speckit-checklist

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

1.33x

Quality

47%

Does it follow best practices?

Impact

95%

1.33x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill provides an exceptionally detailed and actionable workflow for generating requirements-quality checklists, with clear sequencing, concrete examples, and well-defined validation steps. However, it is severely over-verbose — the core concept of 'testing requirements not implementation' is hammered home through redundant examples, anti-examples, and restatements that could be condensed by 50-60%. The content would benefit greatly from splitting examples and reference material into separate bundle files.

Suggestions

Consolidate the repeated 'unit tests for requirements' concept explanation — state it once with one good/bad example pair, then remove the redundant Anti-Examples section, the repeated ❌/✅ comparisons, and the 'Key Differences' block at the end.

Move the 'Example Checklist Types & Sample Items' section (UX, API, Performance, Security examples) into a separate reference file like `examples.md` and link to it, reducing the main skill by ~40 lines.

Merge the 'ABSOLUTELY PROHIBITED' and 'REQUIRED PATTERNS' lists with the earlier 'NOT for verification/testing' and 'FOR requirements quality validation' lists — these say the same thing in different formats.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~300+ lines. The core concept ('unit tests for requirements') is repeated and re-explained at least 5-6 times with overlapping examples, anti-examples, and restatements. The prohibited/required patterns sections, example checklist types, and anti-examples all redundantly reinforce the same point. Claude would understand this concept from a single clear explanation with one example set.	1 / 3
Actionability	Highly actionable with concrete execution steps (shell commands, file paths, naming conventions), specific item formatting patterns (CHK### IDs, bracket tags), executable examples for multiple domains, and clear algorithmic procedures for question generation and content consolidation. The workflow is copy-paste ready.	3 / 3
Workflow Clarity	The 7-step workflow is clearly sequenced with explicit pre-execution checks, clarifying questions with defaults, context loading strategy, generation rules, and post-execution hooks. Validation is embedded (pre/post hook checks, prerequisite script, content consolidation caps). The feedback loop for clarifying questions (Q1-Q3 with optional Q4-Q5 escalation) is well-defined.	3 / 3
Progressive Disclosure	References external files appropriately (extensions.yml, templates, spec/plan/tasks), but the SKILL.md itself is monolithic — the extensive examples, anti-examples, and repeated concept explanations should be split into separate reference files. No bundle files are provided to offload content, and the inline content is far too long for a single skill file.	2 / 3
	Total	9 / 12 Passed

Description

32%

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 is too brief and lacks explicit trigger guidance ('Use when...'), making it hard for Claude to know when to select this skill over others. While 'checklist' provides some specificity, the description doesn't clarify the type of checklist, the context (e.g., QA, code review, deployment), or the expected output format. It needs both more concrete capability details and explicit usage triggers.

Suggestions

Add a 'Use when...' clause with trigger terms like 'checklist', 'QA review', 'feature validation', 'acceptance criteria', 'task list', or 'definition of done'.

Specify what kind of checklist is generated and in what context, e.g., 'Generates QA checklists, acceptance criteria, and review task lists for software features based on requirements and specifications.'

Clarify the output format and scope, e.g., whether it produces markdown checklists, covers testing scenarios, or integrates with specific workflows.

Dimension	Reasoning	Score
Specificity	Names the domain (checklist generation) and one action (generate a custom checklist), but lacks detail on what kind of checklist, what format, or what specific steps are involved beyond 'based on user requirements.'	2 / 3
Completeness	Describes what it does (generate a custom checklist) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric should cap completeness at 2, and the 'what' is also quite thin, bringing this to a 1.	1 / 3
Trigger Term Quality	Includes 'checklist' and 'feature' as relevant keywords, but misses common variations users might say like 'QA checklist', 'review checklist', 'task list', 'acceptance criteria', or 'definition of done.'	2 / 3
Distinctiveness Conflict Risk	'Checklist' is somewhat specific, but 'current feature' and 'user requirements' are vague enough that this could overlap with project management, QA, or general planning skills.	2 / 3
	Total	7 / 12 Passed

Validation

81%

Warnings & errors only

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

Validation — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: mixpanel/mixpanel-headless
Commit: fd7b9ba

Reviewed: 27 days ago

Table of Contents

Discovery Implementation Validation

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.