samber / cc-skills
★ 157A skill package that teaches your agent 20 capabilities — every one documented and browsable below, no GitHub required · by samber.
Each skill below is one capability this package teaches your agent. Install the whole package, or open a skill to install just that one.
Comprehensive guide for building Chrome extensions with Manifest V3. Use this skill whenever the user mentions Chrome extension, browser extension, manifest.json, content script, service worker (in extension context), popup, side panel, chrome.runtime, chrome.tabs, chrome.storage, chrome.scripting, background script, MV3, Manifest V3, or any Chrome extension API. Also trigger when the user wants to inject scripts into web pages, communicate between page and background, bypass CSP from a...
15 files — installable on its own
Conventional Commits v1.0.0 branch naming, worktree naming, and commit message standards for GitHub and GitLab projects. Use when creating branches, naming worktrees, writing commits, generating commit messages, reviewing branch conventions, or setting up changelog automation. Apply when your project needs consistent git history, SemVer-driven releases, parseable changelog generation, or automatic issue closing. Trigger when the user asks how to name a worktree, create a git worktree, or...
3 files — installable on its own
Design end-of-article CTAs (calls-to-action placed at the bottom of blog posts, newsletters, essays, articles, or any long-form content). Use this skill whenever the user asks to write, design, review, or improve a CTA at the bottom of an article, blog post, or essay; mentions "end-of-post CTA", "bottom of the article", "call-to-action", "signup box", "newsletter CTA", "subscribe block", "what should I put at the bottom", "how do I get readers to subscribe / share / book a call / buy /...
7 files — installable on its own
Generate opening hooks and post titles for long-form articles in EN or FR — blog posts, Substack/Medium/dev.to, LinkedIn long-form, paid newsletters, opinion essays, reported features, technical deep-dives. Trigger whenever the user asks for a hook, opening, lede, intro, first sentence/paragraph, opener, accroche, attaque, phrase d'accroche, or première phrase — including making a flat intro punchier or rewriting a draft opening. Also trigger when user asks for a post title, titre d'article,...
6 files — installable on its own
Codifies how someone or a brand writes — prose mechanics (lexicon, syntax, rhythm, structure, signature moves) independent of emotional tone. Output: PROSE.md. Three modes: BUILD a fresh guide from SOUL.md + TONE.md + discovery interview; ADAPT an existing guide to a new channel; AUDIT a corpus for prose patterns before codification. Use when: writing rules for a content factory, codifying ghostwriting voice for multi-writer consistency, defining banned words and sentence-length targets,...
11 files — installable on its own
Build a brand tone of voice guide (TONE.md) via discovery, voice definition, and channel modulation. Outputs voice attributes with do's/don'ts, NN/g positioning, tone modulation matrix, lexicon, mechanics, and channel rules — consumed by downstream content skills writing on-brand copy. Covers B2B SaaS, B2C/D2C, NGO, public sector, consulting, industrial, product-led, personal, and volunteering brands; researches uncovered contexts (politics, regulated niches, religious orgs, gaming) on...
10 files — installable on its own
CRXJS Chrome extension development — true HMR for popup, options, content scripts, side panels, manifest-driven builds, dynamic content script imports (`?script`, `?script&module`), and `defineManifest` for type-safe manifests. Uses Vite as its build tool. Use when the user mentions CRXJS, crxjs, @crxjs/vite-plugin, 'extension with hot reload', 'HMR for chrome extension', or wants to set up a CRXJS-based Chrome extension project with any framework (React, Vue, Svelte, Solid, Vanilla). Also...
1 file — installable on its own
Deep research skill — broad parallel web searches, multi-source validation, confidence tracking, cited Markdown report. Supports 11 research types: market (TAM/SAM, segments, pricing, trends), domain (industry structure, ecosystem, regulatory landscape), technical (architecture, tools, benchmarks), competitive (competitor teardown, positioning, win/loss), product (feature analysis, reviews, roadmap signals), academic (literature survey, citation networks, key authors), person/org (due...
19 files — installable on its own
Produce distinctive, non-generic UI and design applications well, working strategy-first. Identify the project (landing page, SaaS app, dashboard, ecommerce, presentation, docs, portfolio...) and its positioning and personality, commit to brand adjectives, translate into a typography and color system, then apply the craft layer (layout, components and states, motion, iconography, imagery, dark mode and theming, accessibility), avoiding the AI-slop / Claude-esque default. This is both a...
23 files — installable on its own
Remove AI-writing patterns from French text and inject voice, personality, and soul. Use when editing, reviewing, rewriting, or cleaning up French content that reads like ChatGPT/Claude output. Humanize, humanise, déslopifier. Detects and fixes 27 patterns: AI vocabulary overuse (crucial, essentiel, notamment, par ailleurs, dans le paysage), anglicisms from English-first models (faire du sens, adresser un problème), copula avoidance, formulaic openings (À l'ère de, Dans le paysage actuel),...
3 files — installable on its own
Influence and negotiation toolkit for any interaction requiring another person's agreement, even when not framed as 'negotiation'. Covers: B2B sales, salary review, collective bargaining/unions, hard 1:1s, decision announcements, mediation, cross-cultural deals, recruitment, reaching out to a manager, CFO, customer, vendor, or colleague, responding to feedback, headcount requests, declining, pushing back on scope, justifying a delay, explaining a decision, raising a concern, getting...
15 files — installable on its own
B2B LinkedIn ghostwriting — strategic interview, hook engineering, and post body. Use when the user wants to write LinkedIn content, create ghostwritten posts, ghostwrite for a founder or executive, develop a B2B social strategy, or needs hooks, post structures, or copywriting frameworks for LinkedIn. Apply when the user shares a story, result, or insight and wants it turned into a post.
6 files — installable on its own
Write professional press releases for any occasion, media type, and country. Use when the user wants to write, draft, or improve a press release, communiqué de presse, media announcement, news release, or PR statement — including product launches, funding rounds, partnerships, crisis communications, earnings, executive hires, events, M&A, open source milestones, and media advisories. Covers all release types, media targets (print, digital/wire, broadcast, social/SMPR, trade press), and...
10 files — installable on its own
CLI for querying Prometheus and PromQL-compatible engines (Thanos, Cortex, VictoriaMetrics, Grafana Mimir, Grafana Tempo...) — instant queries, range queries, metric discovery (metrics/labels/meta subcommands), output formats (table/csv/json/graph). Apply when executing PromQL queries, troubleshooting performance issues on a software having observability, investigating latency/error rates/saturation, or analyzing time series data.
9 files — installable on its own
Pre-launch checklist for shipping a new website. Orchestrates analytics setup (GA4, PostHog, Google Search Console, Ahrefs), legal compliance, security headers and audit, SEO and GEO with keyword research validated against Google Trends (robots.txt, sitemaps, llms.txt, AI policy, schema markup, hreflang), copywriting consistency via a TONE.md and a humanizer pass in the matching language, OpenGraph and social previews, full favicon set with manifest, quality gates (Lighthouse, Core Web...
7 files — installable on its own
Decide how to split skill content between SKILL.md and reference files for context efficiency and reliable triggering. Use this whenever creating a new Claude skill, refactoring an existing one, or when a SKILL.md is growing past 300-400 lines. Also trigger when the user mentions "progressive disclosure", "reference files", "splitting skills", "skill bundling", "context window for skills", "SKILL.md too long", "what goes in references/", "skill structure", or expresses any uncertainty about...
3 files — installable on its own
Compliance expert for snyk-agent-scan — the agent skill file scanner — NOT for other Snyk CLI tools (snyk test, snyk code SAST, snyk iac, snyk container). Fixes alerts through content restructuring, never by suppressing or deleting information. Covers every file in a skill directory: SKILL.md, references/, assets/, and any secondary markdown. Apply when authoring a new skill, editing an existing one, triaging a failed snyk-agent-scan run locally or in CI, or unblocking a PR held by agent...
7 files — installable on its own
Write, optimize, and grow Substack content — both newsletter issues (email-first) and web posts (web-first articles/essays). Covers ghostwriting with voice matching, Substack algorithm optimization, Notes strategy, email formatting, SEO, growth tactics, and monetization planning. Use when the user mentions Substack, newsletters, write a newsletter issue, Substack post, Substack article, web post on Substack, evergreen content, SEO for Substack, newsletter growth, Notes strategy, ghostwrite...
10 files — installable on its own
Write compelling technical articles and blog posts for developer audiences. Use this skill whenever the user asks to write a blog post, technical article, or any long-form technical content. Also trigger when the user says 'write about [technical topic]', 'help me draft an article', 'turn this into a blog post', 'write a post about', 'I want to publish something about', or mentions writing for a developer audience. Covers the full pipeline: idea sharpening, hook/title generation, article...
6 files — installable on its own
Produce a professional training/workshop report as a .docx file. Use this skill whenever the user mentions "training report", "workshop report", "compte rendu", "compte rendu de formation", "formation report", "debriefing a workshop", "write up a training session", "résumé de formation", or any request to document a training session, workshop, or onboarding event with individual participant feedback and recommendations. Also trigger when the user says things like "I just ran a workshop and...
7 files — installable on its own
Agent Skills
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.
For Golang-related skills, please visit cc-skills-golang.
<img width="3808" height="1280" alt="image" src="https://github.com/user-attachments/assets/95139f6f-c19c-4041-a010-d94bca594bba" />[!IMPORTANT] Bootstrapped with Claude. Edited, tested, reviewed and reworked by a human.
No AI slop here. AI-made skills are useless.
🚀 How to use?
Install with skills CLI (universal, works with any Agent Skills-compatible tool):
npx skills add https://github.com/samber/cc-skills --all
# or a single skill:
npx skills add https://github.com/samber/cc-skills --skill promql-cli/plugin marketplace add samber/cc
/plugin install cc-skills@samberCopy skills into the cross-client discovery directory:
git clone https://github.com/samber/cc-skills.git ~/.openclaw/skills/cc-skills
# or in workspace:
git clone https://github.com/samber/cc-skills.git ~/.openclaw/workspace/skills/cc-skillsgemini extensions install https://github.com/samber/cc-skillsUpdate with gemini extensions update cc-skills.
Copy skills into the cross-client discovery directory:
git clone https://github.com/samber/cc-skills.git ~/.cursor/skills/cc-skillsCursor auto-discovers skills from .agents/skills/ and .cursor/skills/.
Copy skills into the cross-client discovery directory:
/plugin install https://github.com/samber/cc-skills
# or
git clone https://github.com/samber/cc-skills.git ~/.copilot/skills/cc-skillsCopilot auto-discovers skills from .copilot/skills/.
Copy skills into the cross-client discovery directory:
git clone https://github.com/samber/cc-skills.git ~/.agents/skills/cc-skillsOpenCode auto-discovers skills from .agents/skills/, .opencode/skills/, and .claude/skills/.
Clone into the cross-client discovery path:
git clone https://github.com/samber/cc-skills.git ~/.agents/skills/cc-skillsCodex auto-discovers skills from ~/.agents/skills/ and .agents/skills/. Update with cd ~/.agents/skills/cc-skills && git pull.
Clone and symlink into the cross-client discovery path:
git clone https://github.com/samber/cc-skills.git ~/.antigravity/skills/cc-skillsUpdate with cd ~/.antigravity/skills/cc-skills && git pull.
🧩 Skills
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.
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.
- Description (tok): weight of the
descriptionfield from YAML frontmatter, always loaded into Claude's context for skill triggering - SKILL.md (tok): weight of the full
SKILL.mdfile loaded when the skill triggers - Directory (tok): weight of all files in the skill directory (SKILL.md + referenced markdown files)
┌──────────────┐
│ Agent Skills │
└───────┬──────┘
│
┌──────────────────┴──────────┐
│ │
▼ ▼
┌────────────────────────┐ ┌─────────────────────────────────────┐
│ Engineering │ │ Marketing & Content │
├────────────────────────┤ ├─────────────────────────────────────┤
│ conventional-git │ │ linkedin-ghostwriting │
│ promql-cli │ │ press-release-writer │
│ chrome-extension │ │ humaniseur-fr │
│ crxjs │ │ copywriting-hooks │
│ site-launch-checklist │ │ copywriting-cta │
│ frontend-design-deslop │ │ copywriting-prose-creator │
│ │ │ copywriting-tone-of-voice-creator │
└────────────────────────┘ └─────────────────────────────────────┘
┌──────────────────────────┐ ┌───────────────────────────┐ ┌─────────────────────────────────────┐
│ Developer Relations │ │ Productivity │ │ Meta │
├──────────────────────────┤ ├───────────────────────────┤ ├─────────────────────────────────────┤
│ technical-article-writer │ │ deep-research │ │ snyk-agent-scan-compliance │
│ substack-ghostwriting │ │ influence-and-negotiation │ │ skill-progressive-disclosure-design │
│ │ │ training-report │ │ │
└──────────────────────────┘ └───────────────────────────┘ └─────────────────────────────────────┘| Skill | Error rate gap | Description (tok) | SKILL.md (tok) | Directory (tok) |
|---|---|---|---|---|
conventional-git | -36% | 73 | 1,446 | 1,446 |
promql-cli | -39% | 87 | 1,257 | 6,248 |
chrome-extension | — | 137 | 3,909 | 36,173 |
crxjs | — | 185 | 2,697 | 2,697 |
site-launch-checklist | -59% | 222 | 6,772 | 13,350 |
frontend-design-deslop | -28% | 220 | 3,859 | 40,876 |
linkedin-ghostwriting | -31% | 87 | 1,045 | 1,993 |
substack-ghostwriting | -51% | 205 | 3,315 | 10,720 |
technical-article-writer | -33% | 147 | 2,295 | 5,737 |
press-release-writer | -34% | 149 | 1,532 | 17,829 |
humaniseur-fr | -14% | 249 | 5,895 | 5,895 |
snyk-agent-scan-compliance | -27% | 144 | 1,884 | 5,592 |
training-report | -61% | 179 | 2,392 | 8,222 |
deep-research | -51% | 316 | 2,915 | 14,070 |
influence-and-negotiation | -68% | 237 | 6,644 | 50,467 |
skill-progressive-disclosure-design | -58% | 154 | 3,533 | 3,533 |
copywriting-hooks | — | 213 | 5,483 | 10,303 |
copywriting-cta | — | 229 | 2,889 | 14,427 |
copywriting-prose-creator | — | 201 | 4,786 | 23,565 |
copywriting-tone-of-voice-creator | — | 223 | 4,030 | 22,286 |
🧪 Skill evaluations
| With Skill | Without Skill | Delta | |
|---|---|---|---|
| Overall | 98% | 50% | +48pp |
See EVALUATIONS.md for the full per-skill breakdown.
📖 Skills description
Engineering
chrome-extension
Chrome Extension development with Manifest V3. Covers architecture, messaging, CSP, storage, permissions, content scripts, service workers, and Chrome Web Store publishing.
conventional-git
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.
crxjs
CRXJS Chrome extension development with Vite. True HMR for popup/options/content scripts/side panels, defineManifest for type-safe manifests, dynamic content script imports.
frontend-design-deslop
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.
promql-cli
CLI for querying Prometheus and PromQL-compatible engines (Thanos, Cortex, VictoriaMetrics, Mimir). Instant/range queries, metric discovery, table/csv/json/graph output.
Marketing & Content
copywriting-cta
End-of-article CTA design. Interviews for objective, audience, and context, then produces copy + visual form + mechanism + A/B test plan + accessibility check.
copywriting-hooks
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.
copywriting-prose-creator
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.
copywriting-tone-of-voice-creator
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.
humaniseur-fr
Removes AI-writing patterns from French text. Detects and fixes 27 patterns: AI vocabulary, anglicisms, formulaic openings, em dash abuse, sycophantic tone, typographic tells.
linkedin-ghostwriting
B2B LinkedIn ghostwriting via strategic interview, hook engineering, and post body. Turns founder stories and results into conversion-focused posts.
press-release-writer
Professional press releases for any occasion and region. Product launches, funding, partnerships, crisis, M&A, events. Region-specific conventions (Europe, Americas, Asia, etc.).
site-launch-checklist
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.
Developer Relations
substack-ghostwriting
Write, optimize, and grow Substack newsletters and articles. Covers topic selection, headline optimization, SEO, and audience building.
technical-article-writer
Technical articles and blog posts for senior developers. Opinionated, practical, example-driven content that teaches something or saves time.
Productivity
deep-research
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.
influence-and-negotiation
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.
training-report
Generates structured training reports from session data. Tracks progress, skills acquired, and outcomes.
Meta
skill-progressive-disclosure-design
Design patterns for skill progressive disclosure. Structures skill content for lazy loading so only relevant sections enter context.
snyk-agent-scan-compliance
Compliance expert for snyk-agent-scan. Validates security scan configurations and ensures compliance with organizational policies.
🎯 Tuning Skill Triggers
If a skill triggers too often or not often enough, please open an issue 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/.
🔄 Overlap
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.
✍️ Contribute
- 100 tokens per skill description - what? when to use this skill?
- 1.000–2.500 tokens per SKILL.md — keep the main file focused on essentials
- 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 - Up to 10.000 tokens for full skill and secondary files
- 2–4 skills loaded simultaneously in a typical session — design skills to coexist
- Stay below ~10k tokens of total loaded SKILL.md anytime to avoid degrading response quality
For more guidelines, please check CLAUDE.md.
💫 Fuel the Revolution
- ⭐️ Star this repo - Your star powers the caffeine engine!
- ☕️ Buy me a coffee - I'll literally use it to build more skills while drinking actual coffee
📝 License
Copyright © 2026 Samuel Berthe.
This project is under MIT license.
Install the whole package (20 skills):
npx skills add https://github.com/samber/cc-skillsOr install a single skill:
npx skills add https://github.com/samber/cc-skills --skill <name>Pick the skill name from the Skills tab — each entry there installs independently.