Council
Run a structured multi-persona deliberation so one builder hears architect, skeptic, strategist, and advocate angles before committing to a technical or product decision.
Overview
Council is a journey-wide agent skill that classifies your question and convenes ordered expert personas—usable whenever a solo builder needs multi-angle debate before committing to design, strategy, or risk calls.
Install
npx skills add https://github.com/gupsammy/claudest --skill councilWhat is this skill?
- Keyword-driven question classification into architecture, strategy, risk, UX, and innovation buckets
- Fixed persona roster: Architect, Skeptic, Pragmatist, Strategist, Advocate, Innovator with per-type priority order
- Council sizes: quick (2), standard (4), full (6) personas with Advocate included by default
- Defaults to General/Mixed when intent is ambiguous instead of forcing a wrong specialty lane
- Designed for agent sessions that simulate a leadership council rather than a single generic assistant voice
- 6 named personas in the roster
- 5 primary question-type lanes plus General/Mixed default
- 3 council sizes: quick=2, standard=4, full=6
Adoption & trust: 1 installs on skills.sh; 253 GitHub stars; 2/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You are about to make a consequential product or technical choice but only get one generic assistant opinion with no structured skepticism or advocacy for users.
Who is it for?
Indie builders deciding architecture, roadmap bets, risk posture, UX friction, or unconventional approaches who want deliberate role-played perspectives in one session.
Skip if: Pure execution tasks with an already-approved spec, or situations where you need live data pulls and tool execution instead of deliberation.
When should I use this skill?
The user faces an ambiguous architecture, strategy, risk, UX, or innovation decision and needs ordered multi-persona debate rather than a single generic answer.
What do I get? / Deliverables
You receive a council-shaped answer with personas matched to your question type and council size, so tradeoffs are visible before you implement or pivot.
- Question type classification
- Ordered persona council response with competing viewpoints
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Debate long-term positioning and competitive bets with Strategist and Skeptic ahead of writing a PRD.
Stress-test MVP scope and downside scenarios before greenlighting the build.
Compare module boundaries and coupling with Architect and Pragmatist before merging a large refactor.
Run a risk-assessment council on exposure, compliance, and failure modes pre-launch.
Challenge go-to-market narrative with Advocate and Strategist before paid campaigns.
How it compares
Use instead of a single-pass chat opinion when you want repeatable persona ordering—not a code generator or automated security scanner.
Common Questions / FAQ
Who is council for?
Solo and indie builders using Claude-style agents who want architect, skeptic, and strategist voices on hard decisions without hiring a formal committee.
When should I use council?
At idea/research for strategy and architecture framing; at validate/scope for risk and positioning; at build/integrations for API and module boundaries; at ship/security for failure modes; at launch/distribution for competitive bets—whenever tradeoffs deserve multiple stances.
Is council safe to install?
Council is deliberation guidance; check the Security Audits panel on this Prism page and avoid piping secrets into multi-persona transcripts you do not want logged.
SKILL.md
READMESKILL.md - Council
# Question Classification Map the user's question to a type, then select personas in the listed priority order. Take the top N based on council size (quick=2, standard=4, full=6). Advocate is always included unless explicitly excluded. ## Classification Rules Match by keywords and intent. If multiple types match, pick the one that best captures the user's primary concern. Default to General/Mixed when ambiguous. ## Question Types ### Architecture / Design **Keywords:** structure, dependency, coupling, module, interface, boundary, schema, API design, refactor, separation of concerns, pattern **Persona order:** Architect, Skeptic, Pragmatist, Strategist, Advocate, Innovator ### Strategy / Direction **Keywords:** direction, roadmap, priority, invest, bet, focus, positioning, competitive, growth, vision, long-term **Persona order:** Strategist, Skeptic, Innovator, Advocate, Architect, Pragmatist ### Risk Assessment **Keywords:** risk, failure, security, vulnerability, what could go wrong, downside, exposure, compliance, audit, incident **Persona order:** Skeptic, Architect, Strategist, Pragmatist, Advocate, Innovator ### UX / Developer Experience **Keywords:** user experience, developer experience, onboarding, documentation, error message, workflow, friction, confusion, discoverability, accessibility **Persona order:** Advocate, Pragmatist, Innovator, Architect, Skeptic, Strategist ### Innovation / Alternatives **Keywords:** alternative, different approach, rethink, creative, novel, unconventional, what if, explore options, brainstorm approaches **Persona order:** Innovator, Architect, Skeptic, Strategist, Pragmatist, Advocate ### Planning / Sequencing **Keywords:** order, sequence, phase, milestone, timeline, deadline, dependency chain, rollout, migration, incremental, ship **Persona order:** Strategist, Pragmatist, Architect, Skeptic, Innovator, Advocate ### General / Mixed **Default type when no strong keyword signal.** **Persona order:** Architect, Skeptic, Pragmatist, Advocate, Strategist, Innovator ## Selection Algorithm 1. Classify the question into one type 2. Take the top N personas from that type's priority order 3. If Advocate is not in the top N, replace the last persona with Advocate (unless `--exclude advocate`) 4. Apply `--include` overrides: add named personas, bumping the list to N+extras 5. Apply `--exclude` overrides: remove named personas 6. Enforce minimum floor: if fewer than 2 personas remain, backfill from the next-ranked personas in the priority order until the council has 2 # Council Output Format Three templates based on council size. Use the matching template for the number of perspectives dispatched. --- ## Quick Format (2 perspectives) ``` ## Council Verdict [1-3 sentence opinionated verdict] **Question type:** [classified type] **Council:** [Persona 1], [Persona 2] **Confidence:** [H/M/L] ### Agreement [Points where both perspectives align] ### Disagreement [Points where they diverge, with your resolution] ### Next Step [Single most important action] ``` --- ## Standard Format (3-4 perspectives) ``` ## Council Verdict [1-3 sentence opinionated verdict] **Question type:** [classified type] **Council:** [Persona 1], [Persona 2], [Persona 3], [Persona 4] ### Consensus [Findings where majority agrees — state as conclusions, not attributions] ### Key Tensions [Each tension named, framed, and either resolved or presented as a tradeoff] ### Blind Spots [What no agent addressed — flagged as open questions] ### Confidence Map | Conclusion | Confidence | Basis | |-----------|------------|-------| | [conclusion] | H/M/L | [why] | ### Next Steps 1. **[do now]** — [specific action] 2. **[do soon]** — [specific action] 3. **[do later]** — [specific action] ``` --- ## Full Format (5-6 perspectives) Use the Standard Format above, plus append individual perspective summaries in collapsible sections: ``` ### Individual Perspectives <details> <summary>[Persona Name] — [one-line po