<< All versions
Skill v1.0.0
currentAutomated scan100/100rafmacalaba/armada/armada-gate
──Details
PublishedNovember 4, 2026 at 04:23 PM
Content Hashsha256:97fa72c2ab26b6ad...
Git SHA8b974bf92e9b
──Files
Files (1 file, 1.8 KB)
SKILL.md1.8 KBactive
SKILL.md · 45 lines · 1.8 KB
name: armada-gate description: Run an evidence-gate checklist for each success criterion in the current phase. Use when checking if a phase is complete before marking it passed. metadata: version: "1.0.0"
You are gating an armada phase. Verify every success criterion in the current phase with evidence.
Process
- Read the current phase in
armada/REQUIREMENTS.md. Note its success criteria. - For each criterion, gather evidence:
- If it involves a test run: run the test command and capture output.
- If it involves a visual check: capture a screenshot.
- If it involves file presence or content: verify on disk.
- For each criterion, report one of: PASS (with evidence path), FAIL (with reason), SKIP (with reason).
- If all criteria pass, the phase gates. Report "PHASE PASS" and update the phase status.
- If any criterion fails, report "PHASE FAIL" with the failing criteria and reasons. Do not proceed.
Evidence format
Phase: <N> -- <name>Criteria:[PASS] <criterion> -- evidence: <path or output snippet>[FAIL] <criterion> -- reason: ...[SKIP] <criterion> -- reason: ...Result: PASS | FAIL
Adaptive depth
- QA always gates. Low risk uses focused smoke and acceptance; medium uses affected tests and
integration smoke; high uses full relevant and negative-path evidence.
- Activate security, adversary, or architect only when risk or changed surface requires them.
- Group findings by root cause, files, or threat class before remediation. Only
BLOCKINGstops
phase; defer unrelated pre-existing findings with rationale.
Rules
- Never skip a criterion without a documented reason.
- Evidence paths must be relative to the repo root.
- Screenshots go in
armada/screenshots/<feature>/. - Test output goes in the gate report. Keep it terse.