/council
Assess a proposal through independent technical, product, risk, and dissenting lenses, then synthesize a decision without mutating unless explicitly requested.
$ npx -y skills add automagik-dev/genie --skill council --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/council
Context preview
The summary Claude sees to decide when to auto-load this skill.
Assess a proposal through independent technical, product, risk, and dissenting lenses, then synthesize a decision without mutating unless explicitly requested.
SKILL.md
council.SKILL.mdname: council
description: "Assess a proposal through independent technical, product, risk, and dissenting lenses, then synthesize a decision without mutating unless explicitly requested."
Council
**Runtime syntax:** in Codex, invoke the plugin copy with the owner-qualified `$genie:<skill>` selector; use bare `$<skill>` only when intentionally selecting a user-tier copy (a separately installed personal copy; Genie no longer seeds this tier). Claude Code and Hermes use `/<skill>`. Cross-skill prose below uses bare names as portable semantic routes; the orchestrator resolves the selector for the active tier.
Use a council when a consequential decision benefits from independent scrutiny. The council assesses by default; it does not edit files, change configuration, or execute a proposed plan unless the user explicitly asks it to mutate.
Dispatch
Read `references/native-surfaces.md` relative to the directory containing this loaded `SKILL.md` and use the active runtime's native delegation surface. Dispatch these lenses independently and in parallel when supported:
1. **Architecture** — contracts, coupling, failure modes, operability, and long-term cost. 2. **Delivery** — sequencing, testability, migration, rollback, and evidence required to ship. 3. **Product** — user value, usability, scope discipline, and compatibility. 4. **Security** — trust boundaries, permissions, data exposure, and abuse cases. 5. **Dissent** — the strongest evidence-backed case against the emerging consensus.
Give every lens the same decision statement, constraints, evidence, and explicit unknowns. Do not show one lens another lens's conclusion before it answers.
Lens response
Verdict: support | support-with-conditions | oppose | insufficient-evidence
Confidence: low | medium | high
Key evidence:
- ...
Risks or objections:
- ...
Required conditions:
- ...
Unknowns:
- ...
Preserve minority opinions. A dissenting finding is not deleted merely because most lenses agree.
Synthesis
Decision: proceed | proceed-with-conditions | revise | stop | gather-evidence
Consensus: <where the lenses agree>
Dissent: <minority positions, attributed by lens>
Conditions: <concrete prerequisites>
Evidence gaps: <unknowns that could change the decision>
Next action: <one bounded next step>
Explain how conflicts were resolved. If evidence is insufficient, say so rather than manufacturing consensus. End after assessment unless mutation was explicitly authorized.
Read more
name: council description: "Assess a proposal through independent technical, product, risk, and dissenting lenses, then synthesize a decision without mutating unless explicitly requested."
Council
**Runtime syntax:** in Codex, invoke the plugin copy with the owner-qualified `$genie:<skill>` selector; use bare `$<skill>` only when intentionally selecting a user-tier copy (a separately installed personal copy; Genie no longer seeds this tier). Claude Code and Hermes use `/<skill>`. Cross-skill prose below uses bare names as portable semantic routes; the orchestrator resolves the selector for the active tier.
Use a council when a consequential decision benefits from independent scrutiny. The council assesses by default; it does not edit files, change configuration, or execute a proposed plan unless the user explicitly asks it to mutate.
Dispatch
Read `references/native-surfaces.md` relative to the directory containing this loaded `SKILL.md` and use the active runtime's native delegation surface. Dispatch these lenses independently and in parallel when supported:
1. **Architecture** — contracts, coupling, failure modes, operability, and long-term cost. 2. **Delivery** — sequencing, testability, migration, rollback, and evidence required to ship. 3. **Product** — user value, usability, scope discipline, and compatibility. 4. **Security** — trust boundaries, permissions, data exposure, and abuse cases. 5. **Dissent** — the strongest evidence-backed case against the emerging consensus.
Give every lens the same decision statement, constraints, evidence, and explicit unknowns. Do not show one lens another lens's conclusion before it answers.
Lens response
Verdict: support | support-with-conditions | oppose | insufficient-evidence Confidence: low | medium | high Key evidence: - ... Risks or objections: - ... Required conditions: - ... Unknowns: - ...
Preserve minority opinions. A dissenting finding is not deleted merely because most lenses agree.
Synthesis
Decision: proceed | proceed-with-conditions | revise | stop | gather-evidence Consensus: <where the lenses agree> Dissent: <minority positions, attributed by lens> Conditions: <concrete prerequisites> Evidence gaps: <unknowns that could change the decision> Next action: <one bounded next step>
Explain how conflicts were resolved. If evidence is insufficient, say so rather than manufacturing consensus. End after assessment unless mutation was explicitly authorized.
Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated worktrees, and reviews code before you see it.
Repo: automagik-dev/genie
Other skills on genie.
- /architecture
Use when reviewing architecture in any codebase — module boundaries, stated design contracts, abstraction depth, error-handling design. Assess by default, apply changes on request; complexity is dependencies plus obscurity, and deep modules win.
Open skill - /brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
Open skill - /code-quality
Use when auditing code quality in any codebase — discover and run the repo's real gates (typecheck, lint, dead-code, complexity), judge type discipline and duplication. Assess by default, apply changes on request; the compiler is the first reviewer.
Open skill - /docs
Dispatch docs subagent to audit, generate, and validate documentation against the codebase.
Open skill - /dream
Batch-execute SHIP-ready wishes overnight — pick wishes, orchestrate workers, review PRs, wake up to results.
Open skill - /dx-docs
Use when auditing DX, docs, and delivery in any codebase — the 30-minute-contributor test, docs-vs-reality drift, onboarding friction, error-message quality. Assess by default, fix docs on request; docs are judged by use, and every failure is a misfiled or missing Diátaxis
Open skill

