CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

spec-generator

Chain-loaded spec generation. 8-phase with quality gate loop and auto-fix.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/workflow-skills/spec-generator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly concise and provides executable commands, but its workflow clarity is capped at 3 because the 8-phase sequence, quality-gate validation, and auto-fix feedback loop are not spelled out in the body. Progressive disclosure is good but the single external reference is a bare, non-existent path.

Suggestions

Add an explicit validation/feedback loop in the body (e.g. 'After each phase, run the quality gate; on failure, auto-fix and re-run') so workflow clarity is not capped at 3.

Briefly explain what the 8 phases are or at least list them, rather than deferring entirely to a phases directory that is not bundled here.

Clarify how the listed variables (readiness_score, fix_iterations, goal, auto_yes) are set or used, and turn the phases reference into a clearly signaled link.

DimensionReasoningScore

Conciseness

The body is a lean overview of two commands plus terse pointers to phases and variables, assuming Claude's competence with no padding; every token earns its place, matching the anchor 5 example.

5 / 5

Actionability

Two copy-paste-ready `chain_loader` commands are concrete and executable, but "Variables: readiness_score, fix_iterations, goal, auto_yes" are listed without usage context and the phases path is a dangling pointer, leaving minor gaps below anchor 5.

4 / 5

Workflow Clarity

Only two run modes are sequenced (full run vs. resume from quality gate); the 8 phases, validation checkpoints, and the auto-fix feedback loop are not described in the body, so per the batch/feedback-loop cap workflow clarity cannot exceed 3.

3 / 5

Progressive Disclosure

The body is a thin overview that defers detail to a one-level-deep external reference ("Phases from `.claude/skills/spec-generator/phases/`") with content appropriately split; not a 5 because the reference is a bare path (no link) and the referenced directory does not exist.

4 / 5

Total

16

/

20

Passed

Description

48%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description conveys a clear what (spec generation with a quality-gate/auto-fix loop) but omits any explicit when-to-use guidance, capping completeness. Trigger terms lean technical with one relevant keyword and missing natural synonyms.

Suggestions

Add a 'Use when...' clause naming concrete trigger phrases, e.g. 'Use when the user asks to generate, write, or refine a spec'.

List a couple of concrete actions (e.g. 'generate specs, run quality gates, auto-fix failures') instead of describing process structure.

Include natural synonyms users would say (spec writing, create a specification) alongside 'spec generation'.

DimensionReasoningScore

Specificity

"Chain-loaded spec generation" names the domain with only a minimal concrete action; "8-phase with quality gate loop and auto-fix" are process/mechanism descriptors rather than distinct user-facing actions, so it sits below the midpoint between anchors 2 and 3.

2 / 5

Completeness

There is a clear "what" (chain-loaded spec generation with quality gate and auto-fix) but no "when" / "Use when..." clause, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

"spec generation" is a relevant keyword, but the rest ("chain-loaded", "8-phase", "quality gate loop") is technical jargon and natural user phrasings like "write a spec" or "create a specification" are missing, matching anchor 3's 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

"Chain-loaded spec generation" occupies a fairly distinct niche with a unique modifier, giving minor overlap risk; not a 5 because the absence of explicit trigger phrases leaves some residual conflict risk with related generation skills.

4 / 5

Total

12

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

catlog22/Claude-Code-Workflow

Path

.claude/workflow-skills/spec-generator/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.