CtrlK
BlogDocsLog inGet started
Tessl Logo

speckit-specify

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

54

Quality

61%

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

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 a thorough, well-sequenced spec-authoring workflow with strong validation feedback loops, but it is verbose (a repeated hook-checking block and basic markdown-formatting tips) and monolithic with no progressive disclosure into reference files. Actionability is high thanks to concrete paths, commands, and templates.

Suggestions

De-duplicate the extension-hook checking instructions: define them once and reference them from step 9 instead of repeating the full block.

Remove markdown-formatting basics ('test that the table renders correctly in markdown preview', pipe-alignment coaching) — Claude already knows markdown.

Extract the checklist template and hook output-format examples into reference files (e.g. references/checklist-template.md) linked one level deep from the body to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly efficient domain guidance, but it repeats the entire extension-hook checking block verbatim in both Pre-Execution Checks and step 9, and over-explains markdown basics ('Use consistent spacing with pipes aligned', 'Test that the table renders correctly in markdown preview'). It is above 2 because the core instruction set is useful and not pure padding, but below 4 due to these unnecessary explanations.

3 / 5

Actionability

It provides concrete file paths (.specify/extensions.yml, .specify/templates/spec-template.md), shell commands (mkdir -p), JSON payloads, and a full checklist template — mostly executable guidance. It stops short of 5 only because some steps still use placeholders ({extension}, {command}) rather than fully copy-paste-ready content.

4 / 5

Workflow Clarity

The Outline lays out a clear 1-9 sequence, and step 7 ('Specification Quality Validation') includes an explicit validate → fix → re-run loop with 'max 3 iterations', plus a generated checklist. This matches the score-5 anchor (clear sequence, explicit validation steps, feedback loops for error recovery, checklists).

5 / 5

Progressive Disclosure

The file is well-sectioned (User Input, Project Context Pre-Load, Pre-Execution Checks, Outline, Quick Guidelines) but is a single ~330-line document with no bundle files; large blocks like the checklist template and hook output formats are inlined rather than split into one-level-deep references. It is not a 4 because content that clearly belongs in separate files is kept inline, and not a 2 because section headers provide real structure.

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 clearly states what the skill does but omits any 'Use when' trigger guidance and lacks natural synonyms, capping completeness and trigger-term quality at 3. It is a competent, third-person statement that would benefit from explicit trigger phrases.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when the user asks to create or update a feature spec from a plain-language description.'

Include natural synonyms users actually say — 'spec', 'specify', 'write a feature spec' — alongside 'feature specification'.

List a couple more concrete actions (e.g. 'generate short name, set up spec directory, validate against quality checklist') to lift specificity toward 4-5.

DimensionReasoningScore

Specificity

Names the domain ('feature specification') and one concrete action pair ('Create or update') from 'a natural language feature description', but coverage is not comprehensive — it lists no other spec-related actions. This matches the score-3 anchor (domain + 1-2 concrete actions) and is below 4, which requires several specific actions.

3 / 5

Completeness

It clearly states the 'what' ('Create or update the feature specification from a natural language feature description') but provides no 'Use when...' clause or explicit trigger guidance, which per the judging guidelines caps completeness at 3. It is not a 2 because the 'what' is concrete rather than vague.

3 / 5

Trigger Term Quality

The phrases 'feature specification' and 'natural language feature description' are relevant but miss common synonyms and variations a user would naturally say ('spec', 'specify', 'write a spec'). It is above score 2 (only generic keywords) but lacks the breadth needed for a 4.

3 / 5

Distinctiveness Conflict Risk

Spec authoring from a natural-language description is a fairly clear niche with distinct triggers, though minor overlap risk exists with sibling speckit commands (plan, tasks, clarify). It is more distinct than the score-3 anchor but does not reach the minimal-conflict clarity of a 5.

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.

Validation14 / 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
g14wx/staffSync
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.