

Also from Kynth Studios


Also from Kynth Studios


Also from Kynth Studios
123456# Orchestrate7> **HARD GATE** — **HARD GATE** — Do NOT invoke orchestrate-project unless you have a clear multi-phase workflow. Single-skill tasks should use dedicated skills instead. Orchestrate is for complex, multi-stage work that requires coordination across phases.8910The orchestrate skill coordinates projects through a prescriptive 6-phase core loop with hard gates, ensuring consistent quality and preventing scope creep.1112## Quick Start1314```bash15# Start a new project (initializes specs/ YAML cockpit and begins discover phase)16claude /orchestrate --mode standard1718# Or resume an existing project at the current phase19claude /orchestrate --mode standard --resume2021# For low-risk scenarios (hotfixes, refactors on well-tested code)22claude /orchestrate --mode fast-track23```2425## The 6-Phase Core Loop26271. **DISCOVER** (3-6 hours): Understand problem. Deliverables: `requirements/VISION_LATEST.yaml`, `requirements/SCOPE_LATEST.yaml`, `plans/TECH_STACK_LATEST.md`.282. **ELABORATE** (3-6 hours): Research solutions. Deliverables: Prior art in scope YAML, ADRs in `specs/adr/`.293. **PLAN** (2-4 hours): Write verifiable plan. Deliverables: `release-plan.yaml`, `epics/eNN-*.yaml` with `verify:` per task.304. **BUILD** (1-8 hours): Execute plan. Runs build-epic once per story in WSJF order. Deliverables: Code; update `execution-status.yaml`.315. **VERIFY** (1-3 hours): Validate success criteria. Deliverables: UAT evidence, `specs/EVALS-*.md` if used.326. **RELEASE** (30 min - 2 hours): Ship to production. Deliverables: Release tag (vX.Y.Z), `state.yaml` `release.last_tag`.3334### Checkpoint / resume3536Track progress via `specs/state.yaml` `project_cycle`:37- `project_cycle.current_phase`: current phase (1–6)38- `project_cycle.completed_phases`: completed phase numbers39- `handoff.next_skill`: skill for the current phase40- On resume, read `project_cycle.current_phase` and continue from there4142See [REFERENCE.md](REFERENCE.md) for detailed phase specifications and gate types.4344## How Orchestrate Works45461. **Maintains state.yaml** — Tracks current phase, `active_epic`, `active_flow`, decisions, risks.472. **Spawns appropriate skills** — Routes by `model:` frontmatter. Decisions pass only via `specs/state.yaml` `handoff` between spawns.483. **Methodology lenses** — If `specs/tech-architecture/e*-TEST_PLAN_LATEST.md` or ADRs exist, apply at phase gates.494. **Enforces gates** — Hard stops if success criteria not met.505. **The Gatekeeper** — Between stories in BUILD: read `specs/execution-status.yaml`; previous story must be `done` before starting the next; use `build-epic` for the 8-step epic cycle.516. **Pauses for confirmation** — After each phase, asks "Ready to proceed?".527. **Snapshots** — `bash scripts/bp-yaml-snapshot.sh` before major release cuts.5354## Orchestration Modes5556- **Standard**: Enforce all gates. Use for new features and major refactors.57- **Fast-Track**: Skip negotiable gates. Use for hotfixes and minor improvements.58- **Ad-Hoc**: Warnings only. Use for prototyping and spikes (non-production).5960See [REFERENCE.md](REFERENCE.md) for full mode behaviors.6162## Verification6364All phases complete with artifacts:65```bash66verify: test -f specs/state.yaml && test -f specs/release-plan.yaml && test -f specs/product/SCOPE_LATEST.yaml && ls specs/epics/*.yaml 1>/dev/null && echo "✅ All phases complete"67```68697071<!-- story: e05s03 -->7273---7475# Orchestrate Reference: Phases, Modes, and Workflows7677Detailed documentation for the `orchestrate-project` meta-skill.7879## The 6-Phase Core Loop8081### PHASE 1: DISCOVER82- **Goal**: Understand the problem completely and map existing context.83- **Deliverables**: `requirements/VISION_LATEST.yaml`, `requirements/SCOPE_LATEST.yaml`, `plans/TECH_STACK_LATEST.md`.84- **Skills**: `survey-context`, `elaborate-spec`, `grill-me`.85- **Gate**: Confirm ("Is the problem clear?").8687### PHASE 2: ELABORATE88- **Goal**: Research solutions and lock architectural design.89- **Deliverables**: Prior art in scope YAML, ADRs in `specs/adr/`.90- **Skills**: `grill-me`, `model-domain`, `define-language`, `deepen-architecture`, `design-interface`.91- **Gate**: Quality ≥94% (via `request-review`) + Confirm ("Are decisions locked?").9293### PHASE 3: PLAN94- **Goal**: Write a verifiable implementation plan with success criteria.95- **Deliverables**: `release-plan.yaml`, `epics/eNN-*.yaml` with `verify:` per task.96- **Skills**: `scope-work`, `slice-tasks`, `plan-work`.97- **Gate**: Quality (request-review ≥94%) + slopcheck [SUS]/[SLOP].9899### PHASE 4: BUILD100- **Goal**: Execute the plan story-by-story using the 8-step `build-epic` cycle with TDD and vertical slices.101- **Deliverables**: Code; `execution-status.yaml` updated per story; `specs/metrics/cycle-times.yaml` row per story.102- **Skills**: `build-epic` (conductor) → per-story: `survey-context`, `plan-work`, `kickoff-branch`, `develop-tdd`, `verify-work`, `audit-code`, `commit-message`, `release-branch`.103- **BCP tracking**: `plan-release` sizes each story in Business Complexity Points (BCP) before the build queue; `plan-work` confirms and writes the size to `state.yaml` as `epic_cycle.story_bcps`. See `docs/references/bcp.md` for the canonical sizing method.104- **Timestamps**: `survey-context` stamps `metrics.story_start`; `release-branch` stamps `metrics.story_end` and writes BCP/hr to `specs/metrics/cycle-times.yaml`.105- **next_skill**: Each critical-path skill writes `handoff.next_skill` to `state.yaml`. Agents resume by reading `state.yaml` — no guessing.106- **Dashboard**: `npm run dashboard` (TUI) or `npm run dashboard:web` (browser, port 7742) shows live pipeline, epic queue, BCP metrics, and cycle-time ledger.107- **Gate**: Integration tests PASS; all 8 build-epic steps completed per story.108109### PHASE 5: VERIFY110- **Goal**: Validate success criteria and ensure production readiness.111- **Deliverables**: UAT evidence, eval results.112- **Skills**: `run-evals`, `verify-work`, `audit-code`, `request-review` (optional).113- **Gate**: Verification Script confirmed; `verify-work` not on `main`/`master`.114115### PHASE 6: RELEASE (Integrate)116- **Goal**: Ship to `main` with full traceability.117- **Deliverables**: Release tag (vX.Y.Z), release notes via semantic-release.118- **Skills**: `commit-message`, `release-branch`.119- **Git arc**:120 1. Plan on `main` (Discover / Plan)121 2. `kickoff-branch` → worktree + feature branch + clean baseline122 3. Build / Verify / Review on feature branch123 4. Integrate: **solo-local** (`scripts/land-branch.sh`) or **team-pr** (`gh pr create` → squash merge)124 5. Cleanup worktree; **end on `main`** in primary repo root125- **Gate**: Safety ("About to land on main. Confirm?").126127---128129## Orchestration Modes130131### Mode 1: Standard (Enforce All Gates)132**Use Case**: New features, major refactors, architectural changes.133**Behavior**:134- All Confirm gates require explicit user approval.135- All Quality gates are hard stops if threshold is not met.136- No shortcuts or phase skipping.137138### Mode 2: Fast-Track (Skip Negotiable Gates)139**Use Case**: Hotfixes, minor improvements, refactors on well-tested code.140**Behavior**:141- Skip Discover if `requirements/SCOPE_LATEST.yaml` exists.142- Skip Elaborate if design decisions are already locked.143- Skip Verify if coverage ≥95% + all tests PASS.144- Soft gates auto-approve if baseline conditions are met.145146### Mode 3: Ad-Hoc (Legacy, Warnings Only)147**Use Case**: Exploration, prototyping, spikes (NOT for production).148**Behavior**:149- Gates emit warnings but do not block execution.150- User can manually skip any phase.151- No enforced quality thresholds.152153---154155## Gate & Checkpoint Types156*See `docs/references/gates.md` and `docs/references/checkpoints.md` for full specs.*157158- **Confirm**: Requires human "yes/no" decision.159- **Quality**: Automated threshold check (e.g., coverage, audit score).160- **Safety**: Destructive actions require risk acknowledgment.161- **Transition**: Mandatory artifact presence check.162- **slopcheck**: Identification of [SUS] (Suspicious) or [SLOP] (High-risk) packages.163164---165166## Error Recovery & State167Orchestrate maintains `specs/state.yaml` to track:168- **Current flow / epic**: `active_flow`, `active_epic_id`, `epic_cycle`.169- **Handoff**: `last_step_completed`, `open_decisions`, `required_reading`, `next_skill`.170- **Git**: `branch`, `hash` for session continuity.171- **Progress**: Story status lives in `execution-status.yaml` only.172173In the event of a crash or exit, run `claude /orchestrate --resume` to pick up exactly where the session left off.174
One repository carrying more than one format is the comparison this product exists for: does anyone actually write different content in each file, or is one a copy of the other?
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| danielvm-git/bigpowers.cursor/rules/simple-english.mdc · 139 | Cursor rules | styletypesgitdatabase+6 | 47/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/assess-impact.mdc · 139 | Cursor rules | testtesting-strategydeployment | 66/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/audit-plan.mdc · 139 | Cursor rules | buildteststylegit | 74/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/build-epic.mdc · 139 | Cursor rules | buildgit | 58/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/change-request.mdc · 139 | Cursor rules | no sections | 48/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/commit-message.mdc · 139 | Cursor rules | lint-formatstyletypesgit+3 | 82/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/compose-workflow.mdc · 139 | Cursor rules | styledo-notagent-behaviour | 65/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/context7-mcp.mdc · 139 | Cursor rules | style | 54/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/deepen-architecture.mdc · 139 | Cursor rules | testtesting-strategydo-not | 57/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/define-language.mdc · 139 | Cursor rules | lint-formatdo-not | 65/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/define-success.mdc · 139 | Cursor rules | no sections | 4/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/delegate-task.mdc · 139 | Cursor rules | git | 62/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/deploy.mdc · 139 | Cursor rules | setupbuildtestdeployment | 77/100 | 14 days ago | |
| danielvm-git/bigpowers.windsurf/rules/verify-work.md · 139 | Windsurf rules | buildtestlint-formatagent-behaviour | 74/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/develop-tdd.mdc · 139 | Cursor rules | teststylearchtesting-strategy+5 | 85/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/diagnose-root.mdc · 139 | Cursor rules | no sections | 39/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/diagnose-stall.mdc · 139 | Cursor rules | no sections | 44/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/dispatch-agents.mdc · 139 | Cursor rules | git | 54/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/edit-document.mdc · 139 | Cursor rules | no sections | 39/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/elaborate-spec.mdc · 139 | Cursor rules | test | 58/100 | 14 days ago |
Same format, overlapping stack, ranked by quality.
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| hiromaily/go-crypto-wallet.cursor/rules/typescript.mdc · 126 | Cursor rules | setupbuildtestlint-format+6 | 100/100 | 14 days ago | |
| TechSquidTV/Hermes.cursor/rules/10-hermes-api.mdc · 46 | Cursor rules | testlint-formatstylearch+5 | 100/100 | 14 days ago | |
| dodgecfr/combatfilms-webapp.cursor/rules/frontend.mdc · 0 | Cursor rules | setuptestlint-formatstyle+7 | 99/100 | 14 days ago | |
| deifos/clipmira-subtitles.cursor/rules/frontend.mdc · 1 | Cursor rules | setuptestlint-formatstyle+7 | 99/100 | 14 days ago | |
| markstev/mark-starter.cursor/rules/frontend.mdc · 0 | Cursor rules | setuptestlint-formatstyle+6 | 99/100 | 14 days ago | |
| Allymahmoud/case-intake-platform.cursor/rules/frontend.mdc · 0 | Cursor rules | setuptestlint-formatstyle+7 | 99/100 | 14 days ago | |
| langflow-ai/langflow.cursor/rules/docs_development.mdc · 153k | Cursor rules | setupbuildtestlint-format+7 | 97/100 | 14 days ago | |
| bybren-llc/safe-agentic-workflow.cursor/rules/10-backend-python.mdc · 399 | Cursor rules | testlint-formatstylegit+4 | 97/100 | today |
A badge carrying the measured quality of the strongest agent config file in this repository, out of 100. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.
[](https://rulestack.kynth.studio/configs/danielvm-git-bigpowers-cursor-rules-orchestrate-project)Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:
Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.