ai-ide-audit
$
npx mdskill add arcasilesgroup/ai-engineering/ai-ide-audit``` /ai-ide-audit all # audit all platforms /ai-ide-audit github-copilot # Copilot only /ai-ide-audit claude-code # Claude Code only /ai-ide-audit antigravity # Antigravity app + agy CLI /ai-ide-audit all --fix # audit + auto-fix P0 issues ```
SKILL.md
.github/skills/ai-ide-auditView on GitHub ↗
--- name: ai-ide-audit description: Audits an IDE end-to-end (instruction surface, hooks, skills, agents, installer wiring) using strict file-evidence — never assumptions. Trigger for 'audit IDE support', 'is Copilot wired up correctly', 'check Claude Code integration', 'are there orphaned hooks', 'verify IDE setup'. Accepts Claude Code, GitHub Copilot, Codex, Antigravity, or all. Not for code quality; use /ai-verify instead. Not for security scanning; use /ai-security instead. effort: high argument-hint: "claude-code|github-copilot|codex|antigravity|all [--fix]" mode: agent tags: [audit, ide, copilot, claude-code, governance] model_tier: opus mirror_family: copilot-skills generated_by: ai-eng sync canonical_source: .claude/skills/ai-ide-audit/SKILL.md edit_policy: generated-do-not-edit --- # IDE Support Audit ## Quick start ``` /ai-ide-audit all # audit all platforms /ai-ide-audit github-copilot # Copilot only /ai-ide-audit claude-code # Claude Code only /ai-ide-audit antigravity # Antigravity app + agy CLI /ai-ide-audit all --fix # audit + auto-fix P0 issues ``` ## Workflow Strict evidence-based audit of IDE support in ai-engineering. No assumptions — every claim cites a file path. Output is always the structured audit document, no matter how many IDEs are requested. 1. **Write the report skeleton first** from `references/report-template.md` BEFORE collecting evidence. 2. **Dispatch a single `Explore` subagent** to read instruction surfaces, hook configs, mirror dirs, and `manifest.yml` counts. 3. **Classify each capability per platform** (SUPPORTED / PARTIAL / UNSUPPORTED) using the capability matrix. 4. **Run spec-107 advisory checks** (advisory-only per NG-11): - **Check 6** — agent naming consistency cross-IDE: every agent file's frontmatter `name:` must equal its slug. - **Check 8** — generic instruction-file count scan: walk every CLAUDE.md / AGENTS.md / copilot-instructions.md and validate `## Skills (N)` + `## Agents (N)` headers vs canonical counts. 5. **With `--fix`**, auto-remediate P0 issues only; re-run mirror sync; verify tests still pass. > Detail: see [evidence collection (instruction surfaces, hooks, mirrors, sync script)](references/evidence-collection.md), [capability matrix + advisory checks + auto-fix policy](references/capability-matrix.md), [audit document skeleton](references/report-template.md). ## When to Use - Verifying an IDE is genuinely wired end-to-end (instruction surface → hooks → skills → agents → installer). - After any change to `scripts/sync_command_mirrors.py`, `src/ai_engineering/installer/templates.py`, or hook files. - When skill or agent counts look wrong across IDEs. - When a hook exists in `scripts/hooks/` but isn't firing. - NOT for general code quality — use `/ai-verify`. NOT for security scanning — use `/ai-security`. Step 0 (load contexts): read `.ai-engineering/manifest.yml` `providers.stacks`; load `.ai-engineering/overrides/<stack>/conventions.md` for each stack and `.ai-engineering/overrides/_shared/conventions.md`; load `.ai-engineering/team/*.md` for team conventions. ## Common Mistakes - Filling the matrix before collecting evidence (write the skeleton first). - Marking SUPPORTED on partial wiring just because a file exists. - Auto-fixing P1/P2 issues with `--fix` (it only touches P0). - Skipping the post-fix unit test run. ## Examples ### Example 1 — full IDE sweep before a release User: "audit every IDE we ship support for, then auto-fix the P0 issues" ``` /ai-ide-audit all --fix ``` Walks every IDE surface, scores SUPPORTED / PARTIAL / UNSUPPORTED per capability, fixes orphaned hooks and stale counts, re-runs mirror sync, re-runs unit tests. ### Example 2 — quick Copilot health check after sync User: "did the sync_command_mirrors run leave Copilot in a good state?" ``` /ai-ide-audit github-copilot ``` Verifies `.github/copilot-instructions.md`, `.github/hooks/hooks.json`, `.github/skills/`, `.github/agents/` against the canonical formula and flags any drift. ## Integration Triggered after: installer changes, `sync_command_mirrors.py` runs, new hooks added. Calls: `python scripts/sync_command_mirrors.py` (with `--fix`). Feeds into: `/ai-governance` (risk acceptance for UNSUPPORTED gaps). See also: `/ai-verify`, `/ai-security`. $ARGUMENTS
More from arcasilesgroup/ai-engineering
- ai-adviseProactive governance advisor — checks standards, decisions, and quality trends during development. Always advisory, NEVER blocks. Three modes: `advise` (post-edit), `gate` (pre-dispatch), `drift` (on-demand decision audit). Trigger for 'governance check', 'advise on this change', 'check for drift', 'is this aligned with active decisions', 'shift-left advisory'. Not for blocking gates — use /ai-verify. Not for narrative code review — use /ai-review.
- ai-analyze-permissionsUse when Claude Code keeps asking to approve commands you have already approved, when settings.local.json has grown large, or when you want to consolidate permission grants into wildcard patterns. Trigger for 'too many permission prompts', 'clean up permissions', 'audit my settings', 'consolidate allow rules'. Claude Code only — not available in GitHub Copilot, Antigravity, or Codex.
- ai-animationDesigns motion, transitions, and micro-interactions for UI components: spring animations, gestures, easing, staggers — taste-driven detail compounding. Trigger for 'animate this', 'add transitions', 'micro-interactions for', 'gesture design', 'swipe to dismiss', 'easing for this', 'stagger the'. Not for design systems; use /ai-design instead. Not for visual art; use /ai-visual instead. Not for testing animation code; use /ai-test instead.
- ai-autopilotDelivers large multi-concern specs and backlog runs autonomously: decomposes specs into sub-specs (or normalizes work items into a backlog DAG), deep-plans with parallel agents, builds a dependency DAG, implements in waves, runs a single final quality loop with one bounded quality-remediation pass (verify+guard+review on full changeset), delivers via PR. Trigger for 'implement spec-NNN end to end', 'autopilot this', 'autonomous delivery', 'decompose and ship', 'run the backlog', 'execute these GitHub issues', 'process the sprint backlog'. Invocation is the approval gate. Not for small or single-concern tasks; use /ai-build instead. Not for ambiguous requirements; use /ai-brainstorm first.
- ai-boardOperates the project board (GitHub Projects v2 or Azure DevOps): discovers configuration after install (fields, state mappings, process templates) and syncs work-item state at lifecycle transitions. Trigger for 'set up the board', 'configure our ADO board', 'discover board fields', 'move this issue to in-review', 'update the board', 'mark as in progress', 'sync the work item state'. Two subcommands: `discover` (post-install configuration write) and `sync` (lifecycle state transitions). Auto-invoked via `sync` by /ai-brainstorm, /ai-build, and /ai-pr; fail-open. Not for backlog execution; use /ai-autopilot --backlog instead.
- ai-brainstormForces rigorous design interrogation BEFORE any code: explores approaches, surfaces ambiguity, gathers evidence, produces an approved spec that becomes the contract for /ai-plan. Trigger for 'lets add X', 'how should we handle Y', 'whats the best approach', 'I am thinking about', 'what should we build for'. Not for existing approved specs; use /ai-plan instead. Not for execution; use /ai-build instead.
- ai-branch-cleanupCleans branches safely: switches to the default branch, prunes merged and squash-merged branches, syncs to remote, sweeps stale specs, rotates `.ai-engineering/runtime/` per retention policy. Trigger for 'tidy up', 'tidy branches', 'sync to main', 'delete old branches', 'start fresh', 'rotate runtime'. Auto-invoked by /ai-pr after merge. Not for committing changes; use /ai-commit instead. Not for code-level dead-code removal; use /ai-simplify instead.
- ai-buildCanonical implementation gateway: reads approved plan.md, resolves stack from manifest, deterministic-routes each task to its adapter, dispatches the build agent in an isolated worktree, runs TDD self-validation per task, then a single final quality loop with one bounded quality-remediation pass on the full changeset before /ai-pr. Trigger for 'go', 'start building', 'execute the plan', 'implement it', 'lets do this', 'build the plan', 'resume', 'continue'. Not without an approved plan; run /ai-plan first. Not for multi-concern specs needing decomposition; use /ai-autopilot instead. Not for a single function or subcomponent; use /ai-code.
- ai-codeWrites production code that satisfies stack-context standards on the first pass: interface-first design, backward-compatibility checks, lightweight self-review. Trigger for 'implement this', 'write the code for', 'add X to Y', 'build this function', 'make this work'. Not for tests; use /ai-test instead. Not for debugging; use /ai-debug instead. Not for refactoring; use /ai-simplify instead. Not for executing an approved plan end-to-end; use /ai-build (the gateway).
- ai-commitRuns the governed commit pipeline: auto-branches from protected, stages selectively, formats and lints, scans for secrets, gates docs, composes a conventional message, pushes. Trigger for 'commit my changes', 'save my work', 'push this to remote', 'stage these files', 'ship it'. Not for opening a PR; use /ai-pr instead. Not for branch hygiene; use /ai-branch-cleanup instead.