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.
IntegrationSlackGitHubwill not run
Call third-party APIs through the Maton gateway, which injects the credential for an app the user has already connected.
Use this skill when the user names a connected app and a co
- References files that are not bundled: references/time/triggers.md, references/instantly/README.md, references/jira/README.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 15 top-level sections: this looks like several domains in one skill
clawhub · ↓ 86 613 ★ 394
Analyzerwill not run
Security gate for skills. Every new skill MUST pass SkillScan before use. Activate on any install, load, add, evaluate, or safety question about a skill. On first load, run first-r
- References files that are not bundled: scripts/.first_run_done
- 1 referenced file(s) missing: scripts/.first_run_done
- Does not say what the result is
clawhub · ↓ 181 787 ★ 40
Integrationwill not run
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. Communicates with EvoMap Hub via local Proxy ma
- References files that are not bundled: assets/gep/genes.json, assets/gep/capsules.json, assets/gep/events.jsonl
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 11 top-level sections: this looks like several domains in one skill
clawhub · ↓ 88 158 ★ 86
Procedurewill not run
TL;DR: 23 marketing playbooks (CRO, SEO, copy, analytics, experiments, pricing, launches, ads, social). Use to get checklists + copy/paste deliverables fast.
- References files that are not bundled: references/<module>/SKILL.md, references/page-cro/SKILL.md, references/signup-flow-cro/SKILL.md
- 24 referenced file(s) missing: references/<module>/SKILL.md, references/page-cro/SKILL.md, references/signup-flow-cro/SKILL.md
- No condition that starts the skill
clawhub · ↓ 19 487 ★ 115
IntegrationYouTubewill not run
Automate TikTok slideshow marketing for any app or product. Researches competitors, generates AI images, adds text overlays, posts via Postiz, tracks analytics, and iterates on wha
- References files that are not bundled: scripts/rc-api.sh
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 1 referenced file(s) missing: scripts/rc-api.sh
clawhub · ↓ 15 000 ★ 143
Integrationwill not run
通过官方 getnote CLI 连接得到大脑,完成浏览器授权、连接诊断、CLI 升级,以及保存、查询、搜索、整理和管理用户的真实笔记。用户明确要求登录、诊断或升级,或要保存链接/图片、查找和查看笔记、整理知识库/文件夹、订阅博主、管理标签时使用;不会自行安装或更新 Skill。
- References files that are not bundled: scripts/install.sh, references/*.md
- 2 referenced file(s) missing: scripts/install.sh, references/*.md
- Does not say what the result is
clawhub · ↓ 30 254 ★ 66
Analyzerwill not run
TikTok Shop e-commerce data assistant. Search products, find trending items, analyze influencers, explore shops, track video performance, and get ad insights via ecomseer.com. Trig
- References files that are not bundled: {url}, url
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 2 referenced file(s) missing: {url}, url
clawhub · ↓ 10 005 ★ 160
Integrationwill not run
Feishu-integrated wrapper for the capability-evolver. Manages the evolution loop lifecycle (start/stop/ensure), sends rich Feishu card reports, and provides dashboard visualization
- References files that are not bundled: assets/gep/events.jsonl
- 1 referenced file(s) missing: assets/gep/events.jsonl
- Does not say what the result is
clawhub · ↓ 77 423 ★ 10
Referencewill not run
AI 新闻聚合与热度排序工具。当用户询问 AI 领域最新动态时触发,如:"今天有什么 AI 新闻?""总结一下这周的 AI 动态""最近有什么火的 AI 产品?""AI 圈最近在讨论什么?"。覆盖:新产品发布、研究论文、行业动态、融资新闻、开源项目更新、社区病毒传播现象、AI 工具/Agent 热门项目。输出中文摘要列表,按热度排序,附带原文链接。
- References files that are not bundled: URL
- 1 referenced file(s) missing: URL
- Does not say what the result is
clawhub · ↓ 13 759 ★ 46
Analyzerwill not run
Use when executing implementation plans with independent tasks in the current session
- References files that are not bundled: ../requesting-code-review/code-reviewer.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- The response is described with custom markup (14 tags): a typed call is more reliable
obra/superpowers · ★ 285 776
Analyzerwill not run
Use when creating new skills, editing existing skills, or verifying skills work before deployment
- References files that are not bundled: ../using-superpowers/references/codex-tools.md, ../using-superpowers/references/gemini-tools.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 21 top-level sections: this looks like several domains in one skill
obra/superpowers · ★ 285 776
Analyzerwill not run
Read the live Hermes desktop DOM/CSS over CDP.
- References files that are not bundled: scripts/perf/lib/cdp.mjs
- 1 referenced file(s) missing: scripts/perf/lib/cdp.mjs
- Does not say what the result is
NousResearch/hermes-agent · ★ 244 884
Procedurewill not run
Author in-repo SKILL.md files: frontmatter and structure.
- References files that are not bundled: references/*.md, scripts/run_tests.sh
- 13 top-level sections: this looks like several domains in one skill
- The response is described with custom markup (23 tags): a typed call is more reliable
NousResearch/hermes-agent · ★ 244 884
ProcedureGitHubwill not run
SAM: zero-shot image segmentation via points, boxes, masks.
- References files that are not bundled: checkpoint="sam_vit_h_4b8939.pth", checkpoint="sam_vit_b_01ec64.pth"
- 13 top-level sections: this looks like several domains in one skill
- 2 referenced file(s) missing: checkpoint="sam_vit_h_4b8939.pth", checkpoint="sam_vit_b_01ec64.pth"
NousResearch/hermes-agent · ★ 244 884
Procedurewill not run
Article illustrations: type × style × palette consistency.
- References files that are not bundled: {relative-path}/NN-{type}-{slug}.png
- 10 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: {relative-path}/NN-{type}-{slug}.png
NousResearch/hermes-agent · ★ 244 884
Procedurewill not run
Plan and run multi-agent video production pipelines.
- References files that are not bundled: assets/brief.md.tmpl
- 1 referenced file(s) missing: assets/brief.md.tmpl
- Does not say what the result is
NousResearch/hermes-agent · ★ 244 884
GeneratorGitHubwill not run
Generate wiki docs + Mermaid diagrams for any codebase.
- References files that are not bundled: <link>, architecture.md, modules/<module>.md
- The response is described with custom markup (9 tags): a typed call is more reliable
- 5 referenced file(s) missing: <link>, architecture.md, modules/<module>.md
NousResearch/hermes-agent · ★ 244 884
Procedurewill not run
Debug Python: pdb REPL + debugpy remote (DAP).
- References files that are not bundled: scripts/run_tests.sh
- 12 top-level sections: this looks like several domains in one skill
- 1 referenced file(s) missing: scripts/run_tests.sh
NousResearch/hermes-agent · ★ 244 884
Generatorwill not run
Create meme PNGs from templates with Pillow text overlay.
- References files that are not bundled: scripts/.cache/
- 1 referenced file(s) missing: scripts/.cache/
- Does not say what the result is
NousResearch/hermes-agent · ★ 244 884
AnalyzerExcelwill not run
Build comparable-company valuation workbooks in Excel.
- References files that are not bundled: examples/comps_example.xlsx
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 22 top-level sections: this looks like several domains in one skill
NousResearch/hermes-agent · ★ 244 884
Procedurewill not run
Knowledge comics (知识漫画): educational, biography, tutorial.
- References files that are not bundled: references/art-styles/<style>.md, references/tones/<tone>.md, references/presets/<preset>.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- The response is described with custom markup (6 tags): a typed call is more reliable
NousResearch/hermes-agent · ★ 244 884
GeneratorExcelwill not run
Build leveraged buyout workbooks with IRR/MOIC in Excel.
- References files that are not bundled: examples/LBO_Model.xlsx
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 11 top-level sections: this looks like several domains in one skill
NousResearch/hermes-agent · ★ 244 884
IntegrationShopifywill not run
Shop catalog search, checkout, order tracking, returns.
- References files that are not bundled: url
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 12 top-level sections: this looks like several domains in one skill
NousResearch/hermes-agent · ★ 244 884
Procedurewill not run
Infographics: 21 layouts x 21 styles (信息图, 可视化).
- References files that are not bundled: references/layouts/<layout>.md, references/styles/<style>.md
- 11 top-level sections: this looks like several domains in one skill
- The response is described with custom markup (8 tags): a typed call is more reliable
NousResearch/hermes-agent · ★ 244 884
ProcedureGitHubDockerwill not run
RL post-training for LLMs with Megatron and SGLang.
- References files that are not bundled: examples/search-r1/, scripts/models/
- 14 top-level sections: this looks like several domains in one skill
- 2 referenced file(s) missing: examples/search-r1/, scripts/models/
NousResearch/hermes-agent · ★ 244 884