feat: add dev-commit skill

README.md

@@ -171,12 +171,13 @@ Agent:  Audits the diff against the design doc — scope creep,
 
 ## What changes in agent behavior
 
-The flow above is powered by eight built-in skills, each addressing a failure mode developers see in real AI coding sessions:
+The flow above is powered by nine built-in skills, each addressing a failure mode developers see in real AI coding sessions:
 
 | Failure mode | AI DevKit behavior |
 |--------------|--------------------|
 | Agent starts coding too early | `dev-lifecycle` forces requirements, design, planning, implementation, tests, and review |
 | Agent says "done" without proof | `verify` blocks completion claims without fresh test/build evidence |
+| Agent commits unrelated local changes | `dev-commit` checks diffs, stages explicit paths, validates, and reports the SHA/status |
 | Agent forgets project decisions | `memory` gives it a local, searchable knowledge base across sessions and projects |
 | New behavior ships without tests | `tdd` pushes test-first implementation |
 | Debugging becomes guess-and-patch | `structured-debug` makes it reproduce, hypothesize, fix, and verify |

packages/cli/src/__tests__/commands/skill.test.ts

@@ -91,6 +91,10 @@ describe('skill command', () => {
       global: undefined,
       environments: undefined,
     });
+    expect(mockAddSkill).toHaveBeenCalledWith('codeaholicguy/ai-devkit', 'dev-commit', {
+      global: undefined,
+      environments: undefined,
+    });
     expect(mockAddSkill).toHaveBeenCalledWith('codeaholicguy/ai-devkit', 'dev-worktree', {
       global: undefined,
       environments: undefined,

packages/cli/src/constants.ts

@@ -13,6 +13,7 @@ export const BUILTIN_SKILL_REGISTRY = 'codeaholicguy/ai-devkit';
 export const BUILTIN_SKILL_NAMES = [
   'agent-communication',
   'agent-management',
+  'dev-commit',
   'dev-lifecycle',
   'dev-worktree',
   'dev-requirements',

skills/dev-commit/SKILL.md

@@ -0,0 +1,39 @@
+---
+name: dev-commit
+description: AI DevKit · Safe git commit workflow for AI coding agents. Use when the user asks to commit, prepare a commit, stage changes, create a PR-ready checkpoint, or finish work with a conventional commit while avoiding unrelated user changes.
+---
+
+# Dev Commit
+
+Make one intentional, verified commit without sweeping in unrelated work.
+
+## Commit Contract
+
+1. Check repository state with `git status --short --branch`, `git diff --stat`, and `git diff`.
+2. Identify the files that belong to the requested change. Treat pre-existing user edits, local config, generated artifacts, dependency caches, build outputs, and unrelated formatting churn as out of scope unless the user explicitly includes them.
+3. Run appropriate validation before committing. Prefer the repo's targeted tests, lint, typecheck, build, or documented verification commands. Record skipped validation with the reason.
+4. Stage only intended paths. Prefer explicit pathspecs such as `git add path/to/file` over `git add .`.
+5. Re-check with `git diff --cached --stat`, `git diff --cached`, and `git status --short`.
+6. Write a concise conventional commit message: `<type>(optional-scope): <summary>`.
+7. Commit, then report the commit SHA, final status, validation commands, and any unstaged/untracked files left behind.
+
+## Guardrails
+
+- Do not commit secrets, credentials, `.env` files, local machine config, caches, coverage, logs, screenshots, or generated files unless the change explicitly requires them.
+- Do not stage another person's unrelated edits. If intended and unrelated changes are mixed in one file, use an interactive or patch-based staging flow and review the staged diff carefully.
+- Do not amend, rebase, force-push, reset, or delete branches unless the user explicitly asks for that operation.
+- If validation fails, stop before committing unless the user explicitly instructs you to commit with failing validation. Report the failing command and key output.
+- If the repo has commit hooks, let them run. If a hook changes files, inspect and stage only intended hook outputs before retrying.
+
+## Message Style
+
+Use semantic or conventional commit types that match the change:
+
+- `feat`: user-facing feature or capability
+- `fix`: bug fix
+- `docs`: documentation-only change
+- `test`: test-only change
+- `refactor`: behavior-preserving code restructuring
+- `chore`: maintenance, build, tooling, metadata, or generated index updates
+
+Keep the subject under about 72 characters when practical, imperative, and specific. Add a body only when it explains non-obvious validation, risk, migration, or follow-up context.

skills/dev-commit/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "Dev Commit"
+  short_description: "AI DevKit · Commit only intended, verified changes"
+  default_prompt: "Use $dev-commit to review, stage, commit, and report this work safely."

skills/index.json

@@ -710,6 +710,13 @@
       "description": "AI DevKit · Update CHANGELOG.md Unreleased items from git commits since the latest release. Use when users ask to update changelog/release notes from recent commits, with one concise line per commit and commit/PR links.",
       "lastIndexed": 1782001853281
     },
+    {
+      "name": "dev-commit",
+      "registry": "codeaholicguy/ai-devkit",
+      "path": "skills/dev-commit",
+      "description": "AI DevKit · Safe git commit workflow for AI coding agents. Use when the user asks to commit, prepare a commit, stage changes, create a PR-ready checkpoint, or finish work with a conventional commit while avoiding unrelated user changes.",
+      "lastIndexed": 1782001853290
+    },
     {
       "name": "dev-design",
       "registry": "codeaholicguy/ai-devkit",

web/content/docs/1-getting-started.md

@@ -113,6 +113,7 @@ Terminal commands still start with `ai-devkit`; skills are used by the agent ins
 |---------|---------|
 | `dev-lifecycle` | Orchestrate worktree setup, requirements, design, planning, implementation, testing, and review |
 | `dev-worktree`, `dev-requirements`, `dev-design`, `dev-planning`, `dev-implementation`, `dev-testing`, `dev-review` | Run focused lifecycle phases directly |
+| `dev-commit` | Commit only intended, verified changes with a conventional message |
 | `tdd` | Add or change behavior test-first |
 | `verify` | Require fresh command output before completion claims |
 | `structured-debug` | Debug issues with reproduction, hypotheses, fixes, and verification |

web/content/docs/7-skills.md

@@ -27,6 +27,7 @@ AI DevKit ships with a core set of skills in its default registry:
 |---|---|
 | `agent-orchestration` | Coordinate running AI agents and manage multi-agent workflows |
 | `document-code` | Document code entry points with structured analysis and dependency mapping |
+| `dev-commit` | Commit only intended, verified changes with a conventional message |
 | `dev-lifecycle` | Orchestrate the SDLC workflow and route to phase skills |
 | `dev-worktree`, `dev-requirements`, `dev-design`, `dev-planning`, `dev-implementation`, `dev-testing`, `dev-review` | Run focused SDLC phases directly |
 | `structured-debug` | Follow a disciplined debugging and RCA process before implementing fixes |

web/lib/skills/built-in.ts

@@ -177,6 +177,20 @@ export const builtInSkills: BuiltInSkill[] = [
     ],
     relatedAgents: ["Claude Code", "Codex"],
   },
+  {
+    name: "dev-commit",
+    title: "Dev Commit",
+    category: "Workflow",
+    summary: "Create safe, verified commits from only the intended changes.",
+    description:
+      "Use dev-commit when work is ready to save as a git commit. It guides agents through status and diff inspection, validation, explicit staging, conventional commit messages, and final SHA/status reporting without including unrelated local changes.",
+    useCases: [
+      "Commit finished work without sweeping in unrelated files",
+      "Stage only the intended paths after reviewing diffs",
+      "Record validation evidence and a conventional commit message",
+    ],
+    relatedAgents: ["Claude Code", "Codex", "Cursor", "opencode"],
+  },
   {
     name: "dev-worktree",
     title: "Dev Worktree",

web/public/llms.txt

@@ -30,6 +30,7 @@ npx ai-devkit@latest init
 ## Key Skills
 
 - `dev-lifecycle` - Start a new feature, validate requirements and design, execute plans, and run pre-commit reviews
+- `dev-commit` - Commit only intended, verified changes with a conventional message
 - `tdd` - Add test coverage with a test-first workflow
 - `structured-debug` - Debug systematically with reproduction, hypotheses, fixes, and verification
 - `memory` - Store important guidelines and patterns in memory