if services are responding on given host:port pairs. Supports TCP and HTTP checks with configurable timeout. Use for service monitoring, health checks, and network debugging.
knownasnaffy/prompthound/dataset/case_02235 Skill
no license0★ repoDiagnose and recover broken Git state and worktree metadata with a staged, low-risk recovery flow. Use when Git reports detached or contradictory HEAD state, phantom worktree locks, orphaned worktree entries, missing refs, 0000000000000000000000000000000000000000 hashes, or branch operations fail with errors like already checked out, unknown revision, not a valid object name, or cannot lock ref.
knownasnaffy/prompthound/dataset/case_02258 Skill
no license0★ repoFetch real-time stock prices and fundamental data. Use when: (1) User asks for current stock price or quote, (2) Need to update portfolio holdings with latest prices, (3) Check PE ratios, 52-week ranges, or market caps, (4) Daily portfolio valuation updates, (5) Pre-trade price verification. Supports bulk queries for multiple symbols. Default: Stooq (free, no API key).
knownasnaffy/prompthound/dataset/case_02292 Skill
no license0★ repoGenerate, install, and manage Git hooks with pre-built templates. Includes hooks for linting staged files, enforcing conventional commits, blocking debug statements, preventing large file commits, auto-formatting code, requiring ticket references, protecting branches, running tests before push, and auto-installing dependencies after merge. Use when setting up git hooks, enforcing commit conventions, or automating pre-commit/pre-push checks.
knownasnaffy/prompthound/dataset/case_02339 Skill
no license0★ repoMake your OpenClaw agent portable and persistent. Version-controls SOUL.md, MEMORY.md, and all core knowledge files using git with automatic GitHub push — so your agent's identity, memory, and operating rules are backed up and can be restored on any machine by cloning the repo. Use whenever core knowledge files are modified to commit and push changes. Also use when asked to show history, diff a file, or revert a change. Watch your assistant evolve over time through its git history.
knownasnaffy/prompthound/dataset/case_02354 Skill
no license0★ repoDiagnose and recover broken Git state and worktree metadata with a staged, low-risk recovery flow. Use when Git reports detached or contradictory HEAD state, phantom worktree locks, orphaned worktree entries, missing refs, 0000000000000000000000000000000000000000 hashes, or branch operations fail with errors like already checked out, unknown revision, not a valid object name, or cannot lock ref.
knownasnaffy/prompthound/dataset/case_02369 Skill
no license0★ repoJSON formatting, validation, and conversion tool. Format, compress, validate JSON, and convert between JSON and YAML.
knownasnaffy/prompthound/dataset/case_02384 Skill
no license0★ repoDiagnose always-loaded workspace context files such as AGENTS.md, SOUL.md, USER.md, MEMORY.md, and TOOLS.md. Use when you want to reduce context bloat, detect duplicated rules, spot misplaced content, identify overweight sections, or audit whether core context files still match their intended roles before reorganizing them.
knownasnaffy/prompthound/dataset/case_02385 Skill
no license0★ repoOpenAI Codex-native multi-agent swarm orchestration for parallel coding. Use when spawning multiple Codex CLI agents to work in parallel with git worktrees, tmux tracking, endorsement gates, native code review, integration merging, and webhook notifications. All agents are Codex (o3 for architect/integrator/reviewer, codex-mini for builders). Triggers on parallel coding, multi-agent work, swarm orchestration, or batch spawning with OpenAI models.
knownasnaffy/prompthound/dataset/case_02397 Skill
no license0★ repoPersona-weighted pre-send email governance for AI systems. Produces APPROVE/BLOCK/REWRITE decisions, writes decision artifacts to the board ledger, and returns strict machine-parseable JSON.
knownasnaffy/prompthound/dataset/case_02403 Skill
no license0★ repoUpdate OpenClaw from source code. Supports custom project path and branch. Includes pulling latest branch, rebasing, building and installing, restarting service. Triggered when user asks to update OpenClaw, sync source, rebase branch, or rebuild.
knownasnaffy/prompthound/dataset/case_02413 Skill
no license0★ repoPre-flight check for GPU cluster nodes — node validation before training, check cluster node health, is my GPU node ready. 26 health checks covering GPU, PCIe, RDMA/IB, Docker, IOMMU, NUMA, firewall, and more
knownasnaffy/prompthound/dataset/case_02452 Skill
no license0★ repoFetch real-time stock prices and fundamental data. Use when: (1) User asks for current stock price or quote, (2) Need to update portfolio holdings with latest prices, (3) Check PE ratios, 52-week ranges, or market caps, (4) Daily portfolio valuation updates, (5) Pre-trade price verification. Supports bulk queries for multiple symbols. Default: Stooq (free, no API key).
knownasnaffy/prompthound/dataset/case_02460 Skill
no license0★ repoUse this skill for any git commit, pull request, or release task. Invoke immediately when the user wants to: stage and commit changes, write a commit message, push code, create a PR or MR, tag a release, or update CHANGELOG. Triggers on: 「帮我提交」「commit」「提交代码」「创建 PR」「发布版本」「打 tag」 「推代码」, or English equivalents like "commit my changes", "create a pull request", "release v", "write a commit message", "push this branch". Do NOT trigger for: bulk repo syncing (use code-sync), general git questions without commit/PR intent, or Yunxiao MR creation (use yunxiao skill).
knownasnaffy/prompthound/dataset/case_02464 Skill
no license0★ repoStore, verify, and manage AI data on the Ethereum blockchain (Base network) using the ERCData standard. Use when an agent needs to store data fingerprints on-chain, verify data integrity, create audit trails, manage access control for private data, or interact with the ERCData smart contract. Supports public and private storage, EIP-712 verification, snapshots, and batch operations.
knownasnaffy/prompthound/dataset/case_02466 Skill
no license0★ repoCreate KSVC-validated Twitter content from research PDFs. Content types: long threads, quick takes, breaking news, shitposts, personal commentary, victory laps. Triggers on "create content", "write thread", "make a post", "shitpost", or when working with PDFs in /Users/Shared/ksvc/pdfs. REQUIRED STEPS - (1a) Explore agents to scan PDFs, (1b) RLM for deep extraction, (1c) Cross-doc synthesis with rlm-multi, (2) KSVC holdings check (preliminary), (3) write data backbone, (4a) AUDIT with RLM verification, (4a.5) Gemini web cross-validation for FAIL/UNSOURCED inferences, (4b) Final holdings verification (ALL 7 models), (4c) Stylize with kirk-mode skill, (4d) humanizer pass, (5) save draft, (6) chart decision & generation.
knownasnaffy/prompthound/dataset/case_02483 Skill
no license0★ repoOpenAI Codex-native multi-agent swarm orchestration for parallel coding. Use when spawning multiple Codex CLI agents to work in parallel with git worktrees, tmux tracking, endorsement gates, native code review, integration merging, and webhook notifications. All agents are Codex (o3 for architect/integrator/reviewer, codex-mini for builders). Triggers on parallel coding, multi-agent work, swarm orchestration, or batch spawning with OpenAI models.
knownasnaffy/prompthound/dataset/case_02497 Skill
no license0★ repo为初中数学章节生成复习指南 HTML 文件(知识点 + SVG 图形 + 选择/填空/大题 + 详解)。 当用户要求"生成数学复习资料"、"出一份数学练习题"、"帮我复习XX章节"、"数学辅导"、"生成数学学习文档"、 "做一份数学错题本"、"生成函数/几何复习指南" 或类似意图时,应使用此 Skill。 该 Skill 在任意对话中均可调用,不限于特定项目。
knownasnaffy/prompthound/dataset/case_02542 Skill
no license0★ repoUpdate OpenClaw from source code. Supports custom project path and branch. Includes pulling latest branch, rebasing, building and installing, restarting service. Triggered when user asks to update OpenClaw, sync source, rebase branch, or rebuild.
knownasnaffy/prompthound/dataset/case_02554 Skill
no license0★ repoPersona-weighted pre-send email governance for AI systems. Produces APPROVE/BLOCK/REWRITE decisions, writes decision artifacts to the board ledger, and returns strict machine-parseable JSON.
knownasnaffy/prompthound/dataset/case_02562 Skill
no license0★ repoLint .sql migration files for common mistakes — missing IF EXISTS guards, UPDATE/DELETE without WHERE, non-idempotent CREATE, missing transaction wrappers, reserved-word identifiers, destructive DDL, and Postgres-specific issues (CREATE INDEX locks, ADD COLUMN NOT NULL without DEFAULT). 17 rules across structure, safety, and style categories. Pure Python stdlib.
knownasnaffy/prompthound/dataset/case_02573 Skill
no license0★ repo为初中数学章节生成复习指南 HTML 文件(知识点 + SVG 图形 + 选择/填空/大题 + 详解)。 当用户要求"生成数学复习资料"、"出一份数学练习题"、"帮我复习XX章节"、"数学辅导"、"生成数学学习文档"、 "做一份数学错题本"、"生成函数/几何复习指南" 或类似意图时,应使用此 Skill。 该 Skill 在任意对话中均可调用,不限于特定项目。
knownasnaffy/prompthound/dataset/case_02591 Skill
no license0★ repoLLM streaming output formatter with auto buffer, format correction, sentence break optimization, markdown rendering, improve chat UX
knownasnaffy/prompthound/dataset/case_02636 Skill
no license0★ repoProfessional code review and Git commit workflow management. Use this skill when users mention 'push', 'commit', '提交', or any Git submission operations. Provides comprehensive pre-commit checks, code
knownasnaffy/prompthound/dataset/case_02642 Skill
no license0★ repoOpenAI Codex-native multi-agent swarm orchestration for parallel coding. Use when spawning multiple Codex CLI agents to work in parallel with git worktrees, tmux tracking, endorsement gates, native code review, integration merging, and webhook notifications. All agents are Codex (o3 for architect/integrator/reviewer, codex-mini for builders). Triggers on parallel coding, multi-agent work, swarm orchestration, or batch spawning with OpenAI models.
knownasnaffy/prompthound/dataset/case_02679 Skill
no license0★ repoComprehensive review and analysis of software engineering resumes in PDF format (frontend, backend, or ML domains). Use this skill when users ask to review, analyze, provide feedback on, or evaluate a resume PDF. The skill analyzes technical content quality, career progression, ATS compatibility, grammar, structure, and provides actionable improvement suggestions based on current industry trends.
knownasnaffy/prompthound/dataset/case_02711 Skill
no license0★ repoGit automation for OpenClaw workspace. Use when user needs to commit and push changes from /home/roger/.openclaw to the remote repository. Triggers on: git commit, git push, save changes, backup openclaw.
knownasnaffy/prompthound/dataset/case_02730 Skill
no license0★ repoRun Claude Code tasks in headless mode with `claude -p` through the local `cc-task-runner.sh` wrapper, including model switching, JSON output capture, structured schema checks, multi-file artifact validation, and glob matching. Use when you need reliable non-interactive Claude Code execution for coding, review, analysis, report generation, or file-producing tasks. Triggers include headless runner, claude -p automation, scripted Claude Code tasks, JSON-schema validation, artifact verification, and GLM-5.1 / MiniMax-M2.7 task orchestration.
knownasnaffy/prompthound/dataset/case_02741 Skill
no license0★ repo为初中数学章节生成复习指南 HTML 文件(知识点 + SVG 图形 + 选择/填空/大题 + 详解)。 当用户要求"生成数学复习资料"、"出一份数学练习题"、"帮我复习XX章节"、"数学辅导"、"生成数学学习文档"、 "做一份数学错题本"、"生成函数/几何复习指南" 或类似意图时,应使用此 Skill。 该 Skill 在任意对话中均可调用,不限于特定项目。