command-capture

Automatically capture reusable task patterns as command candidates after completing coding work. This skill identifies multi-step workflows that could benefit other developers across projects and logs them to command-candidates.yaml for potential automation. Use this proactively when completing tasks that represent common, repeatable patterns worth standardizing as commands.

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/command-capture/SKILL.md

Quality

Content

46%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 skill is highly actionable with a clear schema and examples, but it is severely over-long and monolithic, inlining material that belongs in separate reference files and lacking validation steps in its workflow.

Suggestions

Move the ten worked examples and the full YAML schema into a separate references/EXAMPLES.md, keeping only one representative example and the field table inline in SKILL.md.

Trim repetitive sections (Benefits, Important Guidelines, Future Use, Integration) that restate the same points, and remove the duplicated schema block at the end.

Add a validation checkpoint to the workflow (e.g., verify the appended entry is valid YAML and not a duplicate of an existing candidate) before considering the log complete.

Dimension	Reasoning	Score
Conciseness	The 600+ line body inlines ten full worked-example YAML blocks plus repeated schema, benefits, and 'MANDATORY' emphasis sections that pad without adding new guidance, fitting 'noticeably verbose' below the midpoint.	2 / 5
Actionability	Provides a concrete, copy-paste-ready YAML schema with explicit field definitions and complete example entries covering common cases, with only minor gaps keeping it below 5.	4 / 5
Workflow Clarity	Steps 1–5 are clearly sequenced, but the file-append workflow has no validation checkpoint (e.g., YAML well-formedness, duplicate detection), so the batch-operation validation gap caps it at 3.	3 / 5
Progressive Disclosure	Despite section headers, the ten full examples and complete schema are bulk content inlined into a single 600+ line file with zero external references, matching the 'content that clearly belongs in separate files is inlined' anchor.	2 / 5
	Total	11 / 20 Passed

Description

67%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 and when to use it, with concrete actions and a distinct niche. Its main weakness is trigger phrasing built on conditions rather than the natural language a user would say.

Suggestions

Rewrite the 'Use when...' clause around natural user requests (e.g., 'Use after setting up testing, adding an API endpoint, or configuring CI') rather than abstract conditions.

Add concrete trigger keywords users actually say (e.g., 'set up Jest', 'create REST endpoint', 'CI/CD pipeline') to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions—'capture reusable task patterns as command candidates', 'identifies multi-step workflows', 'logs them to command-candidates.yaml'—with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the comprehensive 5.	4 / 5
Completeness	Both 'what' (logs reusable patterns to command-candidates.yaml) and 'when' ('Use this proactively when completing tasks...') are present, but the 'when' could be more explicit with concrete trigger phrases, so it sits above 3 but below 5.	4 / 5
Trigger Term Quality	Trigger guidance is condition-based ('when completing tasks that represent common, repeatable patterns') rather than natural user phrases; relevant keywords exist but common variations a user would actually say are missing, matching the 3 anchor.	3 / 5
Distinctiveness Conflict Risk	The command-candidates.yaml / Packmind-recipe niche is clearly distinct from sibling capture skills with only minor overlap risk, fitting 'mostly distinct' rather than the fully niche-specific 5.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (614 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: cteyton/packmind
Path: .claude/skills/command-capture/SKILL.md
Commit: e198635

Reviewed: 5 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.