Is doncheli-spec-score-11b2ac safe to install?

SaferSkills independently audited doncheli-spec-score-11b2ac (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

.agent/skills/doncheli-spec-score/SKILL.md · 1 file

.agent/skills/doncheli-spec-score/SKILL.md1.9 KB · Markdown

name: doncheli-spec-score

description: Evaluate the quality of a spec and return a structured score with improvement recommendations. Activate when user mentions "spec quality", "score spec", "how good is my spec", "spec review", "validate spec quality".

Don Cheli: Spec Score

Instructions

Accept a spec file path or read the current spec from .dc/specs/
Evaluate the spec across 5 dimensions (0–10 each):

Completeness: all scenarios covered, no missing edge cases
Clarity: unambiguous language, no "should", "may", "probably"
Testability: each scenario has a verifiable, binary outcome
Consistency: no contradictions between scenarios or with existing specs
Scope control: no out-of-scope behavior mixed in, single responsibility

For each dimension below 7, provide 2–3 specific improvement suggestions with line references
Compute a weighted total score (Completeness 30%, Clarity 25%, Testability 25%, Consistency 10%, Scope 10%)
Assign a grade: A (90-100), B (75-89), C (60-74), D (below 60)
Grade D specs must be improved before implementation — flag as a hard blocker
Optionally save the score card to .dc/spec-scores/<spec-name>-<date>.md

Output Format

## Spec Score — checkout.feature — 2026-03-28

### Scores
| Dimension     | Score | Weight | Weighted |
|--------------|-------|--------|---------|
| Completeness  |   8   |  30%   |   2.4   |
| Clarity       |   6   |  25%   |   1.5   |
| Testability   |   9   |  25%   |   2.25  |
| Consistency   |   7   |  10%   |   0.7   |
| Scope Control |   8   |  10%   |   0.8   |
| **Total**     |       |        | **7.65**|

### Grade: B

### Improvement Suggestions

**Clarity (score: 6)**
- Line 14: "the system should respond quickly" — define SLA (e.g., "within 200ms")
- Line 28: "valid payment method" — list accepted types explicitly

### Verdict
Spec is implementation-ready with minor clarity fixes recommended.

doncheli-spec-score-11b2ac— agent skill

Is doncheli-spec-score-11b2ac safe to install?

Don Cheli: Spec Score

Instructions

Output Format

Audit the pieces. Scan the whole. Decide.