# agent-skills changelog

> agent-skills release notes.

- Vendor: agent-skills
- Category: AI
- Official site: https://skills.addy.ie/
- Tracked by: What's New (https://whatsnew.fyi/product/agent-skills)
- Harvested from: GitHub (addyosmani/agent-skills)
- Entries below: 7 (newest first)

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

## Releases

### 0.6.5

- Date: 2026-07-26
- Version: 0.6.5
- Original notes: https://github.com/addyosmani/agent-skills/releases/tag/0.6.5
- Permalink: https://whatsnew.fyi/product/agent-skills/releases/0.6.5

- **changed** — Eval gates are now enforced in CI on every push with a rank-1 floor and ratcheted routing quality
- **added** — Dialogue evals are now supported for skills whose deliverable is the conversation itself rather than a file edit
- **fixed** — Skill validator no longer trips over headings inside fenced code blocks or negated trigger phrases
- **changed** — Lint rules were extracted into scripts/lib/skill-lint.js with their own unit tests
- **changed** — test-driven-development skill no longer hardcodes npm and instead describes the repository's own test command
- **changed** — ADR skill now detects and matches an existing ADR convention before creating a new one
- **fixed** — Orchestration-patterns reference mapping in the getting-started docs so the links resolve
- **fixed** — Opt-in hook paths are now quoted in the setup docs so installs no longer break on paths with spaces
- **fixed** — The simplify-ignore-test hook asserts its no-jq guard instead of failing when jq is absent
- **added** — New skill-gap issue form so people can report guidance that doesn't match reality in a structured way
- **added** — Shared references/ design is now documented with its rationale and skill-local references/ directory is described as the emerging convention
- **changed** — README spacing and copy tidy-ups

Agent Skills 0.6.5 graduates the eval framework from opt-in to CI-enforced, hardens the validators, and kicks off an ecosystem-neutral pass so the skills stop assuming a JavaScript stack. Mostly a quality-and-infrastructure release on top of 0.6.4.

##### Highlights

- **Eval gates are now trusted and enforced in CI** (#381, @ZhiyaoWen999). The deterministic trigger-and-routing tier runs on every push with a rank-1 floor, the gates are ratcheted so routing quality can only move up, and dialogue evals are supported for skills whose deliverable is the conversation itself rather than a file edit. The framework shipped in 0.6.4; this is where it starts actually guarding the pack.
- **Validators hardened** (#387/#405, @kevglynn; #379, @nucliweb). The skill validator no longer trips over headings inside fenced code blocks or negated trigger phrases, and the lint rules were extracted into `scripts/lib/skill-lint.js` with their own tests so the rules are unit-tested instead of buried in the runner.
- **Ecosystem-neutral pass, Phase 1** (#419, @ayobamiseun). `test-driven-development` no longer hardcodes `npm`; it describes the repository's own test command with one concrete example, so the guidance reads correctly on Python, Go, Rust, and the rest. This is the first skill in a broader pass.

##### Skills and content

- ADR skill now detects and matches an existing ADR convention before creating a new one, and stays repository-local and forge-agnostic (#402, @CybotTM).
- Fixed the orchestration-patterns reference mapping in the getting-started docs so the links resolve (#407, @Quantum22).

##### Tooling and fixes

- `fix(hooks)`: opt-in hook paths are now quoted in the setup docs, so installs no longer break on paths with spaces (#420, @jagadishs-oss).
- `fix(hooks)`: the simplify-ignore-test hook asserts its no-jq guard instead of failing when `jq` is absent (#406, @youjinch).

##### Docs

- The shared `references/` design is now documented with its rationale, and the skill-local `references/` directory is described as the emerging convention for self-contained skills (#401, @kevglynn; #236, @nucliweb; closes #329).
- New skill-gap issue form so people can report guidance that doesn't match reality in a structured way (#418, @Alex7develop).
- README spacing and copy tidy-ups (#107, @ZuoFuhong).

##### Thanks

Thanks to everyone who contributed this release: @ZhiyaoWen999, @nucliweb, @kevglynn, @ayobamiseun, @CybotTM, @Quantum22, @jagadishs-oss, @youjinch, @Alex7develop, and @ZuoFuhong.

**Full Changelog**: https://github.com/addyosmani/agent-skills/compare/0.6.4...0.6.5

### 0.6.4

- Date: 2026-07-12
- Version: 0.6.4
- Original notes: https://github.com/addyosmani/agent-skills/releases/tag/0.6.4
- Permalink: https://whatsnew.fyi/product/agent-skills/releases/0.6.4

- **added** — Skill eval framework with three-tier validation system including structural validation, deterministic trigger-and-routing checks in CI, and optional behavioral tier for grading execution traces
- **added** — Native Codex support to install as a Codex plugin with codex plugin marketplace add addyosmani/agent-skills
- **added** — Dependency-upgrade workflow to code-review-and-quality skill
- **added** — Database expand/contract schema migrations to deprecation-and-migration skill
- **changed** — Frontend and performance skill descriptions updated to match user vocabulary, improving trigger rank-1 rate to 86%
- **changed** — Playwright examples switched to accessibility-first role and label locators
- **changed** — Quick Start in README now leads with npx skills add addyosmani/agent-skills as fastest install path
- **fixed** — Hardened eval and command validators for CRLF and Windows line endings with fixture path-traversal guard
- **security** — Supply-chain hardening with package-manager and version-aware dependency guidance and install-script gate that blocks unreviewed lifecycle scripts before first install
- **changed** — Documented HTTPS git-config workaround for plugin install SSH failures on Windows and macOS
- **added** — New adoption guide covering greenfield vs brownfield rollout with verification-first path for established codebases
- **added** — New developer-onboarding guide for contributors working on the repository
- **changed** — Cursor setup modernized for native .cursor/skills
- **changed** — comparison.md refreshed with expanded how to decide section and documented no-translations policy
- **changed** — AGENTS.md and CLAUDE.md clarified as repo-scoped with Team section added to README
- **changed** — webperf configuration guidance updated to keep CrUX API keys in environment variables rather than hard-coded

Agent Skills 0.6.4 adds two big pieces, an in-repo skill eval framework and native Codex support, alongside a security-hardening pass, real skill-content additions, and a wave of adoption and contributor docs.

##### Highlights

- **Skill eval framework** (#342). A three-tier system that checks the pack actually works: structural validation, a deterministic trigger-and-routing tier that runs in CI (does each skill's description carry the words users say, and do any two skills collide), and an opt-in behavioral tier that grades a real execution trace against per-skill expectations. Neither of the packs we get compared to ships this in-repo.
- **Native Codex support** (#88). Install as a Codex plugin with `codex plugin marketplace add addyosmani/agent-skills`; the root `skills/` directory is read directly through `.codex-plugin/plugin.json`, no duplication.
- **Fastest install path in the README**. `npx skills add addyosmani/agent-skills` now leads the Quick Start, one command across 70+ agents, with per-skill installs for the headline skills.
- **Supply-chain hardening** (#392). The dependency guidance is now package-manager and version aware, with an install-script gate that blocks unreviewed lifecycle scripts before the first install, the exact hole the recent npm postinstall worms used.

##### Skills and content

- Dependency-upgrade workflow added to `code-review-and-quality` (#346, @HMAKT99).
- Database expand/contract schema migrations added to `deprecation-and-migration` (#345, @HMAKT99).
- Frontend and performance descriptions now carry the vocabulary users actually type; trigger rank-1 rate up to 86% (#358, @ZhiyaoWen999).
- Playwright examples switched to accessibility-first role and label locators (#359, @debs-obrien).

##### Tooling and fixes

- Harden the eval and command validators for CRLF and Windows line endings, plus a fixture path-traversal guard (#372, @ShiroKSH).
- webperf config note: keep CrUX API keys in environment variables, never hard-coded (#357, @orbisai0security).
- Document the HTTPS git-config workaround for `/plugin install` SSH failures on Windows and macOS (#368, @mvanhorn).

##### Docs

- New adoption guide: greenfield vs brownfield rollout, with a verification-first path for established codebases (#396, @nucliweb).
- New developer-onboarding guide for people working on the repo itself (#397, @nucliweb).
- Cursor setup modernized for native `.cursor/skills` (#218, @nguyenducthaonguyen).
- comparison.md refreshed and expanded with a fuller "how to decide" section; no-translations policy documented (#375, @nucliweb); AGENTS.md and CLAUDE.md clarified as repo-scoped (#374, @nucliweb); a Team section added to the README.

##### Thanks

Thanks to everyone who contributed this release: @nucliweb, @federicobartoli, @HMAKT99, @ZhiyaoWen999, @ShiroKSH, @mvanhorn, @nguyenducthaonguyen, @debs-obrien, and @orbisai0security.

**Full Changelog**: https://github.com/addyosmani/agent-skills/compare/0.6.3...0.6.4

### 0.6.3

- Date: 2026-07-03
- Version: 0.6.3
- Original notes: https://github.com/addyosmani/agent-skills/releases/tag/0.6.3
- Permalink: https://whatsnew.fyi/product/agent-skills/releases/0.6.3

- **changed** — code-review-and-quality skill gains structural-depth lenses including reduce-don't-relocate pattern, a named Structural Remedies catalog, a file-size gate, and finding prioritization
- **changed** — Severity labels in code-review-and-quality now line up with the skill's own taxonomy
- **added** — New observability reference checklist covering on-call questions, RED/USE metrics, and symptom-based alerting
- **added** — New project-wide Definition of Done reference checklist
- **added** — New comparison documentation (docs/comparison.md) comparing agent-skills with Superpowers and Matt Pocock's skills
- **added** — CONTRIBUTING pre-flight checklist as guardrail against duplicate skills
- **added** — Path-scoped .claude/rules/ guardrail to prevent skill duplication
- **added** — PR-overlap guideline to prevent duplicate skills
- **changed** — Validator and CI upgraded to enforce naming, description triggers, and command-description parity
- **added** — git-workflow-and-versioning skill now includes release and versioning guidance covering semver, tags, and changelog
- **changed** — spec-driven-development skill now delegates task mechanics to planning-and-task-breakdown
- **added** — planning skill now documents the tasks/plan.md and tasks/todo.md output paths
- **changed** — browser-testing skill defaults to an isolated profile
- **fixed** — debugging skill step range
- **changed** — Use repo-relative script paths instead of the old /mnt/skills/user/ form
- **fixed** — Gemini /ship agent path
- **fixed** — Explain the expected commands/ ignored plugin warning and clear the underlying lint without breaking Antigravity
- **changed** — Antigravity code-simplify now reads AGENTS.md
- **fixed** — Make helper scripts executable
- **fixed** — hooks.json path fallback for manual installs

Agent Skills 0.6.3 sharpens code review, adds two new reference checklists and an honest comparison doc, and introduces a set of guardrails that steer new-skill work away from duplication, plus a wave of community fixes and polish.

##### Highlights

- **Deeper code review.** `code-review-and-quality` gains structural-depth lenses (reduce-don't-relocate, a named Structural Remedies catalog, a file-size gate, and finding prioritization), and its severity labels now line up with the skill's own taxonomy. (#304, #302)
- **Two new reference checklists.** An observability checklist (on-call questions, RED/USE metrics, symptom-based alerting) and a project-wide Definition of Done. (#240, #317)
- **How it compares.** A new `docs/comparison.md` puts agent-skills side by side with Superpowers and Matt Pocock's skills, with a link to a controlled head-to-head. (#300)
- **Guardrails against duplicate skills.** A CONTRIBUTING pre-flight checklist, a path-scoped `.claude/rules/` guardrail, a PR-overlap guideline, and validator/CI upgrades that enforce naming, description triggers, and command-description parity. (#301, #313, #325, #323, #270, #255)

##### Skills, commands & references

- git-workflow-and-versioning: add release and versioning guidance (semver, tags, changelog). (#334, @HMAKT99)
- spec-driven-development now delegates task mechanics to planning-and-task-breakdown. (#303, @nucliweb)
- planning: document the `tasks/plan.md` and `tasks/todo.md` output paths. (#337, @hiyochi)
- browser-testing: default to an isolated profile. (#239, @federicobartoli)
- debugging: fix the step range. (#293, @shihyuho)

##### Fixes & polish

- Use repo-relative script paths (drop the old `/mnt/skills/user/` form). (#307, @creazyfrog)
- Fix the Gemini `/ship` agent path. (#306, @creazyfrog)
- Explain the expected "commands/ ignored" plugin warning, and clear the underlying lint without breaking Antigravity. (#305, @creazyfrog; #273, @CollabxConstruct)
- Antigravity code-simplify reads AGENTS.md. (#288, @Dashsoap)
- Make helper scripts executable. (#289, #276, @Dashsoap)
- hooks.json path fallback for manual installs. (#269, @worldfunction4)
- Move `agents/README.md` to `docs/agents.md` to fix a custom-agent frontmatter warning. (#260, @nucliweb)

##### Docs & CI

- Document the `/webperf` command and setup. (#247, @Bortlesboat; #268, @CooperSheroy)
- README and getting-started tidy: list orchestration-patterns, add code-simplify. (#290, #283, @Dashsoap)
- Standardize `actions/checkout` to v6. (#275, @Dashsoap)

##### Thanks

Big thanks to everyone who contributed this release: @nucliweb, @federicobartoli, @HMAKT99, @Dashsoap, @creazyfrog, @An-idd, @Swing-G, @hiyochi, @shihyuho, @Bortlesboat, @CooperSheroy, @CollabxConstruct, and @worldfunction4.

**Full Changelog**: https://github.com/addyosmani/agent-skills/compare/0.6.2...0.6.3

### 0.6.2 — v0.6.2

- Date: 2026-06-11
- Version: 0.6.2
- Original notes: https://github.com/addyosmani/agent-skills/releases/tag/0.6.2
- Permalink: https://whatsnew.fyi/product/agent-skills/releases/0.6.2

- **fixed** — Use relative path source in marketplace to bypass install bug
- **fixed** — Update marketplace.json to use explicit GitHub source format
- **fixed** — Correct chrome-devtools-mcp install config in browser-testing
- **added** — Add /build auto command for one-pass plan and implement
- **added** — Add web-performance-auditor persona and /webperf command
- **added** — Add observability-and-instrumentation skill
- **added** — Add native support for Antigravity CLI (agy)
- **changed** — Strengthen security skills with threat modeling, SSRF, supply chain, and AI/LLM coverage

##### What's Changed
* fix(marketplace): use relative path source to bypass install bug by @git-clone-abhinav in https://github.com/addyosmani/agent-skills/pull/163
* docs(copilot): fix agent file naming — use *.agent.md extension by @creazyfrog in https://github.com/addyosmani/agent-skills/pull/183
* docs: route all lifecycle skills from meta-skill by @superShen0916 in https://github.com/addyosmani/agent-skills/pull/186
* fix: update marketplace.json to use explicit GitHub source format by @addyosmani in https://github.com/addyosmani/agent-skills/pull/215
* Strengthen security skills: threat modeling, SSRF, supply chain & AI/LLM by @addyosmani in https://github.com/addyosmani/agent-skills/pull/219
* fix(browser-testing): correct chrome-devtools-mcp install config by @nucliweb in https://github.com/addyosmani/agent-skills/pull/221
* feat(build): add /build auto for a one-pass plan + implement by @addyosmani in https://github.com/addyosmani/agent-skills/pull/220
* feat(agents): add web-performance-auditor persona and /webperf command by @nucliweb in https://github.com/addyosmani/agent-skills/pull/222
* feat: add observability-and-instrumentation skill by @federicobartoli in https://github.com/addyosmani/agent-skills/pull/223
* feat: add native support for Antigravity CLI (agy) by @hk1997 in https://github.com/addyosmani/agent-skills/pull/227

##### New Contributors
* @git-clone-abhinav made their first contribution in https://github.com/addyosmani/agent-skills/pull/163
* @superShen0916 made their first contribution in https://github.com/addyosmani/agent-skills/pull/186
* @hk1997 made their first contribution in https://github.com/addyosmani/agent-skills/pull/227

**Full Changelog**: https://github.com/addyosmani/agent-skills/compare/0.6.1...0.6.2

### 0.6.1

- Date: 2026-05-23
- Version: 0.6.1
- Original notes: https://github.com/addyosmani/agent-skills/releases/tag/0.6.1
- Permalink: https://whatsnew.fyi/product/agent-skills/releases/0.6.1

- **fixed** — Add guidance to prevent redundant build verification commands
- **fixed** — Declare skills and agents paths in plugin.json
- **added** — Add doubt-driven-development skill
- **fixed** — Add explicit cross-skill paths in spec-driven-development
- **added** — Add interview-me skill during the Define phase
- **added** — Add CI skill validator
- **changed** — Add reason to low-confidence numbers in interview-me
- **fixed** — Drop pinning version field from plugin.json

##### What's Changed
* Fix: Add guidance to prevent redundant build verification commands by @sbusanelli in https://github.com/addyosmani/agent-skills/pull/70
* fix(plugin): declare skills and agents paths in plugin.json by @creazyfrog in https://github.com/addyosmani/agent-skills/pull/114
* docs: list using-agent-skills in README by @aqilaziz in https://github.com/addyosmani/agent-skills/pull/142
* test: add session-start JSON regression coverage by @Bortlesboat in https://github.com/addyosmani/agent-skills/pull/132
* Add doubt-driven-development skill by @federicobartoli in https://github.com/addyosmani/agent-skills/pull/139
* docs: clarify README skill count by @MiladZarour in https://github.com/addyosmani/agent-skills/pull/159
* fix(spec-driven-development): add explicit cross-skill paths by @245678000000 in https://github.com/addyosmani/agent-skills/pull/169
* docs(skills): tighten frontmatter for idea-refine and browser-testing-with-devtools by @spboyer in https://github.com/addyosmani/agent-skills/pull/174
* docs: clarify when skills should include scripts/ by @toby-bridges in https://github.com/addyosmani/agent-skills/pull/170
* fix(#75): Docs inconsistency: conflicting skill description and anatomy guidance by @toby-bridges in https://github.com/addyosmani/agent-skills/pull/167
* feat: add interview-me skill (during the Define phase) by @addyosmani in https://github.com/addyosmani/agent-skills/pull/164
* Add CI skill validator by @googlarz in https://github.com/addyosmani/agent-skills/pull/60
* feat(interview-me): add reason to low-confidence numbers by @danielart in https://github.com/addyosmani/agent-skills/pull/187
* fix(#145): drop pinning version field from plugin.json by @felixlogotel in https://github.com/addyosmani/agent-skills/pull/189

##### New Contributors
* @devmarkpro made their first contribution in https://github.com/addyosmani/agent-skills/pull/108
* @sbusanelli made their first contribution in https://github.com/addyosmani/agent-skills/pull/70
* @creazyfrog made their first contribution in https://github.com/addyosmani/agent-skills/pull/114
* @aqilaziz made their first contribution in https://github.com/addyosmani/agent-skills/pull/142
* @Bortlesboat made their first contribution in https://github.com/addyosmani/agent-skills/pull/132
* @MiladZarour made their first contribution in https://github.com/addyosmani/agent-skills/pull/159
* @245678000000 made their first contribution in https://github.com/addyosmani/agent-skills/pull/169
* @spboyer made their first contribution in https://github.com/addyosmani/agent-skills/pull/174
* @toby-bridges made their first contribution in https://github.com/addyosmani/agent-skills/pull/170
* @googlarz made their first contribution in https://github.com/addyosmani/agent-skills/pull/60
* @danielart made their first contribution in https://github.com/addyosmani/agent-skills/pull/187
* @felixlogotel made their first contribution in https://github.com/addyosmani/agent-skills/pull/189

**Full Changelog**: https://github.com/addyosmani/agent-skills/compare/0.6.0...0.6.1

### 0.6.0

- Date: 2026-04-28
- Version: 0.6.0
- Original notes: https://github.com/addyosmani/agent-skills/releases/tag/0.6.0
- Permalink: https://whatsnew.fyi/product/agent-skills/releases/0.6.0

- **added** — Three composable orchestration layers (Personas, Skills, Slash commands) defined in AGENTS.md and references/orchestration-patterns.md
- **added** — Parallel fan-out orchestrator for /ship that runs code-reviewer, security-auditor, and test-engineer concurrently and merges their reports
- **added** — Composition block to each persona file documenting how it composes with skills
- **added** — Personas index at agents/README.md with a composition decision matrix
- **added** — Orchestration patterns catalog at references/orchestration-patterns.md
- **added** — Agent Teams worked example for competing-hypothesis debugging
- **added** — Documentation of Claude Code subagent and Agent Teams compatibility, including how skills, mcpServers, and permissionMode frontmatter are handled
- **added** — Seven slash commands under .gemini/commands/ (/spec, /planning, /build, /test, /review, /code-simplify, /ship) for Gemini CLI
- **added** — Gemini CLI setup documentation at docs/gemini-cli-setup.md
- **added** — Kiro IDE and CLI to README quick start with setup details and link formatting
- **added** — OpenCode symlink so OpenCode resolves skills correctly out of the box
- **added** — Opt-in citation cache for source-driven-development so framework-doc lookups do not repeat across sessions
- **changed** — /ship now replaces hand-wavy skip-fan-out rule with concrete thresholds (≤2 files, <50 lines, no auth/payments/data/config)
- **changed** — /planning command for Gemini CLI instead of /plan to avoid colliding with Gemini CLI internal command
- **changed** — Agent Teams system-prompt handling now appends instead of replaces
- **fixed** — Properly JSON-escape SKILL.md content via jq to fix invalid JSON when content contains quotes or newlines
- **fixed** — Gracefully fall back with an INFO-priority message when jq is missing on PATH instead of failing silently
- **fixed** — Button accessibility guidance in Frontend UI Engineering skill
- **fixed** — Custom button example in Frontend UI Engineering skill to align with native Space activation timing
- **fixed** — Custom button example in Frontend UI Engineering skill to prevent teaching a scrolling interaction bug
- **fixed** — Skip-to-content link must be visible on focus in Accessibility Checklist skill
- **changed** — Added autocomplete requirement for known fields in forms to Accessibility Checklist skill
- **changed** — Expanded INP coverage in Performance Checklist skill with concrete optimization techniques
- **changed** — Added fonts section and yieldToMain pattern to Performance Checklist skill

#### Agent Skills 0.6.0

This is an orchestration release. Personas, skills, and slash commands now compose as three explicit layers, and `/ship` runs three specialist personas in parallel against the current change before synthesizing a go/no-go decision. New tool integrations land for Gemini CLI, Kiro, and OpenCode, and `source-driven-development` gains an opt-in citation cache.

##### Orchestration

Three composable layers, defined in `AGENTS.md` and worked through in `references/orchestration-patterns.md`:

- **Personas** - roles with a perspective and an output format (the *who*)
- **Skills** - workflows with steps and exit criteria (the *how*)
- **Slash commands** - user-facing entry points (the *when*)

Composition rule: the user (or a slash command) is the orchestrator. Personas do not invoke other personas.

- Turned `/ship` into a parallel fan-out orchestrator that runs `code-reviewer`, `security-auditor`, and `test-engineer` concurrently and merges their reports
- Replaced `/ship`'s hand-wavy skip-fan-out rule with concrete thresholds (≤2 files, <50 lines, no auth/payments/data/config)
- Added a Composition block to each persona file documenting how it composes with skills
- Added a personas index (`agents/README.md`) with a composition decision matrix
- Added an orchestration patterns catalog (`references/orchestration-patterns.md`)
- Added an Agent Teams worked example for competing-hypothesis debugging
- Documented Claude Code subagent and Agent Teams compatibility, including how `skills`, `mcpServers`, and `permissionMode` frontmatter are handled (silently dropped when used as teammates)
- Corrected Agent Teams system-prompt handling — appended, not replaced
- Noted `/ship` picks up user-defined personas in `.claude/agents/` and `~/.claude/agents/` automatically (plugin scope is lowest priority)

##### New Tool Integrations

###### Gemini CLI 

- Added 7 slash commands under `.gemini/commands/` (`/spec`, `/planning`, `/build`, `/test`, `/review`, `/code-simplify`, `/ship`) mirroring the Claude Code set
- Used `/planning` instead of `/plan` to avoid colliding with a Gemini CLI internal command
- Documented the commands in `docs/gemini-cli-setup.md`

###### Kiro IDE & CLI 

- Added Kiro to the README quick start with setup details and link formatting

###### OpenCode

- Added a symlink so OpenCode resolves skills correctly out of the box

##### Hooks

###### Source-Driven Development citation cache

- Opt-in citation cache so framework-doc lookups don't repeat across sessions

###### Session-start JSON robustness 

- Properly JSON-escape `SKILL.md` content via `jq` — fixes invalid JSON when content contains quotes or newlines
- Gracefully fall back with an INFO-priority message when `jq` is missing on `PATH` instead of failing silently

##### Skill Improvements

###### Frontend UI Engineering

- Fixed button accessibility guidance ([[#58](https://github.com/addyosmani/agent-skills/pull/58)](https://github.com/addyosmani/agent-skills/pull/58))
- Aligned the custom button example with native Space activation timing ([[#79](https://github.com/addyosmani/agent-skills/pull/79)](https://github.com/addyosmani/agent-skills/pull/79))
- Prevented the custom button example from teaching a scrolling interaction bug

###### Accessibility Checklist

- Skip-to-content link must be visible on focus ([[#54](https://github.com/addyosmani/agent-skills/pull/54)](https://github.com/addyosmani/agent-skills/pull/54))
- Added `autocomplete` requirement for known fields in forms ([[#55](https://github.com/addyosmani/agent-skills/pull/55)](https://github.com/addyosmani/agent-skills/pull/55))

###### Performance Checklist

- Expanded INP coverage with concrete optimization techniques ([[#84](https://github.com/addyosmani/agent-skills/pull/84)](https://github.com/addyosmani/agent-skills/pull/84))
- Added a fonts section and the `yieldToMain` pattern ([[#63](https://github.com

_[Truncated at 4000 characters — full notes: https://github.com/addyosmani/agent-skills/releases/tag/0.6.0]_

### 0.5.0 — Agent Skills 0.5.0

- Date: 2026-04-10
- Version: 0.5.0
- Original notes: https://github.com/addyosmani/agent-skills/releases/tag/0.5.0
- Permalink: https://whatsnew.fyi/product/agent-skills/releases/0.5.0

- **added** — Source-Driven Development skill that grounds framework-specific implementation decisions in official documentation, with stack detection, citation format, and optional documentation cache
- **changed** — Performance Optimization skill now distinguishes synthetic and RUM measurements with guidance on when each applies
- **changed** — Expanded TTFB diagnosis into a decision tree covering DNS, TCP/TLS, and server processing with 800ms threshold aligned to web.dev
- **fixed** — Image optimization examples now use aspect-ratio, fetchpriority="high", and explicit width/height for hero/LCP images, and loading="lazy" + decoding="async" for below-the-fold images
- **removed** — Removed decoding="sync" from hero image examples to avoid blocking the main thread
- **added** — Art direction and resolution switching example with <picture>, AVIF → WebP → JPG cascade, and realistic sizes attributes
- **fixed** — Corrected date-fns tree-shaking example to use dynamic imports and route-level code splitting instead of relying on modern bundler handling
- **added** — Suspense wrapper to code-splitting examples with clarified ESM and sideEffects: false requirements
- **changed** — Clarified spec and task file lifecycle in Spec & Task Lifecycle documentation
- **changed** — Improved Gemini CLI configuration guide and fixed installation path for skills
- **changed** — Corrected GitHub Copilot skills setup instructions
- **changed** — Added OpenCode integration with agent-driven skill execution and clarified command support and agent-driven design
- **changed** — Added SSH troubleshooting hint to Marketplace install documentation
- **added** — Added See Also sections across SKILL.md files with cross-references to security, performance, accessibility resources, testing patterns, and pre-launch and review checklists

#### Release Notes

##### New Skills

- **Source-Driven Development** (#45) - New skill that grounds framework-specific implementation decisions in official documentation. Covers stack detection, citation format, handling conflicting sources, and an optional documentation cache. Framework-agnostic by design.

##### Skill Improvements

###### Performance Optimization (#40)
- Distinguished synthetic (Lighthouse/CI) vs RUM (web-vitals) measurement, with guidance on when each applies.
- Expanded TTFB diagnosis into a decision tree covering DNS, TCP/TLS, and server processing — mirrored in the checklist with TTFB "good" threshold aligned to web.dev (800ms).
- Fixed image optimization examples: hero/LCP images now use `aspect-ratio`, `fetchpriority="high"`, and explicit width/height; below-the-fold images use `loading="lazy"` + `decoding="async"`. Removed `decoding="sync"` from hero examples to avoid blocking the main thread.
- Added art direction + resolution switching example with `<picture>`, AVIF → WebP → JPG cascade, and realistic `sizes` attributes.
- Corrected the `date-fns` tree-shaking example — modern bundlers handle named imports; replaced with dynamic imports and route-level code splitting.
- Added Suspense wrapper to code-splitting examples; clarified ESM + `sideEffects: false` requirements.

###### Spec & Task Lifecycle (#42)
- Clarified spec and task file lifecycle (fixes #39).

##### Documentation & Setup Guides

- **Gemini CLI** (#43): Improved configuration guide and fixed installation path for skills.
- **GitHub Copilot**: Corrected skills setup instructions (#21).
- **OpenCode**: Added integration with agent-driven skill execution; clarified command support and agent-driven design.
- **Marketplace install** (#37): Added SSH troubleshooting hint.

##### Cross-Reference Additions (#34)

Added "See Also" sections across multiple SKILL.md files linking to:
- Security checklist references
- Performance resources
- Accessibility resources
- Testing patterns
- Pre-launch checklists (security, performance, accessibility)
- Review guidance (security and performance review checklists)

##### Contributors

@federicobartoli, @nucliweb, @zerone0x, @bonigarcia, @faisalbasra, @dj2313, @cseas