battle-test
Deep audit of a skills directory against the Skill Creator standard. Produces a scored report and phased remediation plan.
Evidence-led blue incident triage with authorization and runtime gates.
$ npx -y skills add hoangnguyen0403/agent-skills-standard --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/cyber-triageContext preview
What this command does when you run it.
Evidence-led blue incident triage with authorization and runtime gates.
Evidence-led blue incident triage with authorization and runtime gates.
**Input:** $ARGUMENTS
Optional args: slug=<feature>, ticket=<id/url>, mode=interactive|autonomous|channel, channel=<id>, auto_continue=true|false, profile=business|hybrid|technical.
Execute the following steps for **$ARGUMENTS**.
Use `cyber-incident-triage` with `cyber-authorization`, `cyber-evidence`, and `cyber-framework-mapping`. Offline synthetic analysis is allowed. Active collection, isolation, deletion, credential use, network changes, or production modification require documented scope, approved operation, accountable owner, and runtime-proven controls. Independent approval is required for containment. Markdown does not enforce permissions.
Return an evidence record containing engagement/scope reference, skill/version/source, observation time, finding status (`confirmed`, `suspected`, `blocked`, `not-tested`, `false-positive`), evidence references, limitations, and accountable owner. Preserve originals and custody details. Keep suspected, blocked, and not-tested findings visible. Carry `feature_status`, `completed_evidence`, `missing_evidence`, `decision_needed`, `recommended_next_workflow`, engagement owner and canonical artifact path.
1. Capture intake and claim without treating it as fact. 2. Preserve and reference original/volatile evidence before alteration. 3. Assess hypothesis, impact, urgency, and lifecycle separately; map framework edges with explicit source and review status. 4. Recommend containment only after authorization, runtime, and independent-approval checks; otherwise mark blocked and continue safe offline analysis. 5. Produce `artifacts/security-review.md` as the canonical finding artifact when a security review is requested; include blockers, warnings, evidence gaps, runtime contract, and handoff notes.
Before active operations: Is scope current and specific? Which required runtime controls are enforced? Who owns evidence custody and independently approves containment? Missing prerequisites block operations, not offline review.
Route completed evidence to `verify-work`; route missing requirements or design contracts to `implementation-readiness`/`design-solution`. Main records final verification in the SRS walkthrough.
# Incident Triage ## Intake and Hypotheses ## Evidence, Status and Limitations ## Authorization and Runtime Gates ## Recommended Approved Action ## Outcome Report feature_status: implemented | partially_implemented | blocked completed_evidence: [] missing_evidence: [] decision_needed: [] recommended_next_workflow: verify-work
The portable SDLC standards layer for AI coding agents. Sync once, then work in your own runtime.
Repo: hoangnguyen0403/agent-skills-standard
Deep audit of a skills directory against the Skill Creator standard. Produces a scored report and phased remediation plan.
Clarify a rough product or engineering idea into a BRD-lite brief (Why) with measurable business value.
Run an AI-assisted PR code review using multi-layer lenses with confidence scoring.
Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system…
Run a bounded cybersecurity exercise workflow with authorization, runtime, control, evidence, and independent adjudication gates; supports safe offline…
Controlled purple validation using paired action-observation evidence and explicit defensive outcomes.