Install
$ agentstack add skill-danielvm-git-bigpowers-orchestrate-project ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Orchestrate
> 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.
The orchestrate skill coordinates projects through a prescriptive 6-phase core loop with hard gates, ensuring consistent quality and preventing scope creep.
Quick Start
# Start a new project (initializes specs/ YAML cockpit and begins discover phase)
claude /orchestrate --mode standard
# Or resume an existing project at the current phase
claude /orchestrate --mode standard --resume
# For low-risk scenarios (hotfixes, refactors on well-tested code)
claude /orchestrate --mode fast-track
The 6-Phase Core Loop
- DISCOVER (3-6 hours): Understand problem. Deliverables:
requirements/VISION_LATEST.yaml,requirements/SCOPE_LATEST.yaml,plans/TECH_STACK_LATEST.md. - ELABORATE (3-6 hours): Research solutions. Deliverables: Prior art in scope YAML, ADRs in
specs/adr/. - PLAN (2-4 hours): Write verifiable plan. Deliverables:
release-plan.yaml,epics/eNN-*.yamlwithverify:per task. - BUILD (1-8 hours): Execute plan. Runs build-epic once per story in WSJF order. Deliverables: Code; update
execution-status.yaml. - VERIFY (1-3 hours): Validate success criteria. Deliverables: UAT evidence,
specs/EVALS-*.mdif used. - RELEASE (30 min - 2 hours): Ship to production. Deliverables: Release tag (vX.Y.Z),
state.yamlrelease.last_tag.
Checkpoint / resume
Track progress via specs/state.yaml project_cycle:
project_cycle.current_phase: current phase (1–6)project_cycle.completed_phases: completed phase numbershandoff.next_skill: skill for the current phase- On resume, read
project_cycle.current_phaseand continue from there
See [REFERENCE.md](REFERENCE.md) for detailed phase specifications and gate types.
How Orchestrate Works
- Maintains state.yaml — Tracks current phase,
active_epic,active_flow, decisions, risks. - Spawns appropriate skills — Routes by
model:frontmatter. Decisions pass only viaspecs/state.yamlhandoffbetween spawns. - Methodology lenses — If
specs/tech-architecture/test.mdor ADRs exist, apply at phase gates. - Enforces gates — Hard stops if success criteria not met.
- The Gatekeeper — Between stories in BUILD: read
specs/execution-status.yaml; previous story must bedonebefore starting the next; usebuild-epicfor the 8-step epic cycle. - Pauses for confirmation — After each phase, asks "Ready to proceed?".
- Snapshots —
bash scripts/bp-yaml-snapshot.shbefore major release cuts.
Orchestration Modes
- Standard: Enforce all gates. Use for new features and major refactors.
- Fast-Track: Skip negotiable gates. Use for hotfixes and minor improvements.
- Ad-Hoc: Warnings only. Use for prototyping and spikes (non-production).
See [REFERENCE.md](REFERENCE.md) for full mode behaviors.
Verification
All phases complete with artifacts:
verify: 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"
Orchestrate Reference: Phases, Modes, and Workflows
Detailed documentation for the orchestrate-project meta-skill.
The 6-Phase Core Loop
PHASE 1: DISCOVER
- Goal: Understand the problem completely and map existing context.
- Deliverables:
requirements/VISION_LATEST.yaml,requirements/SCOPE_LATEST.yaml,plans/TECH_STACK_LATEST.md. - Skills:
survey-context,elaborate-spec,grill-me. - Gate: Confirm ("Is the problem clear?").
PHASE 2: ELABORATE
- Goal: Research solutions and lock architectural design.
- Deliverables: Prior art in scope YAML, ADRs in
specs/adr/. - Skills:
grill-me,model-domain,define-language,deepen-architecture,design-interface. - Gate: Quality ≥94% (via
request-review) + Confirm ("Are decisions locked?").
PHASE 3: PLAN
- Goal: Write a verifiable implementation plan with success criteria.
- Deliverables:
release-plan.yaml,epics/eNN-*.yamlwithverify:per task. - Skills:
scope-work,slice-tasks,define-success,plan-work. - Gate: Quality (request-review ≥94%) + slopcheck [SUS]/[SLOP].
PHASE 4: BUILD
- Goal: Execute the plan story-by-story using the 8-step
build-epiccycle with TDD and vertical slices. - Deliverables: Code;
execution-status.yamlupdated per story;specs/metrics/cycle-times.yamlrow per story. - Skills:
build-epic(conductor) → per-story:survey-context,plan-work,kickoff-branch,develop-tdd,verify-work,audit-code,commit-message,release-branch. - BCP tracking:
plan-releasesizes each story in Business Complexity Points (BCP) before the build queue;plan-workconfirms and writes the size tostate.yamlasepic_cycle.story_bcps. Seedocs/references/bcp.mdfor the canonical sizing method. - Timestamps:
survey-contextstampsmetrics.story_start;release-branchstampsmetrics.story_endand writes BCP/hr tospecs/metrics/cycle-times.yaml. - next_skill: Each critical-path skill writes
handoff.next_skilltostate.yaml. Agents resume by readingstate.yaml— no guessing. - Dashboard:
npm run dashboard(TUI) ornpm run dashboard:web(browser, port 7742) shows live pipeline, epic queue, BCP metrics, and cycle-time ledger. - Gate: Integration tests PASS; all 8 build-epic steps completed per story.
PHASE 5: VERIFY
- Goal: Validate success criteria and ensure production readiness.
- Deliverables: UAT evidence, eval results.
- Skills:
run-evals,verify-work,audit-code,request-review(optional). - Gate: Verification Script confirmed;
verify-worknot onmain/master.
PHASE 6: RELEASE (Integrate)
- Goal: Ship to
mainwith full traceability. - Deliverables: Release tag (vX.Y.Z), release notes via semantic-release.
- Skills:
commit-message,release-branch. - Git arc:
- Plan on
main(Discover / Plan) kickoff-branch→ worktree + feature branch + clean baseline- Build / Verify / Review on feature branch
- Integrate: solo-local (
scripts/land-branch.sh) or team-pr (gh pr create→ squash merge) - Cleanup worktree; end on
mainin primary repo root
- Gate: Safety ("About to land on main. Confirm?").
Orchestration Modes
Mode 1: Standard (Enforce All Gates)
Use Case: New features, major refactors, architectural changes. Behavior:
- All Confirm gates require explicit user approval.
- All Quality gates are hard stops if threshold is not met.
- No shortcuts or phase skipping.
Mode 2: Fast-Track (Skip Negotiable Gates)
Use Case: Hotfixes, minor improvements, refactors on well-tested code. Behavior:
- Skip Discover if
requirements/SCOPE_LATEST.yamlexists. - Skip Elaborate if design decisions are already locked.
- Skip Verify if coverage ≥95% + all tests PASS.
- Soft gates auto-approve if baseline conditions are met.
Mode 3: Ad-Hoc (Legacy, Warnings Only)
Use Case: Exploration, prototyping, spikes (NOT for production). Behavior:
- Gates emit warnings but do not block execution.
- User can manually skip any phase.
- No enforced quality thresholds.
Gate & Checkpoint Types
See docs/references/gates.md and docs/references/checkpoints.md for full specs.
- Confirm: Requires human "yes/no" decision.
- Quality: Automated threshold check (e.g., coverage, audit score).
- Safety: Destructive actions require risk acknowledgment.
- Transition: Mandatory artifact presence check.
- slopcheck: Identification of [SUS] (Suspicious) or [SLOP] (High-risk) packages.
Error Recovery & State
Orchestrate maintains specs/state.yaml to track:
- Current flow / epic:
active_flow,active_epic_id,epic_cycle. - Handoff:
last_step_completed,open_decisions,required_reading,next_skill. - Git:
branch,hashfor session continuity. - Progress: Story status lives in
execution-status.yamlonly.
In the event of a crash or exit, run claude /orchestrate --resume to pick up exactly where the session left off.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: danielvm-git
- Source: danielvm-git/bigpowers
- License: MIT
- Homepage: https://github.com/danielvm-git/bigpowers
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.