CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

spec-authoring

Use when writing a new requirement, defining a new feature, or when asked to implement behavior that has no requirement in specs/. Produces an EARS requirement with an FDD-style feature name, anchor Gherkin scenarios, and a stable REQ ID. Also use when an existing requirement must change.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

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 highly actionable, well-sequenced instruction skill with concrete commands, exact templates, and a real verification checklist. The only improvements are trimming a few narrative asides and splitting the specialized oracle-mode guidance into a separate reference file. Both judges scored identically strong.

DimensionReasoningScore

Conciseness

The body is dense and prescriptive with essentially no explanation of concepts Claude already knows, and project-specific conventions (ID scheme, EARS table, modes A/B) earn their tokens. A few narrative passages — the '~118 merge sites' anecdote and the aside about agents letting specs and tests diverge — could be trimmed, matching the efficient-with-minor-trimming anchor rather than the every-token-earns-its-place anchor.

4 / 5

Actionability

Guidance is fully concrete and executable: copy-paste commands ('ls specs/ | cut -d- -f2 | sort -u', "rg 'REQ-<ID>' --type rust specs/ src/ tests/"), an exact FDD naming template with worked examples, a complete EARS pattern table, and explicit file-naming rules. Specific examples cover the common cases, matching the top anchor for an instruction-only skill.

5 / 5

Workflow Clarity

The authoring flow is clearly sequenced (numbered sections 1–6) with an explicit 'Done means' checklist, a concrete ID-collision verification command, a human-review checkpoint before implementation, and recovery rules ('If the change invalidates an anchor scenario, rewrite it — do not delete it without replacement'). Section 6 gives a clean 4-step sequence for modifying existing requirements. This matches the anchor for explicit validation steps and checklists.

5 / 5

Progressive Disclosure

The body is well-sectioned with clear headers and one-level references to project artifacts (templates/requirement.md) and sibling skills (golden-parity, verification-ratchet), with no nested reference chains. However, at ~167 lines with no bundle files, the sizable oracle-mode section (4a) is specialized port/rewrite guidance that could live in its own reference file — good structure with a minor organization gap rather than an ideal split.

4 / 5

Total

18

/

20

Passed

Description

88%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 strong description with explicit trigger guidance and a concrete, multi-part statement of outputs. Its only weaknesses are a slightly broad 'defining a new feature' trigger and missing common synonyms like 'spec' or 'specification'.

DimensionReasoningScore

Specificity

The description lists multiple concrete outputs — 'Produces an EARS requirement with an FDD-style feature name, anchor Gherkin scenarios, and a stable REQ ID' — giving comprehensive, specific coverage of what the skill produces. It matches the anchor for multiple specific concrete actions with comprehensive coverage, not merely naming the domain.

5 / 5

Completeness

It explicitly answers both questions: 'Use when writing a new requirement, defining a new feature, or when asked to implement behavior that has no requirement in specs/' gives concrete triggers, and the production sentence states exactly what it does. This clearly matches the anchor for explicit what AND when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases like 'writing a new requirement', 'defining a new feature', and 'an existing requirement must change' are what users would actually say. A few natural synonyms are missing (e.g., 'spec', 'specification', 'user story'), so it falls just short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The requirement/spec-authoring niche is clear and largely distinct, but 'defining a new feature' is a fairly broad trigger that could also fire for general feature-implementation requests, creating minor overlap risk with closely related skills. It is more distinct than anchor 3 but does not fully meet the minimal-conflict anchor 5.

4 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

igouss/gitweb-rs

Path

.claude/skills/spec-authoring/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.