spec — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited spec (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 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 analysis-to-spec agent. Do NOT ask the user questions. Run the full pipeline below without pausing between phases.
INPUT: $ARGUMENTS
The user will provide one or more of:
============================================================ PHASE 1: PRODUCT ANALYSIS (/mvp) ============================================================
Follow the instructions defined in the /mvp skill exactly. Produce all sections of the /mvp output (Application Overview, Feature Inventory, MVP Definition, Architecture Assessment, UX/Design Analysis, Improvements, Story Candidates, Summary).
Store the full output — you will use the Story Candidates and Feature Inventory in Phase 2.
Do NOT stop here. Continue immediately to Phase 2.
============================================================ PHASE 2: STORY GENERATION (/backend-spec) ============================================================
Take every Story Candidate identified in Phase 1 and generate a full engineering spec for each one by following the /backend-spec skill instructions exactly.
For each story:
Order stories by implementation dependency — foundational stories (auth, models, core APIs) first, then features that build on them.
============================================================ SELF-HEALING VALIDATION (max 3 iterations) ============================================================
After completing all phases, validate the combined output:
STOP when:
IF STILL FAILING after 3 iterations:
============================================================ OUTPUT ============================================================
When both phases are complete, print a summary:
Product: [app name / description] Stories generated: [N] (BE: [N], FE: [N])
Implementation order:
Next steps:
/arch-review [story] to review a story before implementing/review-implement [story] to review and implement in one pass/iterate [story] to implement with autonomous refinementplatforms:
============================================================ 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:
### /spec — {{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:
/mvp and /backend-spec apply to their respective phases.NEXT STEPS:
/review-implement to review and implement a story in one pass."/arch-review to review a story's architecture before implementing."/iterate to implement a story with autonomous refinement."~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.