What exactly is broken in popular skills: references to files that are not bundled, actions taken without human approval, processes with no stopping condition. Everything here is measured from the skill text rather than judged by a model, so every line can be checked.
Generatorwill not run
Pre-sprint brief that locks challenge, sprint questions, team and role assignments, customer recruiting plan, prototype medium, interview format, logistics, and success criteria be
- References files that are not bundled: ../../docs/reference/skill-families/design-sprint-skills-contract.md
- 1 referenced file(s) missing: ../../docs/reference/skill-families/design-sprint-skills-contract.md
- No condition that starts the skill
product-on-purpose/pm-skills · ★ 669
Analyzerwill not run
Run a repo-wide cross-cutting governance audit via the pm-skill-auditor sub-agent. Aggregates the enforcing validator suite, re-derives aggregate counters, and surfaces cross-cutti
- References files that are not bundled: ../../docs/reference/sub-agent-compatibility.md, ../../agents/pm-skill-auditor.md, ../../docs/internal/release-plans/v2.16.0/spec_pm-skill-auditor.md
- 5 referenced file(s) missing: ../../docs/reference/sub-agent-compatibility.md, ../../agents/pm-skill-auditor.md, ../../docs/internal/release-plans/v2.16.0/spec_pm-skill-auditor.md
- Does not say what the result is
product-on-purpose/pm-skills · ★ 669
AnalyzerGitHubwill not run
Guides contributors from a PM skill idea to a complete Skill Implementation Packet aligned with pm-skills conventions. Runs gap analysis, validates through a Why Gate, classifies b
- References files that are not bundled: ../../site/src/content/docs/guides/creating-pm-skills.md, scripts/check-trigger-fixtures.mjs, scripts/check-output-eval-assets.mjs
- The skill tells the model to perform an irreversible action with no human approval
- 3 referenced file(s) missing: ../../site/src/content/docs/guides/creating-pm-skills.md, scripts/check-trigger-fixtures.mjs, scripts/check-output-eval-assets.mjs
product-on-purpose/pm-skills · ★ 669
GeneratorGitHubwill not run
Checks for newer pm-skills releases, compares local vs. latest version, previews what would change, and updates local files after user confirmation. Generates a structured update r
- References files that are not bundled: ../../docs/guides/updating-pm-skills.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 1 referenced file(s) missing: ../../docs/guides/updating-pm-skills.md
product-on-purpose/pm-skills · ★ 669
Reference
- Prose only: no discrete steps
- Does not say what the result is
product-on-purpose/pm-skills · ★ 669
Analyzerwill not run
Run adversarial review on a PM artifact via the pm-critic sub-agent. Returns findings graded P0/P1/P2/P3 with a concrete fix suggestion per finding and a machine-readable status bl
- References files that are not bundled: ../../docs/reference/sub-agent-compatibility.md, ../../docs/internal/release-plans/v2.16.0/maintainer-gate-testing-codex.md, ../../agents/pm-critic.md
- 6 referenced file(s) missing: ../../docs/reference/sub-agent-compatibility.md, ../../docs/internal/release-plans/v2.16.0/maintainer-gate-testing-codex.md, ../../agents/pm-critic.md
- No condition that starts the skill
product-on-purpose/pm-skills · ★ 669
IntegrationDiscord
TKSeller �Զ������ͻ�??skill��װ????��¼�˺����� ??/tkseller ֱ��??������??
- 12 top-level sections: this looks like several domains in one skill
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 3 407
Referencewill not run
Instantly switch the current OpenClaw session model; supports gpt, claude, qianwen, minimax, current model status, configured model listing, and restoring the default session model
- References files that are not bundled: scripts/model-status.sh
- 10 top-level sections: this looks like several domains in one skill
- The response is described with custom markup (4 tags): a typed call is more reliable
clawhub · ↓ 907 ★ 1
Integration
search hotels for your next trip
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 788 ★ 2
ProcedureTelegramDiscordwill not run
Manage multiple workplaces (project directories) with multi-agent orchestration, isolated memory, and inter-agent communication. Use when the user mentions: workplace init/list/swi
- References files that are not bundled: assets/bin/workplace-server-{os}-{arch}
- The response is described with custom markup (7 tags): a typed call is more reliable
- 1 referenced file(s) missing: assets/bin/workplace-server-{os}-{arch}
clawhub · ↓ 1 675
Generatorwill not run
Generate executable Hyperliquid trading strategy code from natural language prompts. Use when a user wants to create automated trading strategies for Hyperliquid exchange based on
- References files that are not bundled: templates/custom/, scripts/template_registry.py
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 18 top-level sections: this looks like several domains in one skill
clawhub · ↓ 1 655
GeneratorPlaywright
Automatically publish notes to Xiaohongshu (小红书) creator center. Generates cover images (PIL poster, multiple styles), writes content from templates, and publishes via Playwright b
- 10 top-level sections: this looks like several domains in one skill
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 905 ★ 1
Generator
Describes the .vl XML file format used by vvvv gamma — document structure, element hierarchy, ID system (base62 GUIDs), NodeReference/Choice patterns, Pins, Pads (IOBoxes), Links,
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 17 top-level sections: this looks like several domains in one skill
- Does not say what the result is
clawhub · ↓ 884 ★ 1
Integration
Integrate PayPal payments with proper webhook verification, OAuth handling, and security validation for checkout flows and subscriptions.
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 650
GeneratorWordwill not run
Convert a Markdown file or raw Markdown string into a polished Word DOCX document. Supports custom Word template files, includes built-in DOCX templates, and is the right skill whe
- References files that are not bundled: assets/templates/, assets/templates/*.docx
- 2 referenced file(s) missing: assets/templates/, assets/templates/*.docx
- Does not say what the result is
clawhub · ↓ 903 ★ 1
Procedurewill not run
当需要调用Finloop资讯相关接口时,请参考此规范。包括市场时段资讯、资讯列表、AI热闻、股票行情等接口。
- References files that are not bundled: references/REFERENCE.md
- 1 referenced file(s) missing: references/REFERENCE.md
- Does not say what the result is
clawhub · ↓ 881 ★ 1
Referencewill not run
将PDF文件的每一页转换为图片文件;支持自定义图片格式(PNG/JPG)和分辨率;适用于文档处理、图片化存档等场景
- References files that are not bundled: scripts/xxx.py
- 1 referenced file(s) missing: scripts/xxx.py
- Does not say what the result is
clawhub · ↓ 1 644
GeneratorYouTube
Fetch full YouTube transcripts with robust InnerTube fallback. Use when extracting captions/transcripts from a YouTube URL, channel, or batch config, especially when normal transcr
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 902 ★ 1
Analyzerwill not run
A股市场全面复盘,整合指数表现、板块热力图、涨跌停、风格轮动、市场温度分析。触发词:市场复盘、今天市场怎么样、市场分析、每日复盘、市场概览。适用场景:对当日A股市场进行全面复盘、生成综合市场分析报告。不适用场景:个股深度分析、单一指标分析、债券/基金分析。
- References files that are not bundled: ../xiapi-top-stocks/references/token-setup.md
- 11 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: ../xiapi-top-stocks/references/token-setup.md
clawhub · ↓ 950 ★ 1
ReferenceDiscordTelegram
使用 edge-tts 生成高质量中文语音消息并发送。当用户要求发语音、语音回复、TTS、文字转语音、语音播报、语音消息时使用。支持多种中文声音(男声/女声/方言),可调节语速音调,适用于飞书/Telegram/Discord 等渠道的语音消息发送。
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 901 ★ 1
Generator
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 682
AnalyzerGitHub
Tool-driven video question answering with frame extraction, sub-agent analysis, and audio transcription
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 648 ★ 2
Analyzer
Live launchpad feed + AI hot topics for meme tokens.
(1) meme-rush: real-time lifecycle feed on launchpads (Pump.fun, Four.meme) — brand-new launches,
currently-finalizing / bondin
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 947 ★ 1
Reference
Publish Gene+Capsule bundles to EvoMap network | 發布Capsule到EvoMap賺積分
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 619
Procedure
Personal habit coach that tracks daily habits, streaks, and provides AI-powered coaching. Say things like "track a new habit", "log my habits", "show my streaks", or "coach me".
- The skill tells the model to perform an irreversible action with no human approval
- Does not say what the result is
- Does not say what the process needs to start
clawhub · ↓ 1 657