| name | maestro-overlay |
| disable-model-invocation | true |
| description | Create or edit command overlays from natural language, or auto-generate them from workflow deficiency signals |
| argument-hint | <intent> | --amend [--scan] [--dry-run] [-y] |
| allowed-tools | ["Bash","Glob","Grep","Read","Write","request_user_input"] |
| session-mode | none |
| version | 0.5.55 |
Turn instructions into command overlays — JSON patch files that augment `.claude/commands/*.md`
non-invasively, auto-applied by `maestro install`. Two modes:
- Default (intent) — turn a natural-language instruction into one overlay interactively.
--amend — signal-driven auto-generation: collect workflow deficiency signals from
multiple sources, diagnose which commands need amendment, batch-generate targeted overlays.
Both modes use the same overlay system (~/.maestro/overlays/*.json) — non-invasive, idempotent,
survives reinstall.
**Mode selection**: `--amend` (or any `--from-*` / `--scan` signal flag) → **Amend mode** (signal-driven auto-generation, jump to `` in execution). Otherwise → **Default mode** (natural-language intent, steps 1–5 below).
Overlay model:
- JSON file:
name, targets[] (command names), patches[]
- Patch:
section (XML tag), mode (append/prepend/replace/new-section), content
- Apply: hashed HTML-comment markers (idempotent, surgical removal)
Where overlays live
- User overlays:
~/.maestro/overlays/*.json — created by this skill
- Shared docs:
~/.maestro/overlays/docs/*.md — referenced via @~/.maestro/overlays/docs/*.md inside patch content
- Shipped examples:
~/.maestro/overlays/_shipped/ — read-only, do not edit
Management — listing and removing overlays is handled by maestro overlay list (ink TUI with interactive delete). This skill focuses solely on creation.
Available sections (for section: in patches): purpose, required_reading, deferred_reading, context, execution, completion, invariants, error_codes, success_criteria.
Amend mode signal sources (when --amend):
| Flag | Source | Collects |
|---|
--from-verify <dir> | verification.json | Workflow gaps from verify failures |
--from-review <dir> | review.json | Process deficiencies from code review |
--from-session <id> | Session artifacts | Problems during workflow execution |
--from-issues ISS-xxx,... | issues.jsonl | Issues tracing to command deficiency |
--scan | Auto-scan .workflow/ | Discover all workflow-related signals |
| (positional text) | User description | Direct observation |
Multiple combinable. --amend with no flags/description → interactive (scan + request_user_input).
Amend control: --dry-run (preview, don't install), -y (skip confirmations).
Amend output: ~/.maestro/overlays/amend-{slug}.json + optional ~/.maestro/overlays/docs/amend-{slug}.md.
Output boundary: ALL file writes MUST target ~/.maestro/overlays/ (overlay JSON + docs) only. Command file patching is handled by maestro overlay add — this skill NEVER modifies .claude/commands/*.md directly.
1. **Non-invasive** — overlays MUST use hashed HTML-comment markers for injection; NEVER edit command file content directly outside the overlay system
2. **Idempotent** — re-running `maestro overlay apply` with the same overlay JSON MUST produce no file changes
3. **Creation only** — this skill MUST only create overlays; listing and removal are handled by `maestro overlay list` (ink TUI)
4. **Pristine source preferred** — injection point analysis MUST read from `$PKG_ROOT/.claude/commands/` (untouched originals) first, fall back to `~/.claude/commands/` only if pristine unavailable
5. **User approval before write** — overlay JSON MUST be shown and approved via request_user_input before writing to disk; NEVER auto-install without confirmation
6. **Chain skip option mandatory** — if a skill chain is configured, the injected content MUST include a "Skip" option in request_user_input; NEVER force the user into a chain
Amend mode only (when --amend):
- Pristine source reads — signal diagnosis MUST read from
$PKG_ROOT/.claude/commands/ (untouched originals), not installed copies
- Code bugs excluded — signals classified as code bugs MUST be routed to
/maestro-companion or step plan (--gaps), NEVER patched via overlay
- Section existence verified — target section MUST be confirmed to exist in the pristine source before drafting a patch; missing sections trigger
new-section mode
Amend mode (--amend or any --from-* / --scan flag): skip steps 1–5 below and follow <amend_mode> at the end of this section instead. Default mode: continue with steps 1–5.
1. Parse user intent
Treat the argument as natural-language intent. If unclear, ask up to 2 questions with request_user_input: (a) which command(s) to target, (b) where in the command flow the injection should happen.
2. Identify targets, injection points, and visualize
For each likely target command, read the pristine source from $PKG_ROOT/.claude/commands/<name>.md (preferred — untouched by overlays) or fall back to ~/.claude/commands/<name>.md. Inspect the XML sections and pick the right one:
- New step after execution →
section: execution, mode: append
- Required reading →
section: required_reading, mode: append
- Preconditions / gating →
section: context, mode: append
- Output quality gate →
section: success_criteria, mode: append
If the user wants a whole new section, use mode: new-section with afterSection: execution (or whichever anchor makes sense).
Injection point preview — after selecting section + mode, render the target command's section map showing existing overlays and the new injection point:
=== maestro-next.md (1 overlay exists) ===
<purpose>
<required_reading>
<context>
<execution>
├─ [existing] cli-verify #1 "CLI Verification step"
>>> NEW: append here (your overlay)
<success_criteria>
Use request_user_input to confirm:
- "Confirm" — proceed with this injection point
- "Pick different section" — re-select section/mode
- "Cancel" — abort
2.5. Skill chain configuration
After confirming the injection point, ask whether this overlay should recommend another retained command upon completion. Emit its exact slash command after confirmation. team-* and maestro-odyssey are not valid handoff targets.
Use request_user_input:
- "No chain" — standard overlay, no skill handoff
- "Chain to skill" → ask for the target skill name (e.g., a step like
review, execute, test invoked via maestro run prepare --platform codex <step> + maestro run create <step> --session YYYYMMDD-<step>-{topic} --intent "{goal}")
- "Chain with alternatives" → ask for primary skill + 1-2 alternative skills
If chain is selected, record the skill name(s) for use in Step 3.
3. Draft the overlay JSON
Build a slug from the user's intent (kebab-case, lowercase). Write to ~/.maestro/overlays/<slug>.json:
{
"name": "<slug>",
"description": "<short summary of what and why>",
"targets": ["maestro-next"],
"priority": 50,
"enabled": true,
"patches": [
{
"section": "execution",
"mode": "append",
"content": "## CLI Verification (overlay)\n\nAfter execution, run:\n```\nccw cli -p \"PURPOSE: ...\" --mode analysis --rule analysis-review-code-quality\n```"
}
]
}
Content guidelines
- Lead the injected block with a heading that includes
(overlay) so readers see it's machine-injected
- Keep content concise — overlays should add a step, not rewrite the command
@~/.maestro/... references are encouraged for pointing at docs- Escape
\n in JSON strings; use a HEREDOC via Bash if content is long
Skill chain content — if a chain was configured in Step 2.5, append a Skill Handoff block at the end of the patch content. The handoff uses request_user_input so the user controls whether to proceed:
---
**Skill Handoff** (overlay)
After the above step completes, use request_user_input:
- "Proceed to review" — Hand off to step `review` (`maestro run prepare --platform codex review` + `maestro run create review --session YYYYMMDD-review-{topic} --intent "{goal}"`)
- "Skip" — Continue with current command flow
- "Alternative: execute" — Run step `execute` with built-in verification instead
On user selection:
- Proceed → run step `review` (`maestro run prepare --platform codex review` + `maestro run create review --session YYYYMMDD-review-{topic} --intent "{goal}"`)
- Alternative → run step `execute` (`maestro run prepare --platform codex execute` + `maestro run create execute --session YYYYMMDD-execute-{topic} --intent "{goal}"`)
- Skip → continue normally
Handoff rules:
- Always include a "Skip" option — the user can always decline the chain
- Use an exact slash command for confirmed retained-command handoffs
- Mark handoff heading with
(overlay) tag
- Support runtime variable placeholders:
{phase}, {description}, {session_id}
- Keep handoff block under 10 lines of markdown
3.5. Content approval
Display the full overlay JSON to the user. request_user_input:
- "Approve & install" — proceed to installation
- "Edit" — user provides corrections, re-draft
- "Cancel" — discard overlay, do not write
Only write the overlay JSON file to ~/.maestro/overlays/<slug>.json after user approval.
4. Install via maestro overlay add
Run:
maestro overlay add ~/.maestro/overlays/<slug>.json
5. Report
Show the user:
- Path of the saved overlay JSON
- Which targets were patched and which were skipped (missing/disabled)
- Skill chain info (if configured)
- A reminder that
maestro install will auto-reapply on every run
- How to remove:
maestro overlay remove <slug>
Report format
=== OVERLAY INSTALLED ===
Name: <slug>
Path: ~/.maestro/overlays/<slug>.json
Targets: maestro-next (applied), maestro-init (skipped: missing)
Chain: review (via request_user_input) | none
Scopes: [global]
Re-apply: maestro overlay apply
Remove: maestro overlay remove <slug>
Inspect: maestro overlay list
After the report, remind the user they can run maestro overlay list for the interactive TUI showing section maps and overlay management.
<amend_mode>
Amend Mode — signal-driven auto-generation
Runs when --amend (or any --from-* / --scan signal flag) is present. Collects deficiency signals, diagnoses which commands need patching, batch-generates targeted overlays. State machine:
S_COLLECT — 收集信号（从 flags / scan / description） PERSIST: —
S_DIAGNOSE — 映射信号到命令补丁 PERSIST: —
S_GROUP — 分组、规划 overlay 粒度 PERSIST: —
S_PREVIEW — 展示注入点地图、用户确认 PERSIST: —
S_DRAFT — 生成 overlay JSON PERSIST: overlay files
S_INSTALL — 安装 overlay PERSIST: command files
S_REPORT — 报告摘要 + post-patch routing PERSIST: —
Transitions: S_COLLECT → S_DIAGNOSE (signals found; else ERROR E001) → S_GROUP (command deficiencies found; else ERROR E003 when all signals are code bugs) → S_PREVIEW → S_DRAFT (user confirms "Apply all" / selects patches; "Edit" loops back to S_PREVIEW; cancel → END) → S_INSTALL (skipped when --dry-run, which displays JSON + section map and ENDs) → S_REPORT → END.
A. Collect signals
If source flags: extract signals from each specified source.
If --scan or interactive: scan .workflow/ for:
- verification.json → must_have_failures, anti_patterns (filter for command gap direction)
- review.json → findings tagged "process" or "workflow"
- debug understanding.md → root causes with workflow/command cause_type
- issues.jsonl → status=open AND tags include "workflow"/"command"
- execution summaries → plan deviations suggesting missing command step
If only description: parse for affected command(s), what's missing, expected behavior.
B. Diagnose signals
Per signal, determine: signal_id, source, description, target_command, target_section, patch_mode, fix_direction, severity.
Section mapping:
| Signal pattern | Section | Mode |
|---|
| Missing pre-check/gate | execution | prepend |
| Missing post-step/verification | execution | append |
| Missing reading/context | required_reading / deferred_reading | append |
| Incomplete success criteria | success_criteria | append |
| Missing error handling | error_codes | append |
| Scope/context gap | context | append |
| Wrong/missing next-step routing | completion | replace / append |
| Missing/wrong invariant | invariants | append |
| Entirely new concern | (new section) | new-section |
Read pristine source from $PKG_ROOT/.claude/commands/<name>.md to confirm section.
Classify: command deficiency → proceed; code bug → skip (suggest /maestro-companion).
C. Group overlays
Group by target command + section (merge same command+section). Granularity: 1-2 signals → patch-{command}-{slug}.json; 3+ cross-command → amend-{slug}.json. Read target commands to verify sections exist, check existing overlays. Display section map with injection points per target command.
D. Preview & confirm
Display the section map with injection points. request_user_input: Apply all / Select patches / Edit (modify signal target/section, loop back) / Cancel. Skip confirmation if -y.
E. Draft overlays
Build overlay JSON per schema: name, description, targets[], cli, priority (60), enabled, patches[{section, mode, content}]. Content rules: heading includes (patch: SIG-NNN), concise, supplementary doc to ~/.maestro/overlays/docs/ if >10 lines. If --dry-run: display JSON + section map preview and END.
CLI targeting: "cli": "claude" (default, patches .claude/commands/), "codex" (patches .codex/skills/), "both" (both paths).
F. Install
maestro overlay add ~/.maestro/overlays/amend-{slug}.json
On validation failure: fix JSON, retry (max 2).
G. Report
Display summary: signals collected/applied/skipped, overlay details, skipped code-bug routing (to /maestro-companion or step plan --gaps).
</amend_mode>
<error_codes>
Amend mode only:
| Code | Condition | Recovery |
|---|
| E001 | No signals from any source | Verify artifact paths or provide description |
| E002 | Signal source path invalid or unreadable | Check --from-* path; ensure artifact exists |
| E003 | All signals are code bugs, not command gaps | Use /maestro-companion or step plan --gaps |
| E004 | Overlay validation failed after 2 retries | Review JSON manually |
| W001 | Some signals skipped (code bugs) | Route to appropriate fix command |
| W002 | Target command has >= 3 existing overlays | Consider consolidating |
| </error_codes> | | |
<success_criteria>
Default mode:
Amend mode:
### Next-step routing
| Condition | Suggestion |
|-----------|-----------|
| Overlay installed | `maestro overlay list` for interactive management |
| Want to create another | `/maestro-overlay ""` |
| Want to auto-fix from signals | `/maestro-overlay --amend --scan` |
| Want to remove | `maestro overlay remove ` |
