CtrlK
BlogDocsLog inGet started
Tessl Logo

speckit-checklist

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

65

1.33x
Quality

50%

Does it follow best practices?

Impact

95%

1.33x

Average score across 3 eval scenarios

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/speckit-checklist/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 highly actionable with concrete commands and rich examples, but it is notably redundant — re-explaining its central concept four times — and its file-writing workflow lacks an explicit post-generation validation step. Progressive disclosure is middling because all content lives in one long, though well-sectioned, file with no reference bundle.

Suggestions

Consolidate the repeated 'test requirements not implementation' explanations into a single canonical section and cross-reference it instead of restating wrong/correct examples in four places.

Add an explicit validation checkpoint after Step 5 (e.g., re-open the generated checklist and confirm IDs are contiguous and ≥80% of items carry a traceability reference) with a fix-and-retry loop, to lift workflow clarity above 3.

Move the long examples-by-dimension and example-checklist-type catalogs into a reference file (e.g., references/item-examples.md) and link to it, improving progressive disclosure.

DimensionReasoningScore

Conciseness

The core 'test requirements, not implementation' concept is explained four times (opening 'Checklist Purpose', Step 5 wrong/correct examples, the 'Example Checklist Types' section, and the 'Anti-Examples' section) with overlapping wrong/correct item lists, making it noticeably verbose with several padded, redundant sections; it is not a 3 because the redundancy is substantial rather than a few trimmable instances.

2 / 5

Actionability

It gives concrete executable commands (`.specify/scripts/bash/check-prerequisites.sh --json`), specific file paths, ID formatting rules (CHK001), and many concrete sample items; it is not a 5 because the core generation is instruction-driven rather than copy-paste code, but guidance is largely executable with only minor gaps.

4 / 5

Workflow Clarity

Execution Steps 1-7 are clearly numbered with a precondition check in Step 1, but the file-writing operation (Step 5 creates/appends checklist files) has no post-write validation or error-recovery feedback loop, so per the destructive/batch-operations cap workflow clarity cannot exceed 3; the sequence alone would warrant higher but the missing validation checkpoint holds it down.

3 / 5

Progressive Disclosure

There are no bundle files (no references/, scripts/, or assets/ directories) and the skill is a single ~360-line file with good ## section headers, but large blocks that could be split out (examples by dimension, hook output templates, anti-examples) are inlined; this fits 'some structure but content that should be separate is inline' rather than the well-split 4 or the minimal-structure 2.

3 / 5

Total

12

/

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 clearly states what the skill does but omits any 'when to use it' trigger guidance, which caps completeness. It is competent but undifferentiated, scoring uniformly at the midpoint across all dimensions.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when generating a requirements-quality checklist for a feature, or when the user asks to validate spec/plan completeness, clarity, or coverage.'

List a few concrete checklist domains (e.g., UX, API, security, performance) to raise specificity and trigger-term coverage.

Tie the skill more tightly to its spec-kit context in the description itself to reduce overlap with generic checklist skills.

DimensionReasoningScore

Specificity

Names the domain ('checklist for the current feature') and one concrete action ('Generate a custom checklist ... based on user requirements'), matching the 'names domain and 1-2 concrete actions but not comprehensive' anchor; it does not list several specific actions, so it is not a 4.

3 / 5

Completeness

The 'what' is clear ('Generate a custom checklist for the current feature based on user requirements') but there is no 'Use when...' clause or equivalent trigger guidance, so per the missing-trigger cap completeness cannot exceed 3; it is not a 2 because the 'what' is explicit rather than vague.

3 / 5

Trigger Term Quality

It contains relevant natural terms a user might say ('checklist', 'feature', 'requirements') but offers limited coverage with no synonyms or variations, fitting 'some relevant keywords but missing common variations or synonyms' rather than the broader coverage of a 4.

3 / 5

Distinctiveness Conflict Risk

'Generate a custom checklist for the current feature' is somewhat specific (tied to a feature/spec-kit context) but 'checklist' is generic enough to overlap with general todo/checklist skills, matching 'somewhat specific but could still overlap with similar skills' rather than the mostly-distinct 4.

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.

Validation14 / 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
mixpanel/mixpanel-headless
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.