{"slug": "addy-osmani-agent-skills-25-production-workflows-for-coding-agents", "title": "Addy Osmani agent-skills: 25 Production Workflows for Coding Agents", "summary": "Addy Osmani published agent-skills on GitHub, a production-grade skill library for coding agents containing 25 skills, nine lifecycle commands, four review personas and seven reference checklists, installable in Claude Code, Cursor, Codex, Gemini CLI, Copilot and 70+ agents via the open `npx skills` CLI. The repository, released under the MIT license, trended with hundreds of new stars on November 10, 2026 and organizes work around a DEFINE → PLAN → BUILD → VERIFY → REVIEW → SHIP lifecycle with commands including /spec, /plan, /build, /test, /constraints, /review, /webperf, /code-simplify and /ship. The README warns that skills are executable policy and should be pinned and audited like any agent dependency.", "body_md": "**Addy Osmani published [agent-skills on GitHub](https://github.com/addyosmani/agent-skills?ref=explainx)** as a **production-grade skill library** for coding agents: **25 skills**, **nine lifecycle commands**, **four review personas**, and install paths for **Claude Code, Cursor, Codex, Gemini CLI, Copilot**, and **70+ agents** via the open `npx skills` CLI. The repo trended with **hundreds of new stars on November 10, 2026** because it encodes how senior engineers actually ship — not just how models autocomplete.\n\nIf you already use [Matt Pocock's engineering skills](https://explainx.ai/blog/matt-pocock-agent-skills-real-engineers) or [Janestreet's Socratic tutor pack](https://explainx.ai/blog/janestreet-agent-skills-socratic-tutor-github-2026), this is a **different editorial bet**: a full **DEFINE → PLAN → BUILD → VERIFY → REVIEW → SHIP** belt with explicit anti-rationalization tables in each skill.\n\n## TL;DR\n\n| Question | Answer | \n|---|---|\n| **What ships?** | **25 skills** plus**using-agent-skills** meta skill;**9 commands** ;**4 personas** ;**7 reference checklists** | \n| **Fastest install?** | `npx skills add addyosmani/agent-skills` (per README) | \n| **Claude Code path?** | `/plugin marketplace add addyosmani/agent-skills` then`/plugin install agent-skills@addy-agent-skills` | \n| **License?** | **MIT** per repository LICENSE file | \n| **Stars (Nov 10)?** | **114k+** on GitHub trending snapshot; verify live count on the repo | \n| **Vs Matt Pocock?** | Broader lifecycle; README points to **docs/comparisons** | \n| **Risk?** | Skills are **executable policy** — pin and audit like any agent dependency | \n\n## What the repository contains\n\nSpec-through-ship workflow diagram beside assembled structure for Addy Osmani agent-skills lifecycle commands\n\nThe [README](https://github.com/addyosmani/agent-skills?ref=explainx) frames skills as **workflows, quality gates, and best practices** senior engineers use, packaged so agents follow them consistently. ASCII art in the repo maps:\n\n**DEFINE → PLAN → BUILD → VERIFY → REVIEW → SHIP**\n\nwith commands `/spec`, `/plan`, `/build`, `/test`, `/constraints`, `/review`, `/webperf`, `/code-simplify`, `/ship`.\n\n### The 25 skills (grouped)\n\n**Meta:** `using-agent-skills` routes work to the right workflow.\n\n**Define:** `interview-me`, `idea-refine`, `spec-driven-development`, `constraints-and-standards`.\n\n**Plan:** `planning-and-task-breakdown`.\n\n**Build:** `incremental-implementation`, `test-driven-development`, `context-engineering`, `source-driven-development`, `doubt-driven-development`, `frontend-ui-engineering`, `api-and-interface-design`.\n\n**Verify:** `browser-testing-with-devtools`, `debugging-and-error-recovery`.\n\n**Review:** `code-review-and-quality`, `code-simplification`, `security-and-hardening`, `performance-optimization`.\n\n**Ship:** `git-workflow-and-versioning`, `ci-cd-and-automation`, `deprecation-and-migration`, `documentation-and-adrs`, `observability-and-instrumentation`, `shipping-and-launch`.\n\nEach skill's `SKILL.md` follows a consistent anatomy: overview, when-to-use, process steps, rationalization tables, red flags, and verification evidence — the same **anti-rationalization** pattern we highlighted in [teardown posts on offline HTML skills](https://explainx.ai/blog/teardown-claude-code-skill-3d-simulator-offline-html-github-trending-2026).\n\n### Commands vs skills\n\nCommands are **entry points** that activate skills automatically. Claude Code installs them as plugin commands; where a built-in `/review` collides, the README says to use **`/agent-skills:review`**.\n\nNotable product detail: **`/build` auto mode** generates a plan and implements every task in one approved pass — still **test-driven per task**, still **commits per task**, but fewer human clicks between tasks.\n\n## How to install without breaking your repo layout\n\nThe README is explicit that **hosts use different folders**:\n\n| Tool | Location | \n|---|---|\n| Cursor | Copy under `.cursor/skills/` ; keep short policies in`.cursor/rules/*.mdc` — see`docs/cursor-setup.md` | \n| OpenCode | `.opencode/skills/` plus optional`AGENTS.md` | \n| Gemini CLI | `gemini skills install` with`--path skills` | \n| Codex | `codex plugin marketplace add` /`codex plugin add` | \n| Copilot | Personas in `agents/` , prose in`.github/copilot-instructions.md` ;**slash commands are Claude-only** | \n\n**Portability caveat (issue #361 in README):** installing a **single** skill via `npx skills add … --skill name` copies only that skill folder, **not** repo-level `references/` checklists. Whole-repo install, clone, or manual copy fixes that.\n\n## Personas for multi-angle review\n\nUnder `agents/`, the pack ships:\n\n- **code-reviewer** — five-axis staff-engineer bar\n- **test-engineer** — coverage and prove-it framing\n- **security-auditor** — OWASP-style pass\n- **web-performance-auditor** — Core Web Vitals with metric-honesty rules\n\n`docs/agents.md` covers orchestration, including the rule that **personas do not spawn personas** — relevant if you chain [multi-agent orchestration benchmarks](https://explainx.ai/blog/workflowarena-multi-agent-orchestration-benchmark-einsia-2026) in production.\n\n## How this compares to other skill libraries\n\n| Pack | Emphasis | explainx.ai coverage | \n|---|---|---|\n| **Addy Osmani agent-skills** | Full SDLC, Google-flavored practices cited in README | This post | \n| **Matt Pocock skills** | TypeScript / real-engineer TDD & planning | [Skills guide](https://explainx.ai/blog/matt-pocock-agent-skills-real-engineers) | \n| **ECC (affaan-m)** | Huge agent + skill count, install risk | [ECC harness guide](https://explainx.ai/blog/ecc-affaan-m-agent-harness-71-agents-311-skills-install-risks-github-trending-guide-2026) | \n| **Anthropic / AAIF** | Standard format donation | [Agent Skills explainer](https://explainx.ai/blog/what-are-agent-skills-complete-guide) | \n\nOsmani's README links **docs/comparisons.md** for Superpowers and Matt Pocock — read that file in-repo for his stated deltas. We do not treat comparisons as independent benchmarks.\n\nContext: Osmani moved to **Anthropic to work on Claude Code** in September, covered in [our Addy Osmani hire post](https://explainx.ai/blog/addy-osmani-joins-anthropic-claude-code-2026). This repo is **personal open source**, not an Anthropic product release — still worth watching because it influences how Claude Code power users structure repos.\n\n## Security and supply-chain hygiene\n\nSupply-chain audit metaphor for vetting third-party agent skill packs before production install\n\nSkills are not passive docs. They can instruct agents to run scripts under `scripts/`, edit `CONSTRAINTS.md`, or call browser tools. Before you `npx skills add`:\n\n1. **Read** the`SKILL.md` files you will enable — same bar as[agent skills security threats](https://explainx.ai/blog/agent-skills-security-threat-explainx-verification) .\n2. **Pin** with[skills-lock.json patterns](https://explainx.ai/blog/skills-lock-json-reproducible-agent-skills-2026) where your harness supports them.\n3. **Separate** \"marketing skills\" from repo-specific skills — our[stack-diagram skill post](https://explainx.ai/blog/stack-diagram-agent-skill-architecture-diagrams-github-trending-2026) shows narrow skills that do one job well.\n4. **Check the format spec** — the open[Agent Skills specification](https://agentskills.io/?ref=explainx) describes the`SKILL.md` folder layout and how agents load skills on demand, so you know what a skill can bundle before you enable it.\n\nThe repo includes `evals/` with **25 case files** and CI under `.github/workflows/` — a sign the maintainer expects **regression testing** on skill routing, similar in spirit to [scenario-labs game-art skills](https://explainx.ai/blog/scenario-labs-skills-agent-skills-scenario-mcp-game-art-blender-unity-install-github-trending-2026).\n\n## Adoption: greenfield vs legacy codebases\n\n`docs/adoption.md` (linked from README) splits rollout:\n\n- **Greenfield:** run the full`/spec → /ship` chain from day one.\n- **Legacy:** incremental, verification-first — align with[incremental implementation](https://explainx.ai/blog/beneath-the-surface-agent-harness-evolution-evoaudit-2026) themes in harness evolution posts.\n\nFor teams standardized on **MCP** instead of skills, pair this pack with [MCP comparison guides](https://explainx.ai/blog/what-is-mcp-model-context-protocol-guide) — skills instruct *procedure*; MCP exposes *tools*. Osmani's `browser-testing-with-devtools` skill assumes Chrome DevTools MCP-style workflows.\n\n## What developers are saying\n\nThe older Hacker News thread on related agent-skills discourse (id **47670950** on the candidate feed) had **low engagement** when we checked. Trending stars on GitHub are the stronger signal for this repo — treat social proof as **install interest**, not a security audit.\n\n## Reference checklists and shared artifacts\n\nThe `references/` directory holds seven checklists skills pull on demand: **definition-of-done**, **testing-patterns**, **security-checklist**, **performance-checklist**, **accessibility-checklist**, **observability-checklist**, and **orchestration-patterns**. Keeping them at repo root is why the README warns that **per-skill npx installs** skip shared files — your agent might reference paths that were never copied.\n\n`CONSTRAINTS.md` is another standing artifact: the **constraints-and-standards** skill helps teams write it once so agents stop renegotiating lint rules every session. That mirrors how [Microsoft Copilot managed runtime templates](https://explainx.ai/blog/microsoft-copilot-managed-runtime-github-repo-vite8-template-claude-code-plugin-ms-cli-guide-2026) bake policy into repo scaffolding.\n\n## Hooks, scripts, and CI\n\nThe repository ships **hooks/** for lifecycle automation and **scripts/** (13 utilities per README) used in contributor workflows. `.github/workflows/` runs validation on skill routing using the **evals/** corpus (**25 case files**). If you fork the pack for a company monorepo, treat those evals as a template for **regression tests on skill selection** — the same mindset as [EVOAudit harness evolution](https://explainx.ai/blog/beneath-the-surface-agent-harness-evolution-evoaudit-2026) research.\n\n## Google engineering culture embedded in prose\n\nThe README explicitly cites practices from **Software Engineering at Google** and Google's engineering practices guide: **Hyrum's Law** in API design, the **Beyonce Rule** in testing, change-sizing norms in review, **Chesterton's Fence** in simplification, trunk-based git workflow, **Shift Left** in CI/CD, and treating deprecation as liability. None of that replaces your team's written standards, but it explains why the skills read **opinionated** rather than generic.\n\nIf you are standardizing agent behavior across Cursor and Codex in the same repo, align this pack with [Claude Code command reference](https://explainx.ai/blog/claude-code-commands-complete-reference-guide-2026) habits so humans and agents share vocabulary for `/review` and `/test`.\n\n## When not to install the full pack\n\nSkip the entire marketplace install if you only need **one narrow skill** (for example `browser-testing-with-devtools`) and you are token-sensitive. Copy that `skills/<name>/` folder manually plus any checklist it references. For diagram-heavy repos, compare with [stack-diagram's single-purpose skill](https://explainx.ai/blog/stack-diagram-agent-skill-architecture-diagrams-github-trending-2026) before importing 25 workflows you will never trigger.\n\n## Practical first steps today\n\n1. **Clone or `npx skills add`** the whole repo if you need` references/` checklists.\n2. Run **`/spec` or `interview-me`** on a vague ticket before`/build` auto mode.\n3. Wire **`/constraints` once** per repo so agents stop re-deciding lint and test rules every session — mirrors[DESIGN.md discipline posts](https://explainx.ai/blog/design-md-templates-professional-ui-ai-agents) .\n4. Compare **`doubt-driven-development`** against your existing human review for high-stakes merges.\n\n## Licensing and contribution expectations\n\nThe repository uses the **MIT License**. `CONTRIBUTING.md` and `AGENTS.md` describe how maintainers expect agents and humans to propose skill changes. `plugin.json` at the repo root wires Antigravity and Copilot CLI discovery — useful if your org standardizes on a single plugin manifest per monorepo.\n\nIf you maintain an internal skills registry, index this repo beside explainx.ai's public [skills directory](https://explainx.ai/skills) so new hires see both **domain-specific** packs (TypeScript, CAD, diagrams) and **process-wide** packs (spec-to-ship). Document which commands are safe in CI versus interactive-only so automated agents do not invoke `/ship` on pull requests without human ack.\n\nStars climbed on **November 10, 2026** because the pack sits at the intersection of two hungry audiences: teams adopting **Claude Code plugins** after Fable 5.2 hype, and engineers tired of one-off `SKILL.md` files with no verification section. Neither audience should skip reading the **Red Flags** sections inside each skill — they exist precisely because agents rationalize skipping tests. Schedule a quarterly re-read when the repo tags a release, the same way you bump npm dependencies after security advisories. Capture which slash commands your team actually uses in a one-page RUNBOOK.md so new hires do not invoke `/ship` during exploratory chats.\n\n## Related reading\n\n*Repository star counts, skill names, and install commands are accurate as of November 10, 2026 — confirm on [github.com/addyosmani/agent-skills](https://github.com/addyosmani/agent-skills?ref=explainx).*", "url": "https://wpnews.pro/news/addy-osmani-agent-skills-25-production-workflows-for-coding-agents", "canonical_source": "https://explainx.ai/blog/addy-osmani-agent-skills-production-pack-github-trending-2026?utm_source=rss&utm_medium=feed&utm_campaign=blog", "published_at": "2026-11-10 00:00:00+00:00", "updated_at": "2026-11-10 11:54:37.956537+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "ai-products"], "entities": ["Addy Osmani", "agent-skills", "GitHub", "Claude Code", "Cursor", "Codex", "Gemini CLI", "Copilot"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/addy-osmani-agent-skills-25-production-workflows-for-coding-agents", "markdown": "https://wpnews.pro/news/addy-osmani-agent-skills-25-production-workflows-for-coding-agents.md", "text": "https://wpnews.pro/news/addy-osmani-agent-skills-25-production-workflows-for-coding-agents.txt", "jsonld": "https://wpnews.pro/news/addy-osmani-agent-skills-25-production-workflows-for-coding-agents.jsonld"}}