CtrlK
BlogDocsLog inGet started
Tessl Logo

speckit-checklist

Generate a custom checklist for the current feature based on user requirements.

51

Quality

56%

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-checklist/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 delivers highly concrete, executable guidance with a well-sequenced workflow and good degradation handling, but it is heavily padded — the central concept is repeated many times and the hook instructions appear twice verbatim. Consolidating the redundant explanation and moving examples/hook protocol into reference files would cut tokens substantially without losing clarity.

Suggestions

Explain the 'unit tests for requirements, not implementation' distinction once (ideally in the Purpose section) and cut the repeated restatements in Core Principle, How to Write, Prohibited/Required Patterns, Anti-Examples, and Example Checklist Types.

Extract the near-identical Pre- and Post-Execution hook protocol into a single parameterized section or a reference file (e.g. references/hooks.md), replacing both duplicated blocks.

Move the per-domain example catalogs (ux.md, api.md, performance.md, security.md samples) into a reference file such as references/examples.md, keeping only one compact illustration inline in SKILL.md.

DimensionReasoningScore

Conciseness

The core "test the requirements, not the implementation" concept is restated across roughly six sections (Purpose, Core Principle, How to Write, Prohibited/Required Patterns, Anti-Examples, Example Types), and the extension-hook protocol is duplicated nearly verbatim in both Pre- and Post-Execution Checks — several clearly padded, redundant sections.

2 / 5

Actionability

Guidance is fully executable: exact commands (".specify/scripts/powershell/check-prerequisites.ps1 -Json"), file paths, filename format, CHK ID continuation rules, exact hook output templates, and dozens of copy-paste-ready example checklist items covering the common cases.

5 / 5

Workflow Clarity

Execution Steps 1–7 are clearly sequenced with conditional fallbacks (invalid extensions.yml → skip silently; template unavailable → inline fallback; existing file → append-only continuation), but there is no post-generation validation loop, e.g. verifying the stated ≥80% traceability target was actually met before reporting.

4 / 5

Progressive Disclosure

The document is a 360-line monolith with no reference files at all; the per-domain example catalogs and the duplicated hook protocol clearly belong in separate bundled files, though the section headers do keep it navigable.

3 / 5

Total

14

/

20

Passed

Description

50%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 states a single clear action but omits when to invoke the skill and what kind of checklist it produces (requirements-quality validation). It reads as generic checklist generation and would rarely trigger on its own. Adding a 'Use when...' clause with concrete trigger phrases would address the main gaps.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for a checklist, wants to review spec/requirements quality, or needs to validate a feature's requirements before implementation."

State the checklist's actual purpose — validating the quality/completeness/clarity of written requirements — so the 'what' is not just 'generate a checklist'.

Include natural trigger synonyms such as "spec review", "requirements quality", and "checklist for this feature" to improve keyword coverage and distinctiveness.

DimensionReasoningScore

Specificity

Names one concrete action ("Generate a custom checklist") and a domain ("the current feature based on user requirements"), but the checklist's actual purpose — validating requirements quality — is left unstated, so coverage is not comprehensive.

3 / 5

Completeness

The 'what' is stated (generate a custom checklist) but the 'when' is entirely absent — there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

"checklist", "feature", and "requirements" are natural terms, but there is no trigger phrasing and no variations or synonyms (e.g., "review my spec", "requirements quality"), matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"Generate a custom checklist" could plausibly match many checklist, code-review, or QA-oriented skills; the spec-kit domain context helps but the wording alone is only somewhat distinct.

3 / 5

Total

12

/

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
unoplatform/uno
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.