CtrlK
BlogDocsLog inGet started
Tessl Logo

write-a-spec

Turn an approved story (issues/NNN-*.md) plus an optional research dump into a technical spec sidecar at issues/NNN-*.spec.md — data model, API, file-by-file change list per lane (as fenced ```paths blocks), behavior-list of tests required, and risks. The spec drives /feature's lane allowlist; lane H3 headings must match labels from CLAUDE.md ## Lane boundaries. Sidecar only — does not modify source files. Use when the user wants to write a technical brief from a story or issue, or whenever /feature dispatches the Spec Writer phase. Triggers: /write-a-spec, "write a spec", "technical spec", "spec from this issue", "draft a technical brief".

75

Quality

94%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A thorough, highly actionable spec-writing skill with clear workflow validation, a verbatim template, and concrete self-check commands. Main weaknesses are repetition of the lane-matching rule and no use of bundle files to slim the long body.

Suggestions

Consolidate the lane-matching rule (case-sensitive, character-for-character, copy from CLAUDE.md verbatim) into one canonical statement under 'Paths block convention' and reference it from Lane discovery, the worked example, and Hard rules instead of restating it four times.

Move the detailed 'Paths block convention' and worked example into a references/ file (e.g. PATHS_FORMAT.md) to slim SKILL.md toward an overview, keeping only the headline rule and the self-check commands inline.

DimensionReasoningScore

Conciseness

Information-dense about a fragile parser protocol with no basic-concept padding, but the lane-matching rule (character-for-character, case-sensitive) is restated across Lane discovery, Paths block convention, the worked example, and Hard rules, and could be consolidated.

4 / 5

Actionability

Provides a copy-paste-ready verbatim template, a concrete worked example, executable self-check commands (grep -c, grep '^### ', awk, test -e), and an exact output path and closing one-liner — fully executable guidance.

5 / 5

Workflow Clarity

An eight-step Process with an explicit Stop-check validation gate and a self-critique feedback loop, plus executable self-check commands; the skill is non-destructive (sidecar only, single Write) so the batch/destructive cap does not apply.

5 / 5

Progressive Disclosure

Well-organized into clear sections with one-level-deep external references (feature-factory.md, ADR 0001, CONTEXT.md) signaled as source-of-truth, but no content is split into bundle files and the ~200-line body could offload the Paths-block convention to a reference.

4 / 5

Total

18

/

20

Passed

Description

100%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.

A highly specific, well-triggered description that clearly answers both what and when with concrete trigger phrases in third-person voice. Verbosity is the only minor weakness, but no description dimension directly penalizes it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — data model, API, file-by-file change list per lane, behavior-list of tests required, and risks — matching the score-5 anchor for comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what (produce a spec sidecar at issues/NNN-*.spec.md with named sections) and when ('Use when the user wants to write a technical brief... or whenever /feature dispatches the Spec Writer phase').

5 / 5

Trigger Term Quality

An explicit 'Triggers:' line with natural phrases ('write a spec', 'technical spec', 'spec from this issue', 'draft a technical brief') plus a 'Use when...' clause gives comprehensive keyword coverage including synonyms.

5 / 5

Distinctiveness Conflict Risk

Clear niche (spec sidecar generation) with distinct triggers and an explicit boundary ('Sidecar only — does not modify source files'), giving minimal conflict risk with neighboring skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository
belchman/claude-skills
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.