Auto-add .devkit/ to .gitignore on init

.github/workflows/release.yml

@@ -21,30 +21,28 @@ jobs:
       - name: Determine version
         id: version
         run: |
-          MANIFEST_VERSION=$(jq -r '.version' manifest.json)
           PLUGIN_VERSION=$(jq -r '.version' .claude-plugin/plugin.json)
           LATEST_TAG=$(git describe --tags --abbrev=0 2>/dev/null | sed 's/^v//' || echo "0.0.0")
 
-          echo "manifest=$MANIFEST_VERSION plugin=$PLUGIN_VERSION latest_tag=$LATEST_TAG"
+          echo "plugin=$PLUGIN_VERSION latest_tag=$LATEST_TAG"
 
-          # If manifest version is ahead of the latest tag, use it (manual bump)
-          if [ "$MANIFEST_VERSION" != "$LATEST_TAG" ] && [ "$MANIFEST_VERSION" != "$PLUGIN_VERSION" ] || [ "$MANIFEST_VERSION" != "$LATEST_TAG" ]; then
-            # Check if manifest version is actually newer
-            MANIFEST_MAJOR=$(echo "$MANIFEST_VERSION" | cut -d. -f1)
-            MANIFEST_MINOR=$(echo "$MANIFEST_VERSION" | cut -d. -f2)
-            MANIFEST_PATCH=$(echo "$MANIFEST_VERSION" | cut -d. -f3)
+          # If plugin.json version is ahead of the latest tag, use it (manual bump)
+          if [ "$PLUGIN_VERSION" != "$LATEST_TAG" ]; then
+            P_MAJOR=$(echo "$PLUGIN_VERSION" | cut -d. -f1)
+            P_MINOR=$(echo "$PLUGIN_VERSION" | cut -d. -f2)
+            P_PATCH=$(echo "$PLUGIN_VERSION" | cut -d. -f3)
             TAG_MAJOR=$(echo "$LATEST_TAG" | cut -d. -f1)
             TAG_MINOR=$(echo "$LATEST_TAG" | cut -d. -f2)
             TAG_PATCH=$(echo "$LATEST_TAG" | cut -d. -f3)
 
-            if [ "$MANIFEST_MAJOR" -gt "$TAG_MAJOR" ] 2>/dev/null || \
-               ([ "$MANIFEST_MAJOR" -eq "$TAG_MAJOR" ] && [ "$MANIFEST_MINOR" -gt "$TAG_MINOR" ]) 2>/dev/null || \
-               ([ "$MANIFEST_MAJOR" -eq "$TAG_MAJOR" ] && [ "$MANIFEST_MINOR" -eq "$TAG_MINOR" ] && [ "$MANIFEST_PATCH" -gt "$TAG_PATCH" ]) 2>/dev/null; then
-              echo "Manual version bump detected: $LATEST_TAG → $MANIFEST_VERSION"
-              echo "version=$MANIFEST_VERSION" >> "$GITHUB_OUTPUT"
+            if [ "$P_MAJOR" -gt "$TAG_MAJOR" ] 2>/dev/null || \
+               ([ "$P_MAJOR" -eq "$TAG_MAJOR" ] && [ "$P_MINOR" -gt "$TAG_MINOR" ]) 2>/dev/null || \
+               ([ "$P_MAJOR" -eq "$TAG_MAJOR" ] && [ "$P_MINOR" -eq "$TAG_MINOR" ] && [ "$P_PATCH" -gt "$TAG_PATCH" ]) 2>/dev/null; then
+              echo "Manual version bump detected: $LATEST_TAG → $PLUGIN_VERSION"
+              echo "version=$PLUGIN_VERSION" >> "$GITHUB_OUTPUT"
               echo "bumped=manual" >> "$GITHUB_OUTPUT"
             else
-              echo "Manifest version $MANIFEST_VERSION is not ahead of tag $LATEST_TAG — auto-bumping patch"
+              echo "plugin.json version $PLUGIN_VERSION is not ahead of tag $LATEST_TAG — auto-bumping patch"
               echo "bumped=auto" >> "$GITHUB_OUTPUT"
             fi
           else
@@ -67,14 +65,13 @@ jobs:
         run: |
           VERSION="${{ steps.version.outputs.version }}"
           jq --arg v "$VERSION" '.version = $v' .claude-plugin/plugin.json > tmp.json && mv tmp.json .claude-plugin/plugin.json
-          jq --arg v "$VERSION" '.version = $v' manifest.json > tmp.json && mv tmp.json manifest.json
 
       - name: Commit version bump
         run: |
           VERSION="${{ steps.version.outputs.version }}"
           git config user.name "github-actions[bot]"
           git config user.email "github-actions[bot]@users.noreply.github.com"
-          git add .claude-plugin/plugin.json manifest.json
+          git add .claude-plugin/plugin.json
           # Only commit if there are changes
           if git diff --cached --quiet; then
             echo "Version files already at $VERSION — no commit needed"

CONTRIBUTING.md

@@ -4,39 +4,39 @@
 
 Slash commands appear in tab-completion and run step-by-step workflows.
 
-1. Create `skills/my-command.md` with YAML frontmatter:
+1. Create `commands/my-command.md` with YAML frontmatter:
    ```markdown
    ---
-   name: devkit:my-command
    description: What this command does.
    ---
    # Command Title
    Step-by-step workflow with numbered steps.
    ```
-2. Add `"skills/my-command.md"` to the `"commands"` array in `manifest.json`
-3. Include Budget & Early Exit section if the command loops
-4. Include `[PARALLEL]` markers if steps run concurrently
+2. Include Budget & Early Exit section if the command loops
+3. Include `[PARALLEL]` markers if steps run concurrently
+
+The command name is derived from the filename: `commands/my-command.md` becomes `/devkit:my-command`.
 
 ## Adding a Context-Activated Skill
 
 Skills activate automatically based on natural language — no slash command needed.
 
-1. Create `skills/my-skill.md` with YAML frontmatter:
+1. Create `skills/my-skill/SKILL.md` with YAML frontmatter:
    ```markdown
    ---
-   name: devkit:my-skill
+   name: my-skill
    description: Triggers on "natural language pattern".
    ---
    # Skill Title
    Guidelines or workflow (keep under 100 lines).
    ```
-2. Add `"skills/my-skill.md"` to the `"skills"` array in `manifest.json`
+
+The skill will be auto-discovered as `devkit:my-skill`.
 
 ## Adding an Agent
 
-1. Create `agents/my-agent.md` with YAML frontmatter specifying model, tools, isolation, and maxTurns
-2. Add `"agents/my-agent.md"` to `manifest.json`
-3. Scope tools to only what the agent needs
+1. Create `agents/my-agent.md` with YAML frontmatter specifying name, description, model, effort, maxTurns, and disallowedTools
+2. Scope tools to only what the agent needs
 
 ## Adding a Workflow
 

README.md

@@ -285,11 +285,11 @@ None yet — `presets/` is reserved for future use.
 
 ```
 devkit/
-├── manifest.json            # Plugin manifest
+├── .claude-plugin/
+│   └── plugin.json          # Plugin metadata (name, version, author)
 ├── ROADMAP.md               # Implemented features and future plans
 ├── PREFERENCES.md           # Agent behavior guidelines
-├── skills/                  # All skill files (commands + skills)
-│   │                        # — 20 slash commands (tab-completable) —
+├── commands/                # 20 slash commands (tab-completable)
 │   ├── tri-*.md             # Multi-agent dispatch (5)
 │   ├── self-*.md            # Self-improvement loops (5)
 │   ├── pr-ready.md          # PR preparation pipeline
@@ -301,22 +301,22 @@ devkit/
 │   ├── workflow.md          # YAML workflow runner
 │   ├── audit.md             # Project health audit
 │   ├── repo-map.md          # AST-based symbol index
-│   ├── status.md            # Health check
-│   │                        # — 14 context-activated skills —
-│   ├── executing.md         # Principle: methodical execution
-│   ├── clean-code.md        # Principle: readability
-│   ├── dry.md               # Principle: don't repeat yourself
-│   ├── yagni.md             # Principle: no speculative features
-│   ├── dont-reinvent.md     # Principle: use existing solutions
-│   ├── stuck.md             # Principle: loop recovery
-│   ├── creating-workflows.md # Tool: YAML workflow authoring
-│   ├── gcli.md              # Tool: Google Workspace CLI
-│   ├── changelog.md         # Auto: "generate a changelog"
-│   ├── doc-gen.md           # Auto: "document this module"
-│   ├── test-gen.md          # Auto: "write tests for X"
-│   ├── onboard.md           # Auto: "explain this codebase"
-│   ├── research.md          # Auto: "research X"
-│   └── scrape.md            # Auto: "scrape this URL"
+│   └── status.md            # Health check
+├── skills/                  # 14 context-activated skills
+│   ├── executing/SKILL.md   # Principle: methodical execution
+│   ├── clean-code/SKILL.md  # Principle: readability
+│   ├── dry/SKILL.md         # Principle: don't repeat yourself
+│   ├── yagni/SKILL.md       # Principle: no speculative features
+│   ├── dont-reinvent/SKILL.md # Principle: use existing solutions
+│   ├── stuck/SKILL.md       # Principle: loop recovery
+│   ├── creating-workflows/SKILL.md # Tool: YAML workflow authoring
+│   ├── gcli/SKILL.md        # Tool: Google Workspace CLI
+│   ├── changelog/SKILL.md   # Auto: "generate a changelog"
+│   ├── doc-gen/SKILL.md     # Auto: "document this module"
+│   ├── test-gen/SKILL.md    # Auto: "write tests for X"
+│   ├── onboard/SKILL.md     # Auto: "explain this codebase"
+│   ├── research/SKILL.md    # Auto: "research X"
+│   └── scrape/SKILL.md      # Auto: "scrape this URL"
 ├── agents/                  # 6 agents
 │   ├── reviewer.md          # Opus, worktree isolation
 │   ├── researcher.md        # Sonnet, worktree isolation

skills/audit.md → commands/audit.md

@@ -1,5 +1,4 @@
 ---
-name: devkit:audit
 description: Unified project health audit — dependencies, vulnerabilities, outdated packages, licenses, lint, and security in one report.
 ---
 

skills/bugfix.md → commands/bugfix.md

@@ -1,5 +1,4 @@
 ---
-name: devkit:bugfix
 description: Full lifecycle bug fix — reproduce, diagnose, fix, regression test, verify.
 ---
 

skills/decompose.md → commands/decompose.md

@@ -1,5 +1,4 @@
 ---
-name: devkit:decompose
 description: Decompose a high-level goal into a task DAG — break down, assign to agents, resolve dependencies, execute in order.
 ---
 

skills/feature.md → commands/feature.md

@@ -1,5 +1,4 @@
 ---
-name: devkit:feature
 description: Full lifecycle feature development — brainstorm, plan, implement, test, lint, review.
 ---
 

skills/pr-monitor.md → commands/pr-monitor.md

@@ -1,5 +1,4 @@
 ---
-name: devkit:pr-monitor
 description: Post-PR review monitor — watches CI, fetches reviewer comments, iteratively resolves them, and pushes fixes.
 ---
 

skills/pr-ready.md → commands/pr-ready.md

@@ -1,5 +1,4 @@
 ---
-name: devkit:pr-ready
 description: Full PR preparation pipeline — necessity check, DRY review, lint, test, security, changelog, and create PR.
 ---
 

skills/refactor.md → commands/refactor.md

@@ -1,5 +1,4 @@
 ---
-name: devkit:refactor
 description: Full lifecycle refactor — analyze code smells, plan transformations, restructure, verify nothing broke.
 ---
 

skills/repo-map.md → commands/repo-map.md

@@ -1,5 +1,4 @@
 ---
-name: devkit:repo-map
 description: Build an AST-based symbol index of the repository — exports, functions, classes, imports — cached for fast agent navigation.
 ---
 

skills/self-improve.md → commands/self-improve.md

@@ -1,5 +1,4 @@
 ---
-name: self:improve
 description: Self-recursive improvement loop — automated refactoring with test gate. Uses native improver agent in worktree isolation. Propose → measure → keep/discard → repeat.
 ---
 

skills/self-lint.md → commands/self-lint.md

@@ -1,5 +1,4 @@
 ---
-name: self:lint
 description: Self-improvement loop targeting lint and type errors. Iteratively fixes issues until zero remain or iterations exhausted.
 ---
 

skills/self-migrate.md → commands/self-migrate.md

@@ -1,5 +1,4 @@
 ---
-name: self:migrate
 description: Self-improvement loop for incremental codebase migrations. Iteratively migrates code with tests as the safety gate.
 ---
 

skills/self-perf.md → commands/self-perf.md

@@ -1,5 +1,4 @@
 ---
-name: self:perf
 description: Hypothesis-driven performance investigation — analyze, hypothesize, test one theory at a time, measure against baseline.
 ---
 

skills/self-test.md → commands/self-test.md

@@ -1,5 +1,4 @@
 ---
-name: self:test
 description: Self-improvement loop targeting test coverage. Iteratively generates and improves tests until a coverage target is met or iterations exhausted.
 ---
 

skills/status.md → commands/status.md

@@ -1,5 +1,4 @@
 ---
-name: devkit:status
 description: Check devkit health — which external CLIs are installed, which agents are available, and which commands are ready to use.
 ---
 

skills/tri-debug.md → commands/tri-debug.md

@@ -1,5 +1,4 @@
 ---
-name: tri:debug
 description: Multi-agent debugging — send a bug report to available agents (Claude + Codex + Gemini) via plugin or CLI, get independent root-cause hypotheses, and a consensus fix.
 ---
 

skills/tri-dispatch.md → commands/tri-dispatch.md

@@ -1,5 +1,4 @@
 ---
-name: tri:dispatch
 description: Dispatch a task to all three agents (Claude, Codex, Gemini) in parallel and compare results. Claude uses native background agent, others via plugin or CLI.
 ---
 

skills/tri-review.md → commands/tri-review.md

@@ -1,5 +1,4 @@
 ---
-name: tri:review
 description: Triple-agent PR/code review. Claude runs as native background agent (token-efficient), Codex and Gemini via plugin or CLI. Consolidates findings.
 ---
 

skills/tri-security.md → commands/tri-security.md

@@ -1,5 +1,4 @@
 ---
-name: tri:security
 description: Multi-agent security audit — independent security reviews from available agents, consolidated with severity-ranked findings.
 ---
 

skills/tri-test-gen.md → commands/tri-test-gen.md

@@ -1,5 +1,4 @@
 ---
-name: tri:test-gen
 description: Multi-agent test generation — each available agent generates tests independently, then merge for maximum coverage.
 ---
 

skills/workflow.md → commands/workflow.md

@@ -1,5 +1,4 @@
 ---
-name: devkit:workflow
 description: Run a user-defined YAML workflow. Multi-step pipelines with loops, approval gates, and branching.
 ---
 
@@ -19,7 +18,6 @@ Execute a YAML-defined workflow from the `workflows/` directory.
 Read `workflows/{name}.yml` and parse:
 
 ```yaml
-name: workflow-name
 description: What this workflow does
 
 steps:

skills/changelog.md → skills/changelog/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: devkit:changelog
+name: changelog
 description: Generate a structured changelog from git history — use when asked to create a changelog, release notes, or summarize what changed between versions/tags/branches.
 ---
 

skills/clean-code.md → skills/clean-code/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: devkit:clean-code
+name: clean-code
 description: Clean code principles — meaningful names, small functions, single responsibility, stepdown rule, flat nesting.
 ---
 

skills/creating-workflows.md → skills/creating-workflows/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: devkit:creating-workflows
+name: creating-workflows
 description: How to create devkit workflow YAML files — schema reference, step types, variable interpolation, and examples.
 ---
 

skills/doc-gen.md → skills/doc-gen/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: devkit:doc-gen
+name: doc-gen
 description: Generate documentation for code — use when asked to document a module, generate API docs, create a README for code, or write reference documentation.
 ---
 

skills/dont-reinvent.md → skills/dont-reinvent/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: devkit:dont-reinvent
+name: dont-reinvent
 description: Don't reinvent the wheel — use existing libraries, tools, and stdlib before building custom solutions. Every custom solution is maintenance burden.
 ---
 

skills/dry.md → skills/dry/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: devkit:dry
+name: dry
 description: Don't Repeat Yourself — Rule of Three, when duplication is fine, extracting the right abstraction.
 ---
 

skills/executing.md → skills/executing/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: devkit:executing
+name: executing
 description: Execute implementation plans — work through steps methodically, verify each one, keep changes small and reviewable.
 ---
 

skills/gcli.md → skills/gcli/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: devkit:gcli
+name: gcli
 description: Google Workspace CLI (Gmail, Calendar, Drive) via gcli — use --for-ai flag for token-efficient structured output.
 ---