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

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/speckit-checklist/SKILL.md

Quality

Discovery

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 vague to effectively guide skill selection. It identifies a single action (generating a checklist) but lacks specificity about what kind of checklist, what context it applies to, and critically omits any explicit trigger guidance for when Claude should select this skill. The description would benefit significantly from concrete details and a 'Use when...' clause.

Suggestions

Add an explicit 'Use when...' clause with trigger terms like 'checklist', 'review list', 'acceptance criteria', 'QA tasks', 'feature validation'.

Specify what kind of checklist is generated (e.g., QA checklist, code review checklist, acceptance criteria) and what inputs it uses (e.g., user stories, feature specs, PRDs).

Include natural keyword variations users might say, such as 'todo list', 'task list', 'pre-launch checklist', or 'definition of done'.

Dimension	Reasoning	Score
Specificity	It names a domain (checklist generation) and a single action (generate a custom checklist), but lacks detail about what the checklist contains, what format it takes, or what kinds of features/requirements are supported.	2 / 3
Completeness	It describes what (generate a checklist) but has no explicit 'Use when...' clause or trigger guidance. Per the rubric, a missing 'Use when' clause caps completeness at 2, and the 'what' itself is also weak, so this scores a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'checklist', 'feature', and 'requirements', but misses common variations users might say such as 'todo list', 'task list', 'acceptance criteria', 'QA checklist', or 'review checklist'.	2 / 3
Distinctiveness Conflict Risk	The mention of 'checklist' and 'feature' provides some specificity, but 'user requirements' is broad enough that it could overlap with skills related to requirements gathering, feature planning, or task management.	2 / 3
	Total	7 / 12 Passed

Implementation

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 extremely thorough 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 excessive repetition across examples, anti-examples, prohibited patterns, required patterns, and multiple restatements. The content would benefit enormously from being cut by 40-50% and splitting reference material into separate bundle files.

Suggestions

Reduce repetition of the 'test requirements, not implementation' concept — state it once clearly with one good/bad example pair, then remove the redundant anti-examples section, the repeated prohibited/required patterns, and the duplicative 'Key Differences' summary.

Extract the example checklist types (UX, API, Performance, Security) and the detailed anti-examples into a separate reference file (e.g., EXAMPLES.md) and link to it from the main skill.

Consolidate the 'HOW TO WRITE CHECKLIST ITEMS', 'ABSOLUTELY PROHIBITED', 'REQUIRED PATTERNS', and 'Anti-Examples' sections into a single concise reference table or decision matrix.

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 extensive anti-examples and examples. The prohibited/required patterns sections, anti-examples, and example checklist types all redundantly reinforce the same point. Claude would understand this concept after one clear explanation.	1 / 3
Actionability	The skill provides highly concrete, executable guidance: specific shell commands (check-prerequisites.sh --json), exact file paths, precise item formatting (CHK### pattern), detailed algorithms for question generation, and numerous copy-paste-ready example checklist items. The workflow steps are specific and actionable.	3 / 3
Workflow Clarity	The 7-step workflow is clearly sequenced with pre-execution hooks, execution steps (setup → clarify → understand → load → generate → structure → report), and post-execution hooks. Validation checkpoints include prerequisite checks, context loading strategy with gap detection, content consolidation with soft caps, and file existence checks for append vs. create behavior.	3 / 3
Progressive Disclosure	The skill references external files (extensions.yml, checklist-template.md, spec.md, plan.md, tasks.md) appropriately, but the SKILL.md itself is monolithic — the extensive examples, anti-examples, and repeated concept explanations could be split into referenced files. No bundle files are provided to offload this content, so everything is inlined in one massive document.	2 / 3
	Total	9 / 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: 3ce3191

Reviewed: 2 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.