Claude
Skills
Sign in
Back

skill-system-review

Included with Lifetime
$97 forever

Bridge between OMO Prometheus and TKT ticket lifecycle. Generates structured review context for Prometheus after bundle close, converts Prometheus plans into TKT bundle commands, writes review feedback into the Review Agent Inbox, and provides a structured question protocol for gathering information efficiently. Load this skill when you need to: (1) generate a review prompt for a completed ticket/bundle, (2) convert a Prometheus plan.md into TKT worker tickets, (3) write review feedback back into the ticket system, (4) ask structured questions using the question tool across all scenarios (requirements, decisions, review, planning).

AI Agentsscripts

What this skill does


# skill-system-review

Bridge between OMO Prometheus and the TKT ticket lifecycle.

**Two directions**:
1. **Review** — After bundle closes, assemble structured review context for Prometheus to evaluate
2. **Plan→TKT** — Convert Prometheus plans into TKT roadmap bundles and worker tickets

## Operations

### generate-review-prompt

Generate a structured review context from a completed/active ticket for Prometheus review.

```bash
python3 "<this-skill-dir>/scripts/review_prompt.py" generate-review-prompt --ticket-id <TKT-XXX>
```

**Input**: `--ticket-id` (required) — the ticket to build review context for
**Output**: JSON with `review_context`, `prometheus_prompt`, `expected_output_format`

Reads:
- Bundle `review.yaml` (stub generated by `tkt.sh close`)
- All completed ticket results in the bundle
- Audit ticket (TKT-A00) findings
- Current `roadmap.yaml` state

### generate-startup-review-prompt

Generate a review overview prompt for Prometheus at session startup (no active ticket context).

```bash
python3 "<this-skill-dir>/scripts/review_prompt.py" generate-startup-review-prompt
```

**Output**: JSON with `roadmap_summary`, `bundles`, `prometheus_prompt`

### generate-startup-review

Generate a compact startup context summary for the next session.

```bash
python3 "<this-skill-dir>/scripts/review_prompt.py" generate-startup-review
```

**Output**: JSON with `context_summary`, `roadmap_summary`, `bundles`

- includes `carryover_bundles[]` when reviewed bundles still have carryover work

### suggest-roadmap-update

Suggest roadmap changes from findings/issues without mutating `roadmap.yaml`.

```bash
python3 "<this-skill-dir>/scripts/review_prompt.py" suggest-roadmap-update --input findings.json
```

**Output**: JSON `suggestions[]` with `{phase, section, change_type, description, rationale}`

### plan-to-bundle

Convert a Prometheus plan file (`.sisyphus/drafts/*.md`) into TKT bundle creation commands.

```bash
python3 "<this-skill-dir>/scripts/review_prompt.py" plan-to-bundle --plan-file <path>
```

**Input**: `--plan-file` (required) — path to Prometheus plan markdown
**Output**: JSON with `route`, `goal`, `tickets[]`, `tkt_commands[]` (ready-to-execute shell commands)

Parsing rules:
- `## ` or `### ` headings with TODO/task keywords → ticket titles
- `- [ ]` checkboxes → individual worker tickets
- Dependency markers (`depends on`, `after`, `blocks`) → `depends_on` fields
- Effort estimates → ticket description metadata
- Categories (`visual-engineering`, `deep`, `quick`, etc.) → ticket `category`
- `### WAVE N` headings → ticket `wave` metadata for following tasks
- Structured ticket metadata lines (category, effort, acceptance, source metadata, skills, QA scenarios) → preserved into ticket objects and generated TKT commands
- Tiny plans can route to express without filename mentions when they stay within the no-dependency, no-effort fast path

### write-review-inbox

Write Prometheus review feedback into the Review Agent Inbox format for `refresh_review_inbox()` ingestion.

```bash
python3 "<this-skill-dir>/scripts/review_prompt.py" write-review-inbox --input <json-file>
```

**Input**: JSON file with `discussion_points[]`, `next_actions[]`, `batch_id`
**Output**: Appends `## Review Agent Inbox` + `# TICKET_BATCH` section to `note/note_tasks.md`

### generate-dispatch

Generate a worker dispatch view from bundle ticket state.

```bash
python3 "<this-skill-dir>/scripts/review_prompt.py" generate-dispatch --bundle B-001 [--tickets TKT-001,TKT-002]
python3 "<this-skill-dir>/scripts/review_prompt.py" generate-dispatch --auto
```

**Input**: `--bundle` (required), optional `--tickets` comma list
**Output**: human-readable wave summary plus last-line JSON containing grouped dispatch waves

Rules:
- without `--tickets`, emit currently open worker tickets only
- preserve bundle dependency order into `dispatch_wave`
- include one-line summary and effort estimate for each ticket
- `--auto` creates the suggested next bundle from `suggest-next-bundle` and immediately emits dispatch for it

### suggest-next-bundle

Suggest the next bundle goal and seed tickets from roadmap/open work/carryover.

```bash
python3 "<this-skill-dir>/scripts/review_prompt.py" suggest-next-bundle
```

**Output**: JSON with `goal`, `suggested_tickets[]`, `open_issues[]`

## Integration with OMO Prometheus

### Prometheus as Review Agent

When a TKT bundle closes:
1. `tkt.sh close` generates `review.yaml` stub
2. PM Agent calls `generate-review-prompt` to assemble review context
3. Prometheus receives the structured context and produces:
   - `summary` — what was accomplished
   - `discussion_points[]` — trade-offs, concerns, questions for user
   - `next_actions[]` — follow-up work items
   - `quality_assessment` — structured quality evaluation
4. `write-review-inbox` converts Prometheus output into TKT-ingestible tickets
5. `refresh_review_inbox()` picks up new tickets automatically

### Prometheus as Roadmap Planner

When a user makes a new request through Prometheus:
1. Prometheus conducts structured interview (OMO default behavior)
2. Prometheus writes plan to `.sisyphus/drafts/`
3. `plan-to-bundle` reads the plan and generates TKT commands
4. PM Agent executes the commands to create roadmap goal + bundle + worker tickets
5. OMO dispatches agents to claim and execute tickets

### Prompt Reference

- `prompts/prometheus-tkt-integration.md` — Instructions for Prometheus on how to use TKT roadmap/bundle system
- `prompts/question-protocol.md` — Structured questioning guide for all scenarios (requirements, branch decisions, review discussion, roadmap planning). Implements the `question_tool_first` policy from `config/tkt.yaml`.

## Compatibility

- **tickets.py alignment**: `review_prompt.py` path matches the hardcoded reference at `tickets.py:2468-2470`
- **Review Inbox format**: Output matches `parse_review_agent_inbox()` expected format (`## Review Agent Inbox` + `# TICKET_BATCH`)
- **Scope rules**: Referenced in 14+ ticket scope `allowed_prefixes` entries in `tickets.py`

```skill-manifest
{
  "schema_version": "2.0",
  "id": "skill-system-review",
  "version": "1.0.0",
  "capabilities": [
    "review-generate",
    "review-startup",
    "review-startup-summary",
    "review-roadmap-suggestion",
    "review-plan-to-bundle",
    "review-generate-dispatch",
    "review-suggest-next-bundle",
    "review-write-inbox"
  ],
  "effects": ["fs.read", "fs.write"],
  "operations": {
    "generate-review-prompt": {
      "description": "Assemble structured review context from completed ticket/bundle for Prometheus",
      "input": { "ticket_id": { "type": "string", "required": true } },
      "output": { "description": "Review context JSON", "fields": { "review_context": "object", "prometheus_prompt": "string" } },
      "entrypoints": {
        "unix": ["python3", "{skill_dir}/scripts/review_prompt.py", "generate-review-prompt", "--ticket-id", "{ticket_id}"]
      }
    },
    "generate-startup-review-prompt": {
      "description": "Generate Prometheus review overview at session startup",
      "input": {},
      "output": { "description": "Startup review context JSON", "fields": { "roadmap_summary": "object", "bundles": "array", "prometheus_prompt": "string" } },
      "entrypoints": {
        "unix": ["python3", "{skill_dir}/scripts/review_prompt.py", "generate-startup-review-prompt"]
      }
    },
    "generate-startup-review": {
      "description": "Generate compact startup context summary from roadmap and recent bundle reviews",
      "input": {},
      "output": { "description": "Startup summary JSON", "fields": { "context_summary": "string", "roadmap_summary": "object", "bundles": "array" } },
      "entrypoints": {
        "unix": ["python3", "{skill_dir}/scripts/review_prompt.py", "generate-startup-review"]
      }
    },
    "suggest-roadmap-update": {
      "description": "Suggest roadmap updates from findings/issues without mutating roadmap.yaml",
      "input": {
  
Files: 14
Size: 110.0 KB
Complexity: 75/100
Category: AI Agents

Related in AI Agents