agentleFS
Sign inStart free
vindreshsinghvindreshsingh/engineering-skills/CLAUDE.md

engineering-skills

CLAUDE.md0 starsChanged 5 months agoMITView on GitHub

A collection of engineering skills for AI coding agents, packaged as a Claude Code plugin. This file guides work on this repository itself (authoring and maintaining skills). - Define: idea-shaping, product-brief, spec-first - Plan: work-planning, product-grooming - Build: incremental-delivery, test-first, ux-design, mobile-patterns, i18n-l10n, context-curation, source-first, ui-craft, micro-interactions, accessibility, react-patterns, interface-design, design-handoff, resilience, data-modeling, caching-strategy, llm-feature-engineering - Verify: browser-checks, e2e-testing, fault-recovery - Review: review-gate, simplify, hardening, perf-budget, dependency-hygiene, version-upgrade - Ship: git-flow, pipeline-ops, migration-path, decision-docs, technical-writing, launch-readiness - Operate: observability, incident-response,…

The file

We split this CLAUDE.md into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every skill has: overview, When to Use, Process, Common Rationalizations, Red Flags, Verification.

    line 40
  2. Very specific:

    Every SKILL.md has valid YAML frontmatter with name and description.

    line 47
  3. Distinctive:

    Always: follow the skill-anatomy format for new or edited skills.

    line 53
  4. Distinctive:

    Never: add a skill that's vague advice instead of an actionable process.

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

engineering-skills

A collection of engineering skills for AI coding agents, packaged as a Claude Code plugin. This file guides work on this repository itself (authoring and maintaining skills).

Structure

skills/         → One SKILL.md per skill (marketing under skills/marketing/)
agents/sdlc/      → SDLC personas (marketing under agents/marketing/)
marketing/      → Marketing team guide, router (SKILL.md), references
prompts/        → Copy-paste agent prompts + skill-loading instructions
commands/       → Slash commands (/spec, /plan, /build, /test, /review, /ship)
hooks/          → Session lifecycle hooks (guardrails + skill-router injected on session start)
references/     → Engineering checklists (testing, performance, security, accessibility)
docs/           → Getting-started and skill-authoring guides
.claude-plugin/ → Plugin + marketplace manifests

Skills by phase

  • Define: idea-shaping, product-brief, spec-first
  • Plan: work-planning, product-grooming
  • Build: incremental-delivery, test-first, ux-design, mobile-patterns, i18n-l10n, context-curation, source-first, ui-craft, micro-interactions, accessibility, react-patterns, interface-design, design-handoff, resilience, data-modeling, caching-strategy, llm-feature-engineering
  • Verify: browser-checks, e2e-testing, fault-recovery
  • Review: review-gate, simplify, hardening, perf-budget, dependency-hygiene, version-upgrade
  • Ship: git-flow, pipeline-ops, migration-path, decision-docs, technical-writing, launch-readiness
  • Operate: observability, incident-response, finops-budget
  • Grow: skills/marketing/ — growth-strategy, content-marketing, social-distribution, seo-growth, community-engagement (team guide: marketing/)
  • Meta: agent-guardrails (always on), skill-router, skill-creator

Conventions

  • A skill lives in skills/<name>/SKILL.md; the directory name equals the frontmatter name.
  • Frontmatter has name and description; the description says what the skill does, then when to use it.
  • Every skill has: overview, When to Use, Process, Common Rationalizations, Red Flags, Verification.
  • Supporting files only when a section truly exceeds ~100 lines; otherwise fold it in.
  • Link related skills with [[name]]. Don't duplicate content across skills — reference instead.
  • Full format spec: docs/skill-anatomy.md.

Validating a change

  • Every SKILL.md has valid YAML frontmatter with name and description.
  • Each directory name matches its skill's name.
  • Plugin manifests in .claude-plugin/ remain valid JSON.

Boundaries

  • Always follow the skill-anatomy format for new or edited skills.
  • Never add a skill that's vague advice instead of an actionable process.
  • Never duplicate prose between skills — link to the other skill.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free