speckit-specify

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

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/speckit-specify/SKILL.md

Quality

Content

70%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 content is highly actionable with a clear, well-validated multi-step workflow including feedback loops, but it is verbose due to duplicated hook-handling sections and inlines template material that would benefit from separate reference files. Tightening repetition and externalizing reusable templates would improve conciseness and progressive disclosure.

Suggestions

De-duplicate the extension-hook handling: define the hook output format once and reference it from both Pre-Execution Checks and step 9 instead of repeating the full blocks verbatim.

Move the large reusable blocks (spec quality checklist template, hook output templates, success-criteria guidelines) into reference files under references/ and link to them, reducing SKILL.md length and improving progressive disclosure.

Consolidate the repeated NEEDS CLARIFICATION limit/priority rules into a single stated location to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient operational guidance with no padding about basic concepts, but it repeats substantial material verbatim (the extension-hook blocks appear nearly identically in Pre-Execution Checks and step 9, and NEEDS CLARIFICATION limits are restated several times), which could be tightened; this matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the leaner 4.	3 / 5
Actionability	It provides concrete executable guidance including exact file paths, mkdir commands, JSON snippets, output/checklist templates, and table-formatting specs; it stays at 4 rather than 5 because several steps use placeholder variables (e.g., 'mkdir -p SPECIFY_FEATURE_DIRECTORY') rather than fully copy-paste-ready commands.	4 / 5
Workflow Clarity	Steps 1-9 are clearly sequenced with explicit validation checkpoints and feedback loops (step 7: validate against a checklist, fix, re-run up to 3 iterations, plus NEEDS CLARIFICATION resolution loops), matching the anchor for a clear sequence with explicit validation steps and error-recovery feedback loops.	5 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and all content is inlined in a ~270-line SKILL.md; large reusable blocks (the checklist template, hook output templates, success-criteria guidelines) that would benefit from separate files are inlined, matching 'some structure but content that should be separate is inline' rather than the well-split 4 or 5.	3 / 5
	Total	15 / 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 is clear and domain-specific about creating or updating feature specifications, but it lacks an explicit 'when to use' trigger clause and natural-language trigger synonyms. Adding a 'Use when...' sentence with user-facing terms would lift completeness and trigger-term quality.

Suggestions

Add a 'Use when...' clause stating when to invoke this skill, e.g. 'Use when a user describes a feature to turn into a spec.'

Include natural trigger terms and synonyms users actually say (e.g., 'spec', 'requirements', 'feature request') to improve trigger-term quality.

Expand the action list slightly (e.g., 'Create, update, or scaffold a feature spec from a plain-language description') to move specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('feature specification') and two concrete actions ('Create or update'), matching the anchor for naming a domain with 1-2 concrete actions; it is not a comprehensive multi-action list so it is not a 4.	3 / 5
Completeness	It clearly states what the skill does but provides no 'Use when...' or equivalent trigger guidance; per the rubric, a missing explicit trigger clause caps completeness at 3, and it does not reach 4 which requires both what and when.	3 / 5
Trigger Term Quality	It includes relevant terms ('feature specification', 'natural language feature description') but lacks common synonyms users naturally say ('spec', 'requirements', 'write a spec'), matching the 'some relevant keywords but missing common variations' anchor rather than the fuller coverage of 4.	3 / 5
Distinctiveness Conflict Risk	'Feature specification' is a clear niche distinct from generic skills with only minor overlap risk against sibling spec-kit skills (plan/tasks/clarify); it is not a 5 because those closely related sibling commands create some overlap risk.	4 / 5
	Total	13 / 20 Passed

Validation

87%

Warnings & errors only

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

Criteria	Description	Result
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
Path: .claude/skills/speckit-specify/SKILL.md
Commit: eaa505e

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.