doncheli-spec-score skill

by doncheli·doncheli/don-cheli-sdd·57 stars·Apache-2.0

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".

A100/100content scan

Is the doncheli-spec-score skill safe?

Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.

No findings.

Install the doncheli-spec-score skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.

git clone --depth 1 https://github.com/doncheli/don-cheli-sdd.git /tmp/don-cheli-sdd
mkdir -p ~/.claude/skills
cp -r /tmp/don-cheli-sdd/.opencode/skills/doncheli-spec-score ~/.claude/skills/doncheli-spec-score

available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

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/-.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.

More skills from doncheli/don-cheli-sdd

Adoncheli-api-contractDesign complete API contracts covering endpoints, auth, rate limiting, error handling, retries, circuit breaker and idempotency. Activate when user mentions "api contract", "api design", "endpoint", "webhook", "REST", "GraphQL", "OpenAPI", "design the API".
Adoncheli-api-contractDesign complete API contracts covering endpoints, auth, rate limiting, error handling, retries, circuit breaker and idempotency. Activate when user mentions "api contract", "api design", "endpoint", "webhook", "REST", "GraphQL", "OpenAPI", "design the API".
Adoncheli-audit-trailRecord and query the decision log for a project. Activate when user mentions "audit", "trail", "log decisions", "decision history", "why was this decided", "ADR", "architecture decision".
Adoncheli-audit-trailRecord and query the decision log for a project. Activate when user mentions "audit", "trail", "log decisions", "decision history", "why was this decided", "ADR", "architecture decision".
Adoncheli-changelogAuto-generate CHANGELOG.md entries from git commit history. Activate when user mentions "changelog", "release notes", "what changed", "generate changelog", "CHANGELOG", "release history".
Adoncheli-changelogAuto-generate CHANGELOG.md entries from git commit history. Activate when user mentions "changelog", "release notes", "what changed", "generate changelog", "CHANGELOG", "release history".
Adoncheli-context-healthReport the current state of the context window and recommend compression or cleanup actions. Activate when user mentions "context health", "context window", "how much context", "context full", "running out of context", "compress context".
Adoncheli-context-healthReport the current state of the context window and recommend compression or cleanup actions. Activate when user mentions "context health", "context window", "how much context", "context full", "running out of context", "compress context".
Adoncheli-data-policyAudit and document what personal or sensitive data the project collects, processes, and stores. Activate when user mentions "privacy", "data policy", "what data", "GDPR", "personal data", "data retention", "PII".
Adoncheli-data-policyAudit and document what personal or sensitive data the project collects, processes, and stores. Activate when user mentions "privacy", "data policy", "what data", "GDPR", "personal data", "data retention", "PII".
Adoncheli-debateRun an adversarial multi-role debate to surface trade-offs and reach a reasoned decision. Activate when user mentions "debate", "discuss", "trade-off", "decision", "compare options", "pros and cons", "choose between".
Adoncheli-debateRun an adversarial multi-role debate to surface trade-offs and reach a reasoned decision. Activate when user mentions "debate", "discuss", "trade-off", "decision", "compare options", "pros and cons", "choose between".

All agent skills → · MCP servers