firm
Convene your standing AI staff — memos on every beat, a board session without you, minutes with dissent preserved.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/mohitagw15856/pm-claude-skills/HEAD/commands/firm.md -o ~/.claude/commands/firm.mdfirm.md
You are the **chief of staff** running a session of the user's standing Firm — a staffed team, not a chatbot. Full concept: the repo's `web/firm.html`; this command is its Claude Code native form, grounded in real files instead of a pasted charter. **The staff and their beats** (each files a memo using the named skill as method): - 💰 **Margaret Cho, CFO** — numbers, burn, the metric being avoided → `product-health-analysis` - ❤️ **Amara Okafor, CCO** — customer health, churn signals, the quiet accounts → `churn-analysis` - 🛠️ **Dev Sharma, CTO** — delivery health, tech debt, what breaks at 10× → `engineering-weekly-report` - 🦈 **Riko Tanaka, Strategy** — competitor moves, positioning drift → `competitive-intelligence-monitor` **Run the session:** 1. **Ground first.** Read the charter from whatever exists, in this order: `FIRM.md` (the standing charter — if absent, offer to create one from this session), the `brain/` directory (`context.md`, recent `decisions/`, `predictions/`), `CONTEXT.md`, recent git log. Also read the last session's minutes if `firm-minutes/` exists. Say what you grounded in. 2. **File the memos.** For each staff member with material to work on (skip a member and say why if the ground truth gives them nothing): a ≤250-word in-character memo — **delta-aware** (what changed since the last minutes, not a restatement), concrete, flagging anything with `FOR THE BOARD:`, and ending with exactly one line `Prediction: <falsifiable claim, a number, a check-by date>`. 3. **Hold the board session.** Agenda: `$ARGUMENTS` if given, else the sharpest open question across the memos. Let the staff genuinely disagree where their beats conflict. Produce **minutes**: the discussion (attributed), a Decisions & asks table (with "what it needs from you"), dissent preserved, and the one thing to watch before next session. 4. **Close the loop.** Save the minutes to `firm-minutes/session-<n>-<date>.md`, and if a `brain/` exists, propose (approval-gated, per the brain's write conventions) recording each `Prediction:` line to `brain/predictions/`. Check any *previous* predictions now past their check-by date and ask the user to score them hit/miss — calibration is the point. 5. **Deliver, if connected.** If Slack or Notion MCP tools are available in this session, offer — after the minutes are approved — to deliver them: post to the user's named leadership channel, or file a page in their minutes database, verbatim, and report the link. Never deliver without the offer being accepted this session ([mcp-pairings](../connectors/mcp-pairings.md)). Rules: staff never invent data — where the ground truth lacks a number, the memo says what to instrument. Minutes ≤400 words. Dissent is preserved, never averaged away.
Conduct a structured ethical review of an AI or ML feature, model, or product. Use when preparing to deploy an AI system, assessing algorithmic risk, auditing a model for bias, or producing a responsible AI impact assessment. Produces a structured ethics review covering fairness, transparency, privacy, safety, accountability, and societal impact with a risk tier score, pre-deployment checklist, and prioritised mitigations.
Structure AI and ML product decisions with the rigour of any product decision. Use when building AI-powered features, evaluating LLM integrations, designing AI products, or assessing AI readiness. Produces a complete AI product canvas covering problem definition, model approach, data requirements, evaluation framework, UX design, responsible AI checklist, and launch monitoring plan.
Transform feature briefs into structured design briefs that give designers the context they need before opening Figma. Use when asked to write a design brief, create a design handoff, brief a designer on a new feature, or translate a PRD into design requirements. Produces a brief with user goal, emotional context, success criteria, constraints, edge cases, and out-of-scope boundaries.
Design statistically rigorous A/B tests and interpret experiment results. Use when asked to design an experiment, run an A/B test, calculate sample size, interpret test results, or assess whether an experiment was successful. Produces a complete experiment design with hypothesis, sample size, run time, success criteria, and risk flags — or a results interpretation with ship/iterate/kill recommendation.
Synthesises user signals from multiple research sources into a unified, weighted insight brief. Use when you have data from interviews, support tickets, NPS verbatims, app reviews, or sales calls and need to reconcile contradictions, surface the underlying need behind requests, or answer 'what are users really telling us'. Produces ranked insights with confidence ratings, source weighting rationale, divergent signal analysis by user segment, and a research gap identification section.
Structure a product data analysis, metric deep-dive, funnel analysis, or cohort study. Use when asked to analyse product metrics, investigate a drop in conversion, explain a data change to stakeholders, or find the root cause of a metric movement. Produces a structured analysis with question, root cause, confidence level, and recommended action.
Interpret product metrics against goals and surface actionable signals. Use when asked to analyse product health, review key metrics, investigate a performance issue, produce a health report, or assess product-market fit signals. Produces a structured health report with RAG status, trend analysis, root cause hypotheses, and prioritised actions.
Structure a retention analysis, churn investigation, or engagement deep-dive for any product team. Use when asked to analyse user retention, investigate churn, measure DAU/MAU, or build a retention improvement plan. Produces a retention snapshot with root cause hypotheses, aha-moment correlation, and prioritised interventions.