CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sdd-spec-enforcer

Triggered when managing, creating or validating feature specifications (specs) in spec-*.md

Quality

76%

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 ./plugins/sdd-workflow/skills/sdd-spec-enforcer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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 lean, well-structured instruction-only skill whose template and naming rules are directly actionable. The main gap is the missing validation workflow: the skill claims to cover validating existing specs but provides no checklist or verification steps, and several template fields lack defined formats or allowed values.

Suggestions

Add a short "Validating an existing spec" section with an explicit checklist (naming format matches, file in /specs or /docs/specs, all required template sections present, required metadata fields filled).

Specify the expected format/values for underspecified template fields, e.g., priority (P0-P3?), iteration (sprint number + deadline format?), and the ID scheme.

Clarify what to do when an existing spec deviates from the template (fix it in place, flag it, or leave it), so the enforcing behavior is unambiguous.

DimensionReasoningScore

Conciseness

The body (~45 lines) contains only the naming format, storage locations, and the mandatory template — no padding, no explanations of concepts Claude already knows. Every rule earns its place, matching the "lean and efficient" anchor.

5 / 5

Actionability

Concrete guidance throughout: an exact filename format with a worked example ("spec-machine-returns-01-abrir-chamado.md"), explicit locations ("/specs" or "/docs/specs"), and a copy-paste-ready template. Minor gaps keep it below 5: allowed values for fields like priority and iteration, and the ID format, are left unspecified.

4 / 5

Workflow Clarity

Rules are grouped logically (nomenclature, location, format) but there is no sequenced workflow and no validation procedure — despite the skill covering "validating" specs, no checklist or checkpoint tells Claude how to verify an existing spec conforms. This matches the anchor for sequence present but checkpoints missing or implicit; it is not level 2 because the rules themselves are unambiguous.

3 / 5

Progressive Disclosure

This is a single-file skill under 50 lines with well-organized sections and no content that warrants external reference files, which per the rubric's simple-skill guideline earns a 5 on well-organized sections alone.

5 / 5

Total

17

/

20

Passed

Description

61%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 has a clear, explicit trigger with good file-pattern keywords, but it reads as a pure trigger clause: it never states what the skill actually does (enforce a mandatory spec template, naming convention, and location rules). Adding a one-line statement of the skill's function would lift both completeness and specificity.

Suggestions

Lead with a 'what' clause stating the skill's function, e.g., "Enforces naming conventions, storage location, and a mandatory Markdown template for feature specs. Use when managing, creating, or validating spec-*.md files."

Name the concrete actions the skill performs (e.g., "apply the mandatory spec template", "check existing specs against the required format") instead of the generic "managing".

Include a couple of natural user phrasings (e.g., "writing a spec", "spec template") to broaden trigger coverage.

DimensionReasoningScore

Specificity

"managing, creating or validating feature specifications" names the domain with a few concrete verbs, but "managing" is generic and the skill's real capability (enforcing a mandatory spec template/format) is never stated. This matches the anchor for naming a domain with 1-2 concrete actions without comprehensive coverage — not level 4, which requires several specific actions, and not level 2, which would lack named actions.

3 / 5

Completeness

The "when" is explicit ("Triggered when managing, creating or validating feature specifications... in spec-*.md"), but the "what" is only weakly implied through the verbs — the description never says what the skill does with those specs (enforce naming/location/template rules). It sits between anchor 2 (only 'when' present without 'what') and anchor 4 (both explicit), scoring above 2 because the verbs gesture at the what.

3 / 5

Trigger Term Quality

"feature specifications (specs) in spec-*.md" covers the full term, its common abbreviation, and the concrete file pattern, giving good keyword coverage. A few natural phrases users might say (e.g., "writing specs", "requirements", "spec template") are missing, so it falls short of level 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The trigger is tied to a distinct artifact ("spec-*.md" feature specification files), making it mostly distinct with only minor overlap risk against generic documentation- or spec-writing skills. Not level 5 because "managing... specifications" could still collide with broader spec/documentation workflows.

4 / 5

Total

14

/

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

JoseMD12/testing-tessl

Path

plugins/sdd-workflow/skills/sdd-spec-enforcer/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.