CtrlK
BlogDocsLog inGet started
Tessl Logo

speckit-specify

Create or update the feature specification from a natural language feature description.

52

Quality

58%

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/skills/speckit-specify/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%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 a strong, highly actionable workflow with excellent validation and feedback loops, but it pays for that with real verbosity: duplicated hook-handling instructions, remedial markdown formatting guidance, and long inline templates that belong in reference files. Deduplicating and moving templates to references would raise both conciseness and progressive disclosure without losing actionability.

Suggestions

Replace the duplicated hook procedure in step 9 with a one-line reference to the Pre-Execution Checks section (parameterized only by the hooks key: before_specify vs after_specify), cutting ~25 lines.

Move the requirements checklist template and the clarification-question format into separate reference files (e.g., references/checklist-template.md, references/clarify-format.md) and link to them from the workflow.

Delete the markdown table formatting instructions (pipe spacing, dash counts, 'test in markdown preview') — Claude already knows how to format tables.

DimensionReasoningScore

Conciseness

The entire extension-hook procedure (enabled filtering, condition handling, dot-to-hyphen conversion, optional/mandatory output templates) is duplicated nearly verbatim between the Pre-Execution Checks section and step 9 (~30 redundant lines), and it spends lines teaching markdown basics Claude already knows ("Use consistent spacing with pipes aligned", "Header separator must have at least 3 dashes", "Test that the table renders correctly in markdown preview"). This matches the 'noticeably verbose; several unnecessary explanations or padded sections' anchor. Not a 3 because the duplication and remedial formatting instruction are substantial, not incidental.

2 / 5

Actionability

Guidance is highly concrete and executable: exact paths (.specify/extensions.yml, .specify/templates/spec-template.md, .specify/feature.json), a resolution-order algorithm for the feature directory, a literal JSON payload with an anti-pattern warning, copy-paste hook output templates, and worked examples of good/bad success criteria. Not a 5 because a few operations are described rather than given as commands (e.g., copying the spec template, scanning specs/ for the next sequential number).

4 / 5

Workflow Clarity

A clearly sequenced 9-step flow with an explicit validation checkpoint (step 7: build a quality checklist, review pass/fail, re-run validation with a max-3-iteration loop and documented escalation), question-numbering rules, and explicit error exits ("No feature description provided"). This matches the top anchor: explicit validation steps, feedback loops for error recovery, and a checklist for a complex process.

5 / 5

Progressive Disclosure

Section headers are sensible, but this is a monolithic 300+ line document with no reference files: the 35-line requirements checklist template, the clarification-question template, and both hook output templates are inlined where separate reference files would serve. This fits 'some structure but could be better organized; content that should be separate is inline'. Not a 2 because the document is genuinely well-sectioned, not an unstructured or buried-reference wall.

3 / 5

Total

14

/

20

Passed

Description

53%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 states a clear, specific 'what' in third person but entirely omits when the skill should be used, and its trigger vocabulary is narrow (no 'spec', 'requirements', or 'Use when' phrasing). This limits both completeness and discoverability. Adding an explicit 'Use when...' clause with natural trigger terms would lift most dimensions.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to create, write, or update a feature spec or specification from a feature description or feature request.'

Include natural synonyms and trigger terms users would actually say — 'spec', 'write a spec', 'requirements', 'feature request' — alongside 'feature specification'.

Optionally broaden the 'what' slightly to mention validation/checklist generation, so the description covers more of the command's concrete actions.

DimensionReasoningScore

Specificity

The description names the domain and 1-2 concrete actions ("Create or update the feature specification") but offers no broader coverage of what the command actually does (validation, checklists, branch handling), matching the '1-2 concrete actions, not comprehensive' anchor. It is not a 4 because it does not list several specific actions, and not a 2 because the action named is concrete rather than generic.

3 / 5

Completeness

It has a clear 'what' but no 'when' clause whatsoever, which caps completeness at 3 per the judging guidelines. Not a 4 because there is no 'Use when...' or equivalent trigger guidance, explicit or weakly implied.

3 / 5

Trigger Term Quality

"feature specification" and "natural language feature description" are relevant keywords, but common natural variations users would say ("spec", "write a spec", "requirements", "feature request") are missing. It is not a 4 because keyword coverage is thin, and not a 2 because the terms present are on-domain rather than generic filler.

3 / 5

Distinctiveness Conflict Risk

"Create or update the feature specification from a natural language feature description" carves a fairly clear niche (spec-kit feature specs) with only minor overlap risk against generic requirements- or document-writing skills. Not a 5 because without trigger phrases its activation boundary is less crisply distinct than the top anchor.

4 / 5

Total

13

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
unoplatform/uno
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.