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_02742 Skill
no license0★ repoSend a message to a contact or group via macOS WeChat desktop client. Use when the user asks to send a WeChat message, message someone on WeChat, or reply to a WeChat contact/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 reading messages, sending files/images.
knownasnaffy/prompthound/dataset/case_02753 Skill
no license0★ repoAuthenticate with LiberFi: register a new account, log in, manage session state, and verify wallet assignments. Two login modes are supported: 1. Key-based (--key): Generates a local P-256 key pair and signs a timestamp. Ideal for agent / headless / automated environments. No email required; a TEE wallet is created automatically. 2. Email OTP: Sends a 6-digit code to the user's email. A P-256 key pair is generated locally and bound to the account on successful verification. A TEE wallet is created automatically. After authentication, a LiberFi JWT is stored in ~/.liberfi/session.json. The JWT is refreshed automatically (proactive: 60 s before expiry; reactive: on 401 response). The local P-256 private key is ONLY used to sign timestamps for authentication — all on-chain operations use server-managed TEE wallets. Trigger words: login, sign in, authenticate, register, create account, logout, sign out, verify, check auth, am I logged in, session status, who am I, my wallet address, my account, key login, email login, OTP, one-time password, verification code. Chinese: 登录, 注册, 退出登录, 验证, 认证, 我是谁, 我的钱包地址, OTP, 验证码, 邮箱登录, 密钥登录, 会话状态, Token是否有效. CRITICAL: Always use `--json` flag for structured output. CRITICAL: Check status BEFORE attempting login. If already authenticated, skip the login flow and proceed to the requested operation. CRITICAL: For agent environments, ALWAYS use `lfi login key --json`. Never block on email OTP in automated contexts.
knownasnaffy/prompthound/dataset/case_02760 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_02780 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_02799 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_02807 Skill
no license0★ repoSimple deployment skill for local git operations. Use when you need to add, commit, and push changes to the Git repository. Designed for quick local deployments (Tasks #3, #4, #5).
knownasnaffy/prompthound/dataset/case_02845 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_02860 Skill
no license0★ repoValidate CSV, JSON, and JSONL data files for quality issues. Detects missing values, duplicates, type inconsistencies, statistical outliers, format violations, whitespace problems, empty columns, and schema drift. Generates quality score (0-100) with severity-ranked issues. Supports schema validation and auto-schema generation. Use when asked to check data quality, validate CSV/JSON files, find data issues, detect duplicates, check for missing values, validate data types, find outliers, generate data quality reports, or validate against a schema. Triggers on "data quality", "validate CSV", "check data", "data issues", "duplicates", "missing values", "outliers", "data validation", "schema validation", "data profiling".
knownasnaffy/prompthound/dataset/case_02943 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_02947 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_02961 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_02985 Skill
no license0★ repoValidate CHANGELOG.md files against the Keep a Changelog format (keepachangelog.com). Checks version ordering, date formats, section types, link references, and formatting. Use when asked to lint, validate, check, or audit a CHANGELOG.md file, verify changelog format, or ensure changelog follows Keep a Changelog conventions. Triggers on "lint changelog", "validate changelog", "check CHANGELOG.md", "changelog format".
knownasnaffy/prompthound/dataset/case_03024 Skill
no license0★ repoAC branch pi-model power flow equations (P/Q and |S|) with transformer tap ratio and phase shift, matching `acopf-math-model.md` and MATPOWER branch fields. Use when computing branch flows in either direction, aggregating bus injections for nodal balance, checking MVA (rateA) limits, computing branch loading %, or debugging sign/units issues in AC power flow.
knownasnaffy/prompthound/dataset/case_03028 Skill
no license0★ repoSend a message to a contact or group via macOS WeChat desktop client. Use when the user asks to send a WeChat message, message someone on WeChat, or reply to a WeChat contact/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 reading messages, sending files/images.
knownasnaffy/prompthound/dataset/case_03068 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_03083 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_03084 Skill
no license0★ repo生成Markdown格式的Git提交记录摘要报告。使用场景:当用户需要按照Markdown格式输出git仓库的详细统计信息时使用此技能。输出内容包括:项目信息、分支信息、提交统计、作者统计、最近提交记录、分支信息和提交类型统计等,全部以标准Markdown格式呈现。
knownasnaffy/prompthound/dataset/case_03094 Skill
no license0★ repoAutomates the backup of the OpenClaw workspace to a remote Git repository. Handles large file exclusions, validates git configuration, and performs intelligent sync with conflict resolution.
knownasnaffy/prompthound/dataset/case_03096 Skill
no license0★ repoThis skill should be used when the user asks to "compose DVP", "create a DVP", "Data Validation Plan", "data cleaning plan", "edit check spec", "validation check list", "write DVP", "draft DVP", or mentions creating, reviewing, or drafting a data validation plan or data cleaning strategy for clinical trials in CRO or sponsor data management contexts.
knownasnaffy/prompthound/dataset/case_03132 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_03159 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_03186 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_03192 Skill
no license0★ repoAutomates the backup of the OpenClaw workspace to a remote Git repository. Handles large file exclusions, validates git configuration, and performs intelligent sync with conflict resolution.
knownasnaffy/prompthound/dataset/case_03200 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_03219 Skill
no license0★ repoLLM streaming output formatter with auto buffer, format correction, sentence break optimization, markdown rendering, improve chat UX
knownasnaffy/prompthound/dataset/case_03235 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_03287 Skill
no license0★ repoValidate CSV, JSON, and JSONL data files for quality issues. Detects missing values, duplicates, type inconsistencies, statistical outliers, format violations, whitespace problems, empty columns, and schema drift. Generates quality score (0-100) with severity-ranked issues. Supports schema validation and auto-schema generation. Use when asked to check data quality, validate CSV/JSON files, find data issues, detect duplicates, check for missing values, validate data types, find outliers, generate data quality reports, or validate against a schema. Triggers on "data quality", "validate CSV", "check data", "data issues", "duplicates", "missing values", "outliers", "data validation", "schema validation", "data profiling".
knownasnaffy/prompthound/dataset/case_03304 Skill
no license0★ repoJSON formatting, validation, and conversion tool. Format, compress, validate JSON, and convert between JSON and YAML.
knownasnaffy/prompthound/dataset/case_03324 Skill
no license0★ repoAutonomous PR review loop with Greptile. Use when an agent creates a PR and needs to autonomously handle code review feedback — reading Greptile reviews, fixing issues, pushing fixes, re-triggering re
knownasnaffy/prompthound/dataset/case_03374 Skill
no license0★ repoIntegrate Self (self.xyz) — a privacy-first identity protocol using zero-knowledge proofs to verify passports and ID cards. Use when the user mentions Self protocol, Self identity, self.xyz, passport verification, zero-knowledge identity verification, SelfAppBuilder, SelfBackendVerifier, SelfVerificationRoot, or wants to add privacy-preserving KYC, age verification, nationality checks, OFAC screening, or Sybil resistance using real-world identity documents. Covers frontend QR code integration, backend proof verification, and on-chain smart contract verification on Celo.
knownasnaffy/prompthound/dataset/case_03383 Skill
no license0★ repoThis skill should be used when the user asks to "compose DVP", "create a DVP", "Data Validation Plan", "data cleaning plan", "edit check spec", "validation check list", "write DVP", "draft DVP", or mentions creating, reviewing, or drafting a data validation plan or data cleaning strategy for clinical trials in CRO or sponsor data management contexts.
knownasnaffy/prompthound/dataset/case_03393 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_03437 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_03441 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_03446 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_03453 Skill
no license0★ repoSession retrospective that analyzes conversation history to produce structured feedback for both user and LLM. Use this skill whenever the user says '复盘', 'retrospect', '批评与自我批评', 'session review', 'review this session', or asks to review/reflect on how a conversation went. Also trigger when the user wants feedback on their prompting skills, wants the LLM to self-critique its mistakes, or asks for a post-mortem of the current or a past session.
knownasnaffy/prompthound/dataset/case_03457 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_03535 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_03580 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_03633 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_03673 Skill
no license0★ repoAutonomous PR review loop with Greptile. Use when an agent creates a PR and needs to autonomously handle code review feedback — reading Greptile reviews, fixing issues, pushing fixes, re-triggering review, and auto-merging when score is 4/5+. Trigger on commands like "pr review {url}", "review my PR", or when a Greptile review webhook/poll delivers feedback.
knownasnaffy/prompthound/dataset/case_03699 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_03705 Skill
no license0★ repoAC branch pi-model power flow equations (P/Q and |S|) with transformer tap ratio and phase shift, matching `acopf-math-model.md` and MATPOWER branch fields. Use when computing branch flows in either direction, aggregating bus injections for nodal balance, checking MVA (rateA) limits, computing branch loading %, or debugging sign/units issues in AC power flow.
knownasnaffy/prompthound/dataset/case_03710 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_03750 Skill
no license0★ repoSession retrospective that analyzes conversation history to produce structured feedback for both user and LLM. Use this skill whenever the user says '复盘', 'retrospect', '批评与自我批评', 'session review', 'review this session', or asks to review/reflect on how a conversation went. Also trigger when the user wants feedback on their prompting skills, wants the LLM to self-critique its mistakes, or asks for a post-mortem of the current or a past session.
knownasnaffy/prompthound/dataset/case_03790 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_03801 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_03825 Skill
no license0★ repoAutonomous PR review loop with Greptile. Use when an agent creates a PR and needs to autonomously handle code review feedback — reading Greptile reviews, fixing issues, pushing fixes, re-triggering review, and auto-merging when score is 4/5+. Trigger on commands like "pr review {url}", "review my PR", or when a Greptile review webhook/poll delivers feedback.
knownasnaffy/prompthound/dataset/case_03834 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_03849 Skill
no license0★ repoThis skill should be used when the user asks to "compose DVP", "create a DVP", "Data Validation Plan", "data cleaning plan", "edit check spec", "validation check list", "write DVP", "draft DVP", or mentions creating, reviewing, or drafting a data validation plan or data cleaning strategy for clinical trials in CRO or sponsor data management contexts.
knownasnaffy/prompthound/dataset/case_03852 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_03892 Skill
no license0★ repoSend a message to a contact or group via macOS WeChat desktop client. Use when the user asks to send a WeChat message, message someone on WeChat, or reply to a WeChat contact/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 reading messages, sending files/images.
knownasnaffy/prompthound/dataset/case_03897 Skill
no license0★ repoRun a local script to fetch current stock prices. Use the read tool to load this SKILL.md, then exec the uv run command inside it. Do NOT use sessions_spawn or web search. Triggers: stock price, share price, how much is [company] stock, ticker price, market price of.
knownasnaffy/prompthound/dataset/case_03905 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_03937 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_03957 Skill
no license0★ repoThis skill should be used when the user asks to "compose DVP", "create a DVP", "Data Validation Plan", "data cleaning plan", "edit check spec", "validation check list", "write DVP", "draft DVP", or mentions creating, reviewing, or drafting a data validation plan or data cleaning strategy for clinical trials in CRO or sponsor data management contexts.
knownasnaffy/prompthound/dataset/case_03999 Skill
no license0★ repo10-dimension weighted scoring framework for prediction market trade evaluation. Enforces disciplined position sizing, circuit breakers, and mandatory counter-arguments. Use when: evaluating prediction market trades, scoring opportunities, deciding position sizes, comparing Polymarket/Kalshi opportunities, running pre-trade checklists. Don't use when: general crypto analysis, DeFi yield farming, non-prediction-market investments, stock/equity analysis, sports betting (different framework needed). Negative examples: - "Should I buy ETH?" → No. This is for prediction markets with binary/discrete outcomes. - "What's the best DeFi yield?" → No. Wrong domain entirely. - "Score this sports bet" → No. Sports betting has different dimensions (injuries, matchups). Edge cases: - Crypto prediction markets (e.g., "Will BTC hit $X?") → YES, use this if on Polymarket/Kalshi. - Multi-outcome markets → Score each outcome separately. - Markets with <$25 liquidity → Auto-fail on Liquidity dimension.
knownasnaffy/prompthound/dataset/case_04029 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_04051 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_04074 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).