CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

speckit-specify

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

56

Quality

71%

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

77%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 highly actionable, well-sequenced instruction set with genuine validation feedback loops — the workflow and actionability are exemplary for a command-style skill. Its weaknesses are structural and redundancy-related: a ~40-line hook protocol duplicated verbatim for the before and after cases, an inlined 35-line checklist template, and no reference files at all to keep the overview lean.

Suggestions

Factor the near-identical before_specify/after_specify hook-processing blocks into a single shared section or a references/hooks.md file, parameterized by the hook key.

Move the full specification quality checklist template out of SKILL.md into references/quality-checklist-template.md and reference it in one line, keeping the main body as an overview.

Trim over-explanations of things Claude already knows, such as the markdown table-formatting bullet points in step 7.4.

DimensionReasoningScore

Conciseness

Most content is task-specific instruction Claude cannot infer (resolution order, hook output formats), but the ~40-line extension-hook protocol is duplicated nearly verbatim for before_specify and after_specify, the 35-line checklist template is inlined wholesale, and sections like 'Ensure markdown tables are properly formatted... pipes aligned' over-explain what Claude already knows. This fits 'Mostly efficient but includes some unnecessary explanation or could be tightened' rather than 2, whose bar is several padded explanatory sections.

3 / 5

Actionability

Guidance is fully concrete and executable: exact paths (`.specify/extensions.yml`, `.specify/templates/spec-template.md`, `.specify/feature.json` with a copy-paste JSON snippet), copy-paste hook output blocks, an explicit SPECIFY_FEATURE_DIRECTORY resolution order, a ready-to-use checklist template, and worked examples (short-name derivation, good/bad success criteria). Not 4 because there are no meaningful gaps — the common cases are covered with specific, ready-to-use material.

5 / 5

Workflow Clarity

The 9-step flow is clearly sequenced with an explicit validation checkpoint (Specification Quality Validation), a feedback loop (update spec → re-run validation, max 3 iterations, warn user if still failing), a checklist for the complex process, and clarification question handling with a defined format and cap. This matches the top anchor: clear sequence, explicit validation steps, error-recovery loops, and checklists.

5 / 5

Progressive Disclosure

The body has good section structure and clear internal navigation, but it is a 347-line monolith with no bundle files at all: the duplicated hook protocol and the full checklist template clearly belong in reference files (e.g. references/hooks.md, references/quality-checklist.md). This fits 'Some structure but could be better organized; content that should be separate is inline'; not 4 because well over a hundred lines of reference material is inlined in SKILL.md.

3 / 5

Total

16

/

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 communicates a clear, specific 'what' in third person, but it omits any 'when to use' trigger guidance and lacks natural synonyms (spec, requirements) that users would actually type. It is serviceable but below the quality of the reference good examples, which all pair capabilities with an explicit 'Use when...' clause.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user describes a feature to spec out, asks for a feature spec, or wants to turn requirements into a specification.'

Include natural synonyms and variations users would say — 'spec', 'write a spec', 'feature requirements', 'spec-driven development' — to improve trigger matching.

Briefly mention the downstream handoff (readiness for /speckit.clarify or /speckit.plan) to distinguish this command from sibling spec-kit commands.

DimensionReasoningScore

Specificity

"Create or update the feature specification from a natural language feature description" names the domain (feature specification) and two concrete actions (create, update), but coverage is not comprehensive — it says nothing about validation, clarification handling, or directory setup. This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' rather than 4, which requires several specific actions.

3 / 5

Completeness

The 'what' is clear (create/update a feature specification from a natural language description), but there is no 'Use when...' clause or equivalent trigger guidance — the 'when' is entirely absent. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3; it is not 2 because the 'what' is specific, not vague.

3 / 5

Trigger Term Quality

Relevant keywords exist ("feature specification", "natural language feature description") but common variations users would naturally say are missing: "spec", "write a spec", "requirements", "spec-driven development". This fits 'Some relevant keywords but missing common variations or synonyms' rather than 4, which expects only a few natural terms missing.

3 / 5

Distinctiveness Conflict Risk

"Feature specification" carves out a fairly distinct niche (spec-driven development workflows), but the description overlaps with sibling spec-kit commands (clarify, plan, tasks) that a user could easily invoke by mistake. 'Mostly distinct; minor overlap risk with closely related skills' is the best fit; not 5 because no trigger phrases help disambiguate from those related skills.

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

g14wx/staffSync

Path

.claude/skills/speckit-specify/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.