A workflow skill that uses four lenses to deterministically generate a roadmap plan.
Install
mkdir -p .claude/skills/committee-plan && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10262" && unzip -o skill.zip -d .claude/skills/committee-plan && rm skill.zipInstalls to .claude/skills/committee-plan
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
**WORKFLOW SKILL** — How the /issue-plan committee fans out four read-only lenses over the open backlog and synthesizes an ORDER-ONLY plan deterministically. USE WHEN running /issue-plan or building the planning step. INVOKES: the plan-lens-* agents (or inline personas), scripts/sync-plan.rb. DO NOT USE FOR implementing tasks (use /issue-implement) or filing them (use /repo-audit intake).Key capabilities
- →Synthesize an order-only plan for the open backlog
- →Analyze tasks using a priority/impact lens
- →Identify task dependencies and sequencing
- →Assess risk and autonomy for task batches
- →Determine testing requirements for each batch
How it works
A committee of four specialized lenses (priority, dependency, risk, test framework) reads the open backlog and synthesizes an order-only plan deterministically.
Inputs & outputs
When to use committee-plan
- →Generate a deterministic roadmap plan
- →Prioritize backlog tasks using multi-lens analysis
- →Identify task dependencies and risk
About this skill
Committee Plan
Operational checklist for the planning committee. Canonical contract: /issue-plan. The committee plans, it does not build — it writes only _data/roadmap_plan.yml + one pinned issue.
Golden rules
- Read-only on code. Only
_data/roadmap_plan.ymland the pinned issue change. - Order only. Reference task ids; never copy a backlog-owned field
(risk/priority/area/status) into the plan —
sync-plan.rb --checkrejects it. - Deterministic. Same corpus ⇒ byte-identical plan. Skip the whole run when the corpus hash is unchanged.
- Bounded. Exactly 4 lenses, no recursion; batches ≤6 tasks; ≤5 batches/run.
- Autonomy is derived, never re-encoded — point at
continuous-evolution.md.
The four lenses (read-only, write nothing)
| Lens | Agent | Answers |
|---|---|---|
| Priority/impact | plan-lens-priority | which tasks matter most |
| Dependency/DAG | plan-lens-dependency | what must precede / not parallelize |
| Risk/autonomy | plan-lens-risk | which batches mix auto + human (→ split) |
| Test framework | plan-lens-test | the tests/evidence each batch needs |
Prefer one Task subagent per lens; if the runtime can't delegate, run the four personas inline and sequentially — identical output.
Synthesis (fixed precedence ⇒ determinism)
dependency sets batch membership → risk splits mixed batches → priority orders within the layering → test annotates test_framework. Write the plan, record meta.corpus_hash + meta.updated, then:
ruby scripts/sync-plan.rb --check # ids open · DAG acyclic · order-only
Open a chore(plan) PR (no auto-merge). On merge, scripts/sync-plan.sh upserts the single pinned tracking issue (agent-hold).
Idempotency
- The corpus-hash gate makes a no-change run a no-op (cheap on schedule).
- The pinned issue is marker-fenced (
<!-- roadmap-plan:pinned -->) and upserted, never duplicated.
When not to use it
- →When implementing tasks
- →When filing new tasks
Limitations
- →The committee plans, it does not build
- →Read-only on code
- →Order only
How it compares
This skill uses a fixed committee structure and synthesis precedence to deterministically generate a roadmap plan, ensuring consistent output for the same input, unlike a manual planning process.
Compared to similar skills
committee-plan side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| committee-plan (this skill) | 0 | 27d | Review | Intermediate |
| trello | 41 | 2mo | Review | Beginner |
| executing-plans | 6 | 3mo | No flags | Intermediate |
| github-project-management | 4 | 6mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by bamr87
View all by bamr87 →You might also like
trello
openclaw
Manage Trello boards, lists, and cards via the Trello REST API.
executing-plans
obra
Use when you have a written implementation plan to execute in a separate session with review checkpoints
github-project-management
ruvnet
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
project-clickup
incidentfox
ClickUp project management integration for incident tracking and task management
coo-advisor
alirezarezvani
Operations leadership for scaling companies. Process design, OKR execution, operational cadence, and scaling playbooks. Use when designing operations, setting up OKRs, building processes, scaling teams, analyzing bottlenecks, planning operational cadence, or when user mentions COO, operations, process improvement, OKRs, scaling, operational efficiency, or execution.
tlc-spec-driven
tech-leads-club
Project and feature planning with 4 phases - Specify, Design, Tasks, Implement+Validate. Creates atomic tasks with verification criteria and maintains persistent memory across sessions. Stack-agnostic. Use when: (1) Starting new projects (initialize vision, goals, roadmap), (2) Working with existing codebases (map stack, architecture, conventions), (3) Planning features (requirements, design, task breakdown), (4) Implementing with verification, (5) Tracking decisions/blockers across sessions, (6) Pausing/resuming work. Triggers on "initialize project", "map codebase", "specify feature", "design", "tasks", "implement", "pause work", "resume work".