tibursocampos/agent-dev-toolkit / core/skills/orchestrate-analyze
orchestrate-analyze
VerifiedOrchestrated Delivery O1: triage a feature, spawn conditional Agent specialists, write FEATURE.md + CONTINUITY + US/TS under features/NNN-slug/. No app code. Use when invoking /orchestrate-analyze.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 18.5 KB |
| reference.md | markdown | 1.8 KB |
| references/arch-confirm.md | markdown | 4.0 KB |
| references/boundaries-handoff.md | markdown | 3.5 KB |
| references/command.md | markdown | 3.5 KB |
| references/intent-classification.md | markdown | 5.2 KB |
| references/memory-bank-gate.md | markdown | 881 B |
| references/must-not.md | markdown | 4.4 KB |
| references/process-common.md | markdown | 3.8 KB |
| references/spawn-map.md | markdown | 3.7 KB |
| references/story-synthesis.md | markdown | 18.8 KB |
| references/triage.md | markdown | 5.0 KB |
references/command.md
View on GitHub# orchestrate-analyze — command playbook
**Load after Step -1 gates.** Ordered step discovery without dumping `SKILL.md` Process. Load **one** section file per step (`SKILL-REFERENCE-RETRIEVAL.md`).
| Step | Action | Lazy section / contract |
|------|--------|-------------------------|
| -1b | Caveman Lite when active | `references/process-common.md` § Caveman |
| 1 | Gate check; load PIPELINE + SESSION; STOP if unchecked | `PIPELINE.md`, `SESSION.md` |
| 1b | Resolve `invocation_context` (default `orchestrated`) | `INVOCATION-CONTEXTS.md` |
| 2 | Resolve storage / bank roots; path sanitize | `references/process-common.md` § Resolve storage; `STORAGE.md` |
| 3 | Intent classification (triage entry) | `references/intent-classification.md` |
| 4 | Step 0 Memory Bank Gate (`auto`) | `references/memory-bank-gate.md`; `MEMORY-BANK.md` |
| 5 | Collect description and triage (`needs_*`) | `references/triage.md`; `ROSTER.md` |
| 6 | Trivial shortcut (optional exit) | `references/triage.md` § Trivial |
| 7 | Allocate NNN-slug; scaffold `FEATURE.md` and `CONTINUITY.md` only (no story folders) | `references/story-synthesis.md` |
| 8 | Spawn Agent specialists (SPAWN; omit model). Return notes to the parent. Do not create story folders until step 9 | `references/spawn-map.md`; `SPAWN.md` |
| 8b | Architecture confirm gate. Return the ARCH draft to the parent until step 9 | `references/arch-confirm.md` |
| 8c | Feature research on `FEATURE.md` only. Must render the 8c stage table and checkpoint from `LIVE-STAGE-TABLE.md` at every named display point. If `open_question`, stop. Do not run step 9 | `{{TOOLKIT_ROOT}}/skills/refine-story/references/feature-research.md`; `readiness-severity.md` § Open-question gate; `LIVE-STAGE-TABLE.md` |
| 9 | Synthesize story folders only when FEATURE has no open question. Then FEATURE / CONTINUITY / STORY, product artifact quality gates (FEATURE depth TE01, promotion TE02, cap ≤4), and brownfield ANALYSIS validation | `references/story-synthesis.md`; `validate-brownfield-analysis.ps1` |
| 10 | Human backlog approval (**sim**) — only if all gates passed, including required brownfield ANALYSIS validation | `references/process-common.md` § Backlog approval |
| 11 | Approve → CONTINUITY + O2 handoff | `references/boundaries-handoff.md` |
| 12 | Durable progress handoff | `references/process-common.md` § Durable progress handoff |
**Must not (full):** `references/must-not.md`. Handoff strings: `references/boundaries-handoff.md`.
## Cumulative O1 checkpoint
At O1 start, you must render the cumulative O1/O2 checkpoint from `{{TOOLKIT_ROOT}}/skills/_shared/sdd-artifacts/LIVE-STAGE-TABLE.md`, in the user chat language. You must refresh it at the start of the stage, before each gate, after each gate answer, on each row state change, on a blocker (`open_question`), and at the close of 8c, plus after each material evidence pass or decision, around architecture/backlog approval gates, and at handoff/close. Always render the full table with every row; no summary rows. State keys and ASCII glyphs follow `LIVE-STAGE-TABLE.md`. The checkpoint shows current process, completed evidence, pending analysis/artifacts, decisions/questions, blockers and next action; keep prior relevant findings across redraws. Derive facts from canonical feature/story artifacts and confirmed conversation decisions. The checkpoint and stage table are chat-only; do not add a second persisted ledger to FEATURE or CONTINUITY. At O1 step 8c, render both the feature-research stage table and the cumulative checkpoint.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |