{
  "markdown": "# Agent Skills\n\nAI 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).\n\nFor Golang-related skills, please visit [cc-skills-golang](https://github.com/samber/cc-skills-golang).\n\n<!-- prettier-ignore-start -->\n\n> [!IMPORTANT]\n> Bootstrapped with Claude. **Edited, tested, reviewed and reworked by a human**.\n>\n> **No AI slop here.** AI-made skills are useless.\n\n<!-- prettier-ignore-end -->\n\n<img width=\"3808\" height=\"1280\" alt=\"image\" src=\"https://github.com/user-attachments/assets/95139f6f-c19c-4041-a010-d94bca594bba\" />\n\n## 🚀 How to use?\n\n**Install with [skills](https://skills.sh/) CLI** (universal, works with any [Agent Skills](https://agentskills.io)-compatible tool):\n\n```bash\nnpx skills add https://github.com/samber/cc-skills --all\n# or a single skill:\nnpx skills add https://github.com/samber/cc-skills --skill promql-cli\n```\n\n<!-- prettier-ignore-start -->\n\n<details>\n<summary>Claude Code</summary>\n\n```bash\n/plugin marketplace add samber/cc\n/plugin install cc-skills@samber\n```\n\n</details>\n\n<details>\n<summary>Openclaw</summary>\n\nCopy skills into the cross-client discovery directory:\n\n```bash\ngit clone https://github.com/samber/cc-skills.git ~/.openclaw/skills/cc-skills\n# or in workspace:\ngit clone https://github.com/samber/cc-skills.git ~/.openclaw/workspace/skills/cc-skills\n```\n\n</details>\n\n<details>\n<summary>Gemini CLI</summary>\n\n```bash\ngemini extensions install https://github.com/samber/cc-skills\n```\n\nUpdate with `gemini extensions update cc-skills`.\n\n</details>\n\n<details>\n<summary>Cursor</summary>\n\nCopy skills into the cross-client discovery directory:\n\n```bash\ngit clone https://github.com/samber/cc-skills.git  ~/.cursor/skills/cc-skills\n```\n\nCursor auto-discovers skills from `.agents/skills/` and `.cursor/skills/`.\n\n</details>\n\n<details>\n<summary>Copilot</summary>\n\nCopy skills into the cross-client discovery directory:\n\n```bash\n/plugin install https://github.com/samber/cc-skills\n# or\ngit clone https://github.com/samber/cc-skills.git ~/.copilot/skills/cc-skills\n```\n\nCopilot auto-discovers skills from `.copilot/skills/`.\n\n</details>\n\n<details>\n<summary>OpenCode</summary>\n\nCopy skills into the cross-client discovery directory:\n\n```bash\ngit clone https://github.com/samber/cc-skills.git ~/.agents/skills/cc-skills\n```\n\nOpenCode auto-discovers skills from `.agents/skills/`, `.opencode/skills/`, and `.claude/skills/`.\n\n</details>\n\n<details>\n<summary>Codex (OpenAI)</summary>\n\nClone into the cross-client discovery path:\n\n```bash\ngit clone https://github.com/samber/cc-skills.git ~/.agents/skills/cc-skills\n```\n\nCodex auto-discovers skills from `~/.agents/skills/` and `.agents/skills/`. Update with `cd ~/.agents/skills/cc-skills && git pull`.\n\n</details>\n\n<details>\n<summary>Antigravity</summary>\n\nClone and symlink into the cross-client discovery path:\n\n```bash\ngit clone https://github.com/samber/cc-skills.git ~/.antigravity/skills/cc-skills\n```\n\nUpdate with `cd ~/.antigravity/skills/cc-skills && git pull`.\n\n</details>\n\n<!-- prettier-ignore-end -->\n\n## 🧩 Skills\n\nThese 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.\n\nEach 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.\n\n- **Description (tok)**: weight of the `description` field from YAML frontmatter, always loaded into Claude's context for skill triggering\n- **SKILL.md (tok)**: weight of the full `SKILL.md` file loaded when the skill triggers\n- **Directory (tok)**: weight of all files in the skill directory (SKILL.md + referenced markdown files)\n\n```\n                     ┌──────────────┐\n                     │ Agent Skills │\n                     └───────┬──────┘\n                             │\n          ┌──────────────────┴──────────┐\n          │                             │\n          ▼                             ▼\n┌────────────────────────┐  ┌──────────────────────────────────────┐\n│      Engineering       │  │         Marketing & Content          │\n├────────────────────────┤  ├──────────────────────────────────────┤\n│ conventional-git       │  │ linkedin-ghostwriting                │\n│ promql-cli             │  │ press-release-writer                 │\n│ chrome-extension       │  │ humaniseur-fr                        │\n│ crxjs                  │  │ humanizer-en-asd-ste100              │\n│ site-launch-checklist  │  │ copywriting-hooks                    │\n│ frontend-design-deslop │  │ copywriting-cta                      │\n│                        │  │ copywriting-prose-creator            │\n│                        │  │ copywriting-tone-of-voice-creator    │\n└────────────────────────┘  └──────────────────────────────────────┘\n\n┌──────────────────────────┐  ┌───────────────────────────┐  ┌─────────────────────────────────────┐\n│   Developer Relations    │  │       Productivity        │  │                Meta                 │\n├──────────────────────────┤  ├───────────────────────────┤  ├─────────────────────────────────────┤\n│ technical-article-writer │  │ deep-research             │  │ snyk-agent-scan-compliance          │\n│ substack-ghostwriting    │  │ influence-and-negotiation │  │ skill-progressive-disclosure-design │\n│                          │  │ training-report           │  │                                     │\n└──────────────────────────┘  └───────────────────────────┘  └─────────────────────────────────────┘\n```\n\n| Skill | Error rate gap | Description (tok) | SKILL.md (tok) | Directory (tok) |\n| --- | --- | --- | --- | --- |\n| `conventional-git` | -36% | 73 | 1,446 | 1,446 |\n| `promql-cli` | -39% | 87 | 1,257 | 6,248 |\n| `chrome-extension` | — | 137 | 3,909 | 36,173 |\n| `crxjs` | — | 185 | 2,697 | 2,697 |\n| `site-launch-checklist` | -59% | 198 | 7,784 | 17,896 |\n| `frontend-design-deslop` | -28% | 168 | 4,294 | 45,097 |\n| `linkedin-ghostwriting` | -31% | 87 | 1,045 | 1,993 |\n| `substack-ghostwriting` | -51% | 154 | 3,416 | 10,821 |\n| `technical-article-writer` | -33% | 157 | 2,809 | 6,251 |\n| `press-release-writer` | -34% | 159 | 1,686 | 17,981 |\n| `humaniseur-fr` | -14% | 166 | 10,782 | 10,782 |\n| `humanizer-en-asd-ste100` | -16% | 141 | 9,594 | 9,594 |\n| `snyk-agent-scan-compliance` | -27% | 144 | 1,904 | 5,612 |\n| `training-report` | -61% | 179 | 2,392 | 8,222 |\n| `deep-research` | -51% | 316 | 2,997 | 14,125 |\n| `influence-and-negotiation` | -68% | 162 | 6,592 | 48,996 |\n| `skill-progressive-disclosure-design` | -58% | 154 | 3,607 | 3,607 |\n| `copywriting-hooks` | — | 169 | 6,705 | 13,484 |\n| `copywriting-cta` | — | 165 | 2,873 | 14,424 |\n| `copywriting-prose-creator` | — | 166 | 4,952 | 24,900 |\n| `copywriting-tone-of-voice-creator` | — | 181 | 4,056 | 22,315 |\n\n## 🧪 Skill evaluations\n\n|             | With Skill | Without Skill | Delta     |\n| ----------- | ---------- | ------------- | --------- |\n| **Overall** | **98%**    | **52%**       | **+46pp** |\n\nSee [EVALUATIONS.md](./EVALUATIONS.md) for the full per-skill breakdown.\n\n## 📖 Skills description\n\n### Engineering\n\n#### `chrome-extension`\n\nChrome Extension development with Manifest V3. Covers architecture, messaging, CSP, storage, permissions, content scripts, service workers, and Chrome Web Store publishing.\n\n#### `conventional-git`\n\nConventional Commits v1.0.0 for branch naming, worktree naming, and commit messages. Keeps git history parseable for auto-changelogs, SemVer bumps, and issue closing.\n\n#### `crxjs`\n\nCRXJS Chrome extension development with Vite. True HMR for popup/options/content scripts/side panels, `defineManifest` for type-safe manifests, dynamic content script imports.\n\n#### `frontend-design-deslop`\n\nStrategy-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.\n\n#### `promql-cli`\n\nCLI for querying Prometheus and PromQL-compatible engines (Thanos, Cortex, VictoriaMetrics, Mimir). Instant/range queries, metric discovery, table/csv/json/graph output.\n\n### Marketing & Content\n\n#### `copywriting-cta`\n\nEnd-of-article CTA design. Interviews for objective, audience, and context, then produces copy + visual form + mechanism + A/B test plan + accessibility check.\n\n#### `copywriting-hooks`\n\nOpening 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.\n\n#### `copywriting-prose-creator`\n\nCodifies 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.\n\n#### `copywriting-tone-of-voice-creator`\n\nBuilds 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.\n\n#### `humaniseur-fr`\n\nRemoves AI-writing patterns from French text. Detects and fixes 27 patterns: AI vocabulary, anglicisms, formulaic openings, em dash abuse, sycophantic tone, typographic tells.\n\n#### `humanizer-en-asd-ste100`\n\nRewrites English into ASD-STE100 Simplified Technical English (Issue 9) and de-slops technical documentation — decorative emojis, conversation leftovers, Markdown residue, mixed quote styles. Enforces the 53 rules across 9 sections — approved word meanings, technical noun/verb categories, sentence-length limits, banned verb tenses, passive-voice restrictions — for maintenance manuals, equipment procedures, and any technical text read by non-native speakers or machine translation.\n\n#### `linkedin-ghostwriting`\n\nB2B LinkedIn ghostwriting via strategic interview, hook engineering, and post body. Turns founder stories and results into conversion-focused posts.\n\n#### `press-release-writer`\n\nProfessional press releases for any occasion and region. Product launches, funding, partnerships, crisis, M&A, events. Region-specific conventions (Europe, Americas, Asia, etc.).\n\n#### `site-launch-checklist`\n\nPre-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.\n\n### Developer Relations\n\n#### `substack-ghostwriting`\n\nWrite, optimize, and grow Substack newsletters and articles. Covers topic selection, headline optimization, SEO, and audience building.\n\n#### `technical-article-writer`\n\nTechnical articles and blog posts for senior developers. Opinionated, practical, example-driven content that teaches something or saves time.\n\n### Productivity\n\n#### `deep-research`\n\nDeep 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.\n\n#### `influence-and-negotiation`\n\nNegotiation 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.\n\n#### `training-report`\n\nGenerates structured training reports from session data. Tracks progress, skills acquired, and outcomes.\n\n### Meta\n\n#### `skill-progressive-disclosure-design`\n\nDesign patterns for skill progressive disclosure. Structures skill content for lazy loading so only relevant sections enter context.\n\n#### `snyk-agent-scan-compliance`\n\nCompliance expert for snyk-agent-scan. Validates security scan configurations and ensures compliance with organizational policies.\n\n## 🎯 Tuning Skill Triggers\n\nIf 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/`.\n\n## 🔄 Overlap\n\nIf 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.`\n\n## ✍️ Contribute\n\n- **100 tokens per skill description** - what? when to use this skill?\n- **1.000–2.500 tokens per SKILL.md** — keep the main file focused on essentials\n- **Use secondary markdown files for depth** — 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\n- **Up to 10.000 tokens** for full skill and secondary files\n- **2–4 skills loaded simultaneously** in a typical session — design skills to coexist\n- **Stay below ~10k tokens of total loaded SKILL.md** anytime to avoid degrading response quality\n\nFor more guidelines, please check `CLAUDE.md`.\n\n## 💫 Fuel the Revolution\n\n- ⭐️ **Star this repo** - Your star powers the caffeine engine!\n- ☕️ **Buy me a coffee** - I'll literally use it to build more skills while drinking actual coffee\n\n[![GitHub Sponsors](https://img.shields.io/github/sponsors/samber?style=for-the-badge)](https://github.com/sponsors/samber)\n\n## 📝 License\n\nCopyright © 2026 [Samuel Berthe](https://github.com/samber).\n\nThis project is under [MIT](./LICENSE) license.\n",
  "bytes": 14171,
  "sha": "48dcf68ff59760c42f04cd67be91f08495fa981e497aed31313490618f76a213",
  "repo_slug": "samber/cc-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_samber_cc_skills_linkedin_ghostwriting_9ad10ddf/readme"
}