Skip to content
Back to search

cc-skills

πŸ§‘β€πŸŽ¨ A collection of agentic skills that works

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/samber-cc-skills/badge.svg)](/listings/samber-cc-skills)

HTML

<a href="/listings/samber-cc-skills"><img src="/api/listings/samber-cc-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/plugin.json Β· Manifest Β· 24 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "cc-skills",
  3. "description": "AI Agent Skills",
  4. "version": "2.4.0",
  5. "author": {
  6. "name": "Samuel Berthe",
  7. "email": "hey@samuel-berthe.fr"
  8. },
  9. "homepage": "https://github.com/samber/cc-skills",
  10. "repository": "https://github.com/samber/cc-skills",
  11. "license": "MIT",
  12. "keywords": [
  13. "claude-code",
  14. "claude-code-plugin",
  15. "plugin",
  16. "ai-agent",
  17. "skills",
  18. "marketing",
  19. "engineering",
  20. "developer",
  21. "coding",
  22. "productivity"
  23. ]
  24. }
README.md Β· README Β· 337 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Agent Skills
  2. AI agent skills are reusable instruction sets that extend your assistant with domain-specific expertise, loaded on demand so they don't bloat your context. This repository covers marketing and engineering skills authored by [@samber](https://github.com/samber).
  3. For Golang-related skills, please visit [cc-skills-golang](https://github.com/samber/cc-skills-golang).
  4. <!-- prettier-ignore-start -->
  5. > [!IMPORTANT]
  6. > Bootstrapped with Claude. **Edited, tested, reviewed and reworked by a human**.
  7. >
  8. > **No AI slop here.** AI-made skills are useless.
  9. <!-- prettier-ignore-end -->
  10. <img width="3808" height="1280" alt="image" src="https://github.com/user-attachments/assets/95139f6f-c19c-4041-a010-d94bca594bba" />
  11. ## πŸš€ How to use?
  12. **Install with [skills](https://skills.sh/) CLI** (universal, works with any [Agent Skills](https://agentskills.io)-compatible tool):
  13. ```bash
  14. npx skills add https://github.com/samber/cc-skills --all
  15. # or a single skill:
  16. npx skills add https://github.com/samber/cc-skills --skill promql-cli
  17. ```
  18. <!-- prettier-ignore-start -->
  19. <details>
  20. <summary>Claude Code</summary>
  21. ```bash
  22. /plugin marketplace add samber/cc
  23. /plugin install cc-skills@samber
  24. ```
  25. </details>
  26. <details>
  27. <summary>Openclaw</summary>
  28. Copy skills into the cross-client discovery directory:
  29. ```bash
  30. git clone https://github.com/samber/cc-skills.git ~/.openclaw/skills/cc-skills
  31. # or in workspace:
  32. git clone https://github.com/samber/cc-skills.git ~/.openclaw/workspace/skills/cc-skills
  33. ```
  34. </details>
  35. <details>
  36. <summary>Gemini CLI</summary>
  37. ```bash
  38. gemini extensions install https://github.com/samber/cc-skills
  39. ```
  40. Update with `gemini extensions update cc-skills`.
  41. </details>
  42. <details>
  43. <summary>Cursor</summary>
  44. Copy skills into the cross-client discovery directory:
  45. ```bash
  46. git clone https://github.com/samber/cc-skills.git ~/.cursor/skills/cc-skills
  47. ```
  48. Cursor auto-discovers skills from `.agents/skills/` and `.cursor/skills/`.
  49. </details>
  50. <details>
  51. <summary>Copilot</summary>
  52. Copy skills into the cross-client discovery directory:
  53. ```bash
  54. /plugin install https://github.com/samber/cc-skills
  55. # or
  56. git clone https://github.com/samber/cc-skills.git ~/.copilot/skills/cc-skills
  57. ```
  58. Copilot auto-discovers skills from `.copilot/skills/`.
  59. </details>
  60. <details>
  61. <summary>OpenCode</summary>
  62. Copy skills into the cross-client discovery directory:
  63. ```bash
  64. git clone https://github.com/samber/cc-skills.git ~/.agents/skills/cc-skills
  65. ```
  66. OpenCode auto-discovers skills from `.agents/skills/`, `.opencode/skills/`, and `.claude/skills/`.
  67. </details>
  68. <details>
  69. <summary>Codex (OpenAI)</summary>
  70. Install the plugin via the Codex CLI:
  71. ```bash
  72. codex plugin add github:samber/cc-skills
  73. ```
  74. Update with `codex plugin update cc-skills`. Falls back to a manual clone if the marketplace path is unavailable:
  75. ```bash
  76. git clone https://github.com/samber/cc-skills.git ~/.agents/skills/cc-skills
  77. ```
  78. Codex auto-discovers skills from `~/.agents/skills/` and `.agents/skills/`.
  79. </details>
  80. <details>
  81. <summary>Antigravity</summary>
  82. Clone and symlink into the cross-client discovery path:
  83. ```bash
  84. git clone https://github.com/samber/cc-skills.git ~/.antigravity/skills/cc-skills
  85. ```
  86. Update with `cd ~/.antigravity/skills/cc-skills && git pull`.
  87. </details>
  88. <!-- prettier-ignore-end -->
  89. ## 🧩 Skills
  90. These skills are designed as **atomic units, cross-referencing units**. A skill may reference conventions defined in another. Installing only a subset will give you a partial and potentially inconsistent view of the guidelines. For best results, install all general-purpose skills together.
  91. Each skill lives in `skills/<name>/` with a `SKILL.md` entry point. The `SKILL.md` is kept small with internal references to advanced markdown files, so only the relevant content is loaded into context.
  92. - **Description (tok)**: weight of the `description` field from YAML frontmatter, always loaded into Claude's context for skill triggering
  93. - **SKILL.md (tok)**: weight of the full `SKILL.md` file loaded when the skill triggers
  94. - **Directory (tok)**: weight of all files in the skill directory (SKILL.md + referenced markdown files)
  95. ```
  96. β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
  97. β”‚ Agent Skills β”‚
  98. β””β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”˜
  99. β”‚
  100. β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
  101. β”‚ β”‚
  102. β–Ό β–Ό
  103. β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
  104. β”‚ Engineering β”‚ β”‚ Marketing & Content β”‚
  105. β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€ β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€
  106. β”‚ conventional-git β”‚ β”‚ linkedin-ghostwriting β”‚
  107. β”‚ promql-cli β”‚ β”‚ press-release-writer β”‚
  108. β”‚ chrome-extension β”‚ β”‚ humaniseur-fr β”‚
  109. β”‚ crxjs β”‚ β”‚ humanizer-en-asd-ste100 β”‚
  110. β”‚ site-launch-checklist β”‚ β”‚ copywriting-hooks β”‚
  111. β”‚ frontend-design-deslop β”‚ β”‚ copywriting-cta β”‚
  112. β”‚ β”‚ β”‚ copywriting-prose-creator β”‚
  113. β”‚ β”‚ β”‚ copywriting-tone-of-voice-creator β”‚
  114. β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
  115. β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
  116. β”‚ Developer Relations β”‚ β”‚ Productivity β”‚ β”‚ Meta β”‚
  117. β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€ β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€ β”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€
  118. β”‚ technical-article-writer β”‚ β”‚ deep-research β”‚ β”‚ snyk-agent-scan-compliance β”‚
  119. β”‚ substack-ghostwriting β”‚ β”‚ influence-and-negotiation β”‚ β”‚ skill-progressive-disclosure-design β”‚
  120. β”‚ β”‚ β”‚ training-report β”‚ β”‚ β”‚
  121. β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
  122. ```
  123. | Skill | Error rate gap | Description (tok) | SKILL.md (tok) | Directory (tok) |
  124. | --- | --- | --- | --- | --- |
  125. | `conventional-git` | -36% | 73 | 1,446 | 1,446 |
  126. | `promql-cli` | -39% | 87 | 1,257 | 6,248 |
  127. | `chrome-extension` | β€” | 137 | 3,909 | 36,173 |
  128. | `crxjs` | β€” | 185 | 2,697 | 2,697 |
  129. | `site-launch-checklist` | -59% | 198 | 7,784 | 17,896 |
  130. | `frontend-design-deslop` | -28% | 168 | 4,294 | 45,097 |
  131. | `linkedin-ghostwriting` | -31% | 87 | 1,045 | 1,993 |
  132. | `substack-ghostwriting` | -51% | 154 | 3,416 | 10,821 |
  133. | `technical-article-writer` | -33% | 157 | 2,809 | 6,251 |
  134. | `press-release-writer` | -34% | 159 | 1,686 | 17,981 |
  135. | `humaniseur-fr` | -14% | 166 | 10,782 | 10,782 |
  136. | `humanizer-en-asd-ste100` | -16% | 141 | 9,594 | 9,594 |
  137. | `snyk-agent-scan-compliance` | -27% | 144 | 1,904 | 5,612 |
  138. | `training-report` | -61% | 179 | 2,392 | 8,222 |
  139. | `deep-research` | -51% | 316 | 2,997 | 14,125 |
  140. | `influence-and-negotiation` | -68% | 162 | 6,592 | 48,996 |
  141. | `skill-progressive-disclosure-design` | -58% | 154 | 3,607 | 3,607 |
  142. | `copywriting-hooks` | β€” | 169 | 6,705 | 13,484 |
  143. | `copywriting-cta` | β€” | 165 | 2,873 | 14,424 |
  144. | `copywriting-prose-creator` | β€” | 166 | 4,952 | 24,900 |
  145. | `copywriting-tone-of-voice-creator` | β€” | 181 | 4,056 | 22,315 |
  146. ## πŸ§ͺ Skill evaluations
  147. | | With Skill | Without Skill | Delta |
  148. | ----------- | ---------- | ------------- | --------- |
  149. | **Overall** | **98%** | **52%** | **+46pp** |
  150. See [EVALUATIONS.md](./EVALUATIONS.md) for the full per-skill breakdown.
  151. ## πŸ“– Skills description
  152. ### Engineering
  153. #### `chrome-extension`
  154. Chrome Extension development with Manifest V3. Covers architecture, messaging, CSP, storage, permissions, content scripts, service workers, and Chrome Web Store publishing.
  155. #### `conventional-git`
  156. Conventional Commits v1.0.0 for branch naming, worktree naming, and commit messages. Keeps git history parseable for auto-changelogs, SemVer bumps, and issue closing.
  157. #### `crxjs`
  158. CRXJS Chrome extension development with Vite. True HMR for popup/options/content scripts/side panels, `defineManifest` for type-safe manifests, dynamic content script imports.
  159. #### `frontend-design-deslop`
  160. Strategy-first UI design for web frontends, apps, dashboards, and landing pages. Escapes AI-generated generic aesthetics (Inter + indigo + rounded cards) by committing to brand adjectives, then deriving a typography and color system, component state matrices, layout rhythm, motion, iconography, and dark mode. Produces a `DESIGN.md` design token contract.
  161. #### `promql-cli`
  162. CLI for querying Prometheus and PromQL-compatible engines (Thanos, Cortex, VictoriaMetrics, Mimir). Instant/range queries, metric discovery, table/csv/json/graph output.
  163. ### Marketing & Content
  164. #### `copywriting-cta`
  165. End-of-article CTA design. Interviews for objective, audience, and context, then produces copy + visual form + mechanism + A/B test plan + accessibility check.
  166. #### `copywriting-hooks`
  167. Opening hooks for long-form articles (blog posts, Substack, LinkedIn long-form, newsletters). Proposes 3-4 hooks with distinct psychological levers: curiosity, contrarian, scene, promise, authority.
  168. #### `copywriting-prose-creator`
  169. Codifies prose mechanics (lexicon, syntax, rhythm, structure) into a PROSE.md style guide. Three modes: BUILD fresh, ADAPT to new channel, AUDIT a corpus. For content factories, ghostwriting teams, house style guides.
  170. #### `copywriting-tone-of-voice-creator`
  171. Builds brand tone of voice guides (TONE.md) with voice attributes, modulation matrix, lexicon, and channel rules. Create from scratch or adapt to a new channel. For B2B, B2C, NGO, public sector, personal brands.
  172. #### `humaniseur-fr`
  173. Removes AI-writing patterns from French text. Detects and fixes 27 patterns: AI vocabulary, anglicisms, formulaic openings, em dash abuse, sycophantic tone, typographic tells.
  174. #### `humanizer-en-asd-ste100`
  175. Rewrites English into ASD-STE100 Simplified Technical English (Issue 9) and de-slops technical documentation β€” decorative emojis, conversation leftovers, Markdown residue, mixed quote styles. Enforces the 53 rules across 9 sections β€” approved word meanings, technical noun/verb categories, sentence-length limits, banned verb tenses, passive-voice restrictions β€” for maintenance manuals, equipment procedures, and any technical text read by non-native speakers or machine translation.
  176. #### `linkedin-ghostwriting`
  177. B2B LinkedIn ghostwriting via strategic interview, hook engineering, and post body. Turns founder stories and results into conversion-focused posts.
  178. #### `press-release-writer`
  179. Professional press releases for any occasion and region. Product launches, funding, partnerships, crisis, M&A, events. Region-specific conventions (Europe, Americas, Asia, etc.).
  180. #### `site-launch-checklist`
  181. Pre-launch checklist for shipping a website. Analytics (GA4, PostHog, GSC), legal, security headers, SEO/GEO, copywriting pass, OpenGraph, favicons, Lighthouse, accessibility. Opinionated for Cloudflare + Vercel.
  182. ### Developer Relations
  183. #### `substack-ghostwriting`
  184. Write, optimize, and grow Substack newsletters and articles. Covers topic selection, headline optimization, SEO, and audience building.
  185. #### `technical-article-writer`
  186. Technical articles and blog posts for senior developers. Opinionated, practical, example-driven content that teaches something or saves time.
  187. ### Productivity
  188. #### `deep-research`
  189. Deep research with parallel web searches, multi-source validation, and cited Markdown reports. 11 research types: market, competitive, technical, academic, financial, legal, trend, community, and more.
  190. #### `influence-and-negotiation`
  191. Negotiation and influence toolkit for any interaction requiring agreement. B2B sales, salary, collective bargaining, hard 1:1s, recruitment, cross-cultural deals. Preparation, live coaching, and diplomatic drafting.
  192. #### `training-report`
  193. Generates structured training reports from session data. Tracks progress, skills acquired, and outcomes.
  194. ### Meta
  195. #### `skill-progressive-disclosure-design`
  196. Design patterns for skill progressive disclosure. Structures skill content for lazy loading so only relevant sections enter context.
  197. #### `snyk-agent-scan-compliance`
  198. Compliance expert for snyk-agent-scan. Validates security scan configurations and ensures compliance with organizational policies.
  199. ## 🎯 Tuning Skill Triggers
  200. If a skill triggers too often or not often enough, please [open an issue](https://github.com/samber/cc-skills/issues) suggesting a description change. The `description` field in SKILL.md frontmatter is the primary triggering mechanism: small wording adjustments can significantly improve trigger accuracy. Some `SKILL.md` might have a `When to use` section which is another level of exclusion. Finally, `SKILL.md` is an entrypoint for lazy loading references with deep knowledge located in `references/`.
  201. ## πŸ”„ Overlap
  202. If your team has its own conventions, create a company skill and declare the override explicitly near the top of its body: `This skill supersedes samber/cc-skills@git-convention skill for [company] projects.`
  203. ## ✍️ Contribute
  204. - **100 tokens per skill description** - what? when to use this skill?
  205. - **1.000–2.500 tokens per SKILL.md** β€” keep the main file focused on essentials
  206. - **Use secondary markdown files for depth** β€” reference them from SKILL.md with relative links (e.g., `[Logging](./logging.md)`). Claude reads these on demand when the topic is relevant, so they don't count against the context budget until needed
  207. - **Up to 10.000 tokens** for full skill and secondary files
  208. - **2–4 skills loaded simultaneously** in a typical session β€” design skills to coexist
  209. - **Stay below ~10k tokens of total loaded SKILL.md** anytime to avoid degrading response quality
  210. For more guidelines, please check `CLAUDE.md`.
  211. ## πŸ’« Fuel the Revolution
  212. - ⭐️ **Star this repo** - Your star powers the caffeine engine!
  213. - β˜•οΈ **Buy me a coffee** - I'll literally use it to build more skills while drinking actual coffee
  214. [![GitHub Sponsors](https://img.shields.io/github/sponsors/samber?style=for-the-badge)](https://github.com/sponsors/samber)
  215. ## πŸ“ License
  216. Copyright Β© 2026 [Samuel Berthe](https://github.com/samber).
  217. This project is under [MIT](./LICENSE) license.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.