What’s New

agent-skills 0.6.0

0.6.0
Added
  • Three composable orchestration layers (Personas, Skills, Slash commands) defined in AGENTS.md and references/orchestration-patterns.md
  • Parallel fan-out orchestrator for /ship that runs code-reviewer, security-auditor, and test-engineer concurrently and merges their reports
  • Composition block to each persona file documenting how it composes with skills
  • Personas index at agents/README.md with a composition decision matrix
  • Orchestration patterns catalog at references/orchestration-patterns.md
  • Agent Teams worked example for competing-hypothesis debugging
  • Documentation of Claude Code subagent and Agent Teams compatibility, including how skills, mcpServers, and permissionMode frontmatter are handled
  • Seven slash commands under .gemini/commands/ (/spec, /planning, /build, /test, /review, /code-simplify, /ship) for Gemini CLI
  • Gemini CLI setup documentation at docs/gemini-cli-setup.md
  • Kiro IDE and CLI to README quick start with setup details and link formatting
  • OpenCode symlink so OpenCode resolves skills correctly out of the box
  • 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)
  • /planning command for Gemini CLI instead of /plan to avoid colliding with Gemini CLI internal command
  • Agent Teams system-prompt handling now appends instead of replaces
  • Added autocomplete requirement for known fields in forms to Accessibility Checklist skill
  • Expanded INP coverage in Performance Checklist skill with concrete optimization techniques
  • Added fonts section and yieldToMain pattern to Performance Checklist skill
Fixed
  • Properly JSON-escape SKILL.md content via jq to fix 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
  • Button accessibility guidance in Frontend UI Engineering skill
  • Custom button example in Frontend UI Engineering skill to align with native Space activation timing
  • Custom button example in Frontend UI Engineering skill to prevent teaching a scrolling interaction bug
  • Skip-to-content link must be visible on focus in Accessibility 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
Accessibility Checklist
Performance Checklist
Skill Contribution Guidance
  • Aligned skill-contribution guidance across CLAUDE.md, AGENTS.md, docs/skill-anatomy.md, and the README — preserved third-person description guidance and corrected README formatting
Contributors

Thanks to everyone who landed changes in this release:

Full Changelog: https://github.com/addyosmani/agent-skills/compare/0.5.0...0.6.0

View original