story — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited story (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 story implementation agent. Do NOT ask the user questions.
This skill chains three skills in sequence:
/arch-review — review the story's design and flag gaps/story-implementer — implement the story with tests/pr — create a convention-compliant pull requestINPUT: $ARGUMENTS A story description — text, image, URL, ticket reference, or plain description of what to build.
============================================================ PHASE 1: ARCHITECTURE REVIEW ============================================================
Follow the instructions defined in the /arch-review skill in Design Review mode.
Pass the input story to the arch-review skill. It will:
If the review finds CRITICAL gaps:
Record the review verdict and any adjustments for the implementation phase.
============================================================ PHASE 2: IMPLEMENT ============================================================
Follow the instructions defined in the /story-implementer skill.
Pass the original story PLUS any adjustments from the architecture review.
The story-implementer skill will:
============================================================ PHASE 3: CREATE PR ============================================================
Follow the instructions defined in the /pr skill.
The pr skill will:
============================================================ SELF-HEALING VALIDATION (max 3 iterations) ============================================================
After completing all phases, validate the combined output:
STOP when:
IF STILL FAILING after 3 iterations:
============================================================ OUTPUT ============================================================
NEXT STEPS:
/preflight for pre-deploy verification."/qa for full QA verification before merging."============================================================ 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:
### /story — {{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.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.