Common Business RequirementsSAFE
A collection of Agent Skills Standard and Best Practice for Programming Languages, Frameworks that help our AI Agent follow best practies on frameworks and programming laguages
Overview
A collection of Agent Skills Standard and Best Practice for Programming Languages, Frameworks that help our AI Agent follow best practies on frameworks and programming laguages
6f5be687a268OBSERVED · 2026-10-14What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: common-business-requirements
description: Standardize BRD and BRD-lite discovery for business goals, stakeholder impact, current-to-future state, and measurable value outcomes. Use when creating BRD, business case, project justification, ROI narrative, or AS-IS to TO-BE scope.
metadata:
triggers:
files:
- "BRD.md"
- "docs/brd/brd-*.md"
- "specs/*.md"
keywords:
- create brd
- business requirements
- business case
- stakeholder impact
- as-is to to-be
- roi justification
---
# Business Requirements Expert
## **Priority: P0 (CRITICAL)**
Frame the business "Why" before product or technical specs.
## 1. Discovery Workflow
- Draft executive summary: purpose, outcome, sponsor, validation owner.
- For vague "implement X" requests, draft BRD-lite first from supplied evidence; ask at most 3 consequential blocking questions with recommended defaults per `common-decision-discipline`. Never re-ask settled decisions.
- Confirm business objective and success metric.
- Identify sponsor, decision-maker, and impacted stakeholders.
- Capture AS-IS process pain and TO-BE target state.
- Define scope boundary, exclusions, assumptions, and constraints. Carry confirmed evidence and explicit non-critical assumptions; blocking unknowns name affected slice, consequence, owner, and required input—no unowned TBD at handoff.
- Record value hypothesis: cost, revenue, risk, compliance, or cycle-time impact.
- **Handoff Quality**: Identify the **Handoff Owner** (BA Lead) and the next accountable team member (Product Manager).
- Add glossary terms when stakeholder or domain language can be misread.
- Add Mermaid AS-IS/TO-BE process diagram when workflow complexity affects approval.
## 2. BRD-lite Drafting
- Load `references/brd-template.md`.
- Keep each objective SMART: specific, measurable, achievable, relevant, and time-bound.
- Link each BRD objective to a candidate PRD requirement placeholder (`REQ-*`).
- **Offshore Ready**: Include stakeholder validation plan and acceptance window for remote delivery teams.
- Add outcome report seed: `feature_status`, `requirement_trace`, completed/missing evidence, decision needed, and recommended next workflow (`plan-feature`).
- Write to `docs/brd/brd-[slug].md`.
## 3. Quality Gate
- Every objective has an owner and KPI target.
- Every in-scope item has a rationale and out-of-scope pair.
- Risk register includes mitigation owner.
- Stakeholder approvals and unresolved decisions are explicit; consequential unknowns block only affected slices.
- Functional behavior is routed to PRD/SRS, not buried in BRD.
- Sufficiently specified low-risk ticket maintenance may proceed with an in-chat contract without mandatory BRD document detours, provided it carries an accountable owner, approved scope fence, value rationale, and verification target.
## Anti-Patterns
- No solution design in a Why-lane BRD; Direction-lane briefs record technical options per `common-decision-discipline`.
- No vague goals ("improve efficiency") without baseline and target.
- No missing owners for objectives or risks.
- No coding or QA routing before the accountable owner, value rationale/metric, and scope fence are clear (formal document artifacts may be omitted only with approved low-risk ticket equivalence).
- No silent scope expansion after approval.
- No jargon without glossary entry.
## References
- [BRD Template](references/brd-template.md)
- [BRD Checklist](references/checklist.md)
- [Requirements Baseline](references/standards-baseline.md)Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
6f5be687a268full audit observations/trust-audit/skill/hoangnguyen0403__common-business-requirements.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-14 | 6f5be687a268 | SAFE | B | 89 | first audit |
Questions
What does the Common Business Requirements skill do?
A collection of Agent Skills Standard and Best Practice for Programming Languages, Frameworks that help our AI Agent follow best practies on frameworks and programming laguages
Is Common Business Requirements safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Common Business Requirements access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (6f5be687a268), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.