launch-readiness — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited launch-readiness (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You are an autonomous launch readiness agent. Do NOT ask the user questions. Run the full pre-launch pipeline below. If any phase finds CRITICAL issues, STOP immediately and report before proceeding -- do not let critical problems cascade through later phases unaddressed.
TARGET: $ARGUMENTS
If arguments are provided, use them as context for the launch scope (e.g., "v2.0 launch", "beta release", specific feature area). If no arguments, evaluate full product launch readiness.
============================================================ PHASE 1: PRODUCT REVIEW (/cpo-review) ============================================================
Follow the instructions defined in the /cpo-review skill exactly.
Evaluate the product from a Chief Product Officer perspective:
Record the CPO verdict and all findings.
CRITICAL GATE: If the CPO review identifies any CRITICAL product gaps (e.g., core user flow is broken, value proposition is unclear, critical feature is missing), STOP and report. Do NOT proceed to later phases -- launching with a broken product wastes all downstream effort.
============================================================ PHASE 2: GROWTH AUDIT (/growth-audit) ============================================================
Follow the instructions defined in the /growth-audit skill exactly.
Evaluate growth readiness:
Record the growth readiness score and all findings.
CRITICAL GATE: If growth audit finds CRITICAL issues (e.g., no way to acquire users, activation flow is broken, zero retention infrastructure), STOP and report.
============================================================ PHASE 3: UX AUDIT (/ux) ============================================================
Follow the instructions defined in the /ux skill exactly, in UX Audit mode.
Evaluate every user-facing screen against:
Fix all issues found and commit the fixes. Record the UX verdict: UX READY, UX NEEDS WORK, or UX POOR.
CRITICAL GATE: If UX verdict is UX POOR, STOP and report.
============================================================ PHASE 4: SECURITY SCAN (/secure) ============================================================
Follow the instructions defined in the /secure skill exactly.
Run the full security audit:
Fix all issues found and commit the fixes.
CRITICAL GATE: If any CRITICAL security vulnerabilities are found that could not be fixed, STOP and report. Do NOT launch with known critical security issues.
============================================================ PHASE 5: DEPLOYMENT PREFLIGHT (/preflight) ============================================================
Follow the instructions defined in the /preflight skill exactly.
Run pre-deploy verification:
Record the preflight verdict: READY TO DEPLOY or NOT READY.
============================================================ SELF-HEALING VALIDATION (max 3 iterations) ============================================================
After completing all phases, validate the combined output:
STOP when:
IF STILL FAILING after 3 iterations:
============================================================ OUTPUT ============================================================
| Phase | Skill | Status | Critical | High | Medium | Verdict |
|---|---|---|---|---|---|---|
| 1 | /cpo-review | {PASS/FAIL} | {N} | {N} | {N} | {verdict} |
| 2 | /growth-audit | {PASS/FAIL} | {N} | {N} | {N} | {verdict} |
| 3 | /ux | {PASS/FAIL} | {N} | {N} | {N} | {UX verdict} |
| 4 | /secure | {PASS/FAIL} | {N} | {N} | {N} | {verdict} |
| 5 | /preflight | {PASS/FAIL} | {N} | {N} | {N} | {READY/NOT READY} |
LAUNCH VERDICT: {GO / NO-GO / CONDITIONAL GO}
addressed soon after launch. List the conditions.
Phase {N} ({skill name}) found CRITICAL issues. Pipeline halted.
Blockers that must be resolved before re-running:
| Phase | Fix | Files Changed |
|---|---|---|
| 3 | {UX fix description} | {files} |
| 4 | {security fix description} | {files} |
| # | Issue | Phase | Severity | Recommendation |
|---|---|---|---|---|
| 1 | {description} | {phase} | {HIGH/MEDIUM} | {action} |
============================================================
============================================================ SELF-EVOLUTION TELEMETRY ============================================================
After producing output, record execution metadata for the /evolve pipeline.
Check if a project memory directory exists:
~/.claude/projects/skill-telemetry.md in that memory directoryEntry format:
### /launch-readiness — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}Only log if the memory directory exists. Skip silently if not found. Keep entries concise — /evolve will parse these for skill improvement signals.
STRICT RULES ============================================================
"SKIPPED -- skill not available" status and continue to the next phase.
NEXT STEPS:
After GO:
/full-deploy to execute the deployment pipeline."After CONDITIONAL GO:
/iterate to address the high-severity items within 1 week."/customer-success-audit to ensure post-launch support infrastructure is ready."After NO-GO:
/launch-readiness."/iterate to address the critical issues."/polish for a thorough quality pass before retrying."~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.