AgentStack
SKILL verified Apache-2.0 Self-run

Doncheli Spec Score

skill-doncheli-don-cheli-sdd-doncheli-spec-score · by doncheli

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".

No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-doncheli-don-cheli-sdd-doncheli-spec-score

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Doncheli Spec Score? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Don Cheli: Spec Score

Instructions

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

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.