skills/canhta/deliverable/business-requirements

business-requirements

Installation
SKILL.md

Business Requirements (BRD)

Draft business requirements through structured interview and research. Works section by section with your approval at every step. Pushes back on vague answers. Spawns bounded sub-agents for competitive research and feasibility checks.

Announce at start: "I'm using the business-requirements skill to draft a BRD through structured phases with approval gates."

When to use

  • "write a BRD", "business requirements", "spec this feature", "requirements for X"
  • After project-charter skill completes (if charter was done)

Phases

flowchart TD
    P1[Intake] --> P2[Discovery Research]
    P2 --> P3[Problem & Users]
    P3 --> P4[Scope & Metrics]
    P4 --> P5[Risks & Assumptions]
    P5 --> P6[BRD Sign-off]
    P6 --> P7[Dual-voice BRD Review]
    P7 --> DONE[Done → suggest SRS]

Intake

Five questions, one at a time:

  1. Project name and slug (skip if charter exists)
  2. Presetgreenfield / feature / internal / auto
  3. Extras — product-facingprd-lite / exec-onepager / none
  4. Extras — engineering-facingrfc / acceptance-tests / none
  5. Extras — cross-cuttingrisks-register / planning-handoff / roadmap / none

Auto-bump signals: If user mentions PII, payment data, PHI, regulated industry — note in state.md for technical-requirements skill.

Discovery Research

Propose sub-agents from sub-agents/:

  • competitor-scan — max 5 candidates, public info (~2 min, ~3k tokens)
  • feasibility-check — library maturity, licensing (~2 min, ~2k tokens)
  • prior-art — existing solutions, patterns (~2 min, ~2k tokens)

User approves which to run. Parallel dispatch OK. Raw → cache, distilled → docs/requirements/research/.

Problem & Users

Interview using roles/sponsor.md, roles/pm.md, roles/designer.md. Draft:

  • BRD §Problem — evidence-backed, not hand-wavy
  • BRD §Users — target personas, JTBD framing

Scope & Metrics

Interview using roles/pm.md, roles/tech-lead.md, roles/designer.md, roles/qa.md. Draft:

  • BRD §Scope — explicit in/out boundaries
  • BRD §Success metrics — measurable, time-bound

Risks & Assumptions

Interview using roles/pm.md, roles/tech-lead.md, roles/security-legal.md*. Draft:

  • BRD §Assumptions — each tagged [ASSUMPTION]
  • BRD §Risks — top risks only

*security-legal loaded if auto-bump signals detected

BRD Sign-off

Present full BRD. List all [ASSUMPTION] and [OPEN] items. Ask for sign-off.

Dual-voice BRD Review

Dispatch sub-agents/dual-voice-reviewer.md for independent second opinion on scope and success metrics. Present findings. User decides what to address.

Preset Weighting

Section greenfield feature internal
§market-sizing required skip skip
§competitive-landscape required optional skip
§pricing-viability required optional skip
§target-user required required "adopter persona"
§success-metric required (north-star) required required (adoption)

Skipped sections omitted entirely — no empty stubs.

Four-Beat Rhythm

Orient → Work → Present → Approve/Edit/Revise/Kill → Commit.

  • Max 3 questions per turn
  • One section per present
  • No silent writes
  • Rushed user? Offer batch mode

Interview Handoff

User can't answer? Suggest the stakeholder-interview skill to generate templates. Pause phase, resume when answers return.

Tone

  • Tight and direct. Push back on weak answers.
  • Numbers over adjectives. [ASSUMPTION] and [OPEN] tags everywhere.
  • Cross-link to decisions.md and open-questions.md, never duplicate.

Next step

"BRD complete. Ready for the technical spec? Say 'write technical requirements' to continue."

Weekly Installs
2
First Seen
6 days ago
Installed on
amp2
cline2
opencode2
cursor2
kimi-cli2
warp2