clear-cove-task-design

Use when orchestration or planning agents are producing task plans, task prompts, or TASK.md instructions that must be unambiguous, verifiable, and resistant to hallucination. Applies CLEAR (Concise, Logical, Explicit, Adaptive, Reflective) to structure and write agent task prompts, then adds CoVe (Chain of Verification) checks where accuracy risk is meaningful. Activates on draft task prompts, swarm plans, migration tasks, and multi-step plans requiring independently executable steps.

Quality

80%

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

Quality

Content

77%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.

A highly actionable, well-sequenced instruction skill with strong validation feedback loops, especially for destructive migration tasks. Its main weaknesses are length/repetition and the lack of progressive disclosure via referenced bundle files.

Suggestions

Move the detailed migration [E] criteria (lines 205-248) into a references/MIGRATION.md file and signal it from SKILL.md with a one-line pointer, reducing the main body and improving progressive_disclosure.

Consolidate the overlapping guidance between "When to Use This Skill", "The Combined Model", and "Your Output Responsibilities When Invoked" to trim repetition and raise conciseness.

Cut filler lines such as "Treat every task prompt as carrying operational consequences." and the restated "CLEAR improves the prompt itself. CoVe improves correctness of claims produced during execution." since the framework already conveys this.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with terse bullets and no over-explanation of basics, but the 274-line body has some repetition ("When to Use" vs "Your Output Responsibilities") and a heavy migration section that could be tightened; not a 4 because the padding is noticeable rather than minor.	3 / 5
Actionability	Fully actionable: a copy-paste task prompt template plus concrete executable examples ("uv run plugins/development-harness/scripts/verify_migration_fidelity.py", "grep -h \"^status:\" real_data/*.md \| sort -u", "assert set(source_sections) == set(...)") covering the common migration case.	5 / 5
Workflow Clarity	Clear sequenced operations (CLEAR ordering, CoVe draft→verify→revise), explicit validation checkpoints, a linting checklist, and a deletion gate conditioned on zero-data-loss; the destructive-operation cap does not apply because validation is explicitly present.	5 / 5
Progressive Disclosure	Good section headers structure the file, but with no bundle files and a 274-line monolith, content that could live in a separate reference (the detailed migration criteria) is inlined and there are no one-level-deep reference signals.	3 / 5
	Total	16 / 20 Passed

Description

83%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.

A strong, specific description that clearly states both capability and activation triggers using natural task-design vocabulary. It is slightly technical in voice and has minor overlap with general planning skills, but is well above average.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ("structure and write agent task prompts", "adds CoVe (Chain of Verification) checks"), with only minor coverage gaps; not a 5 because the actions all serve one workflow rather than a comprehensive action set.	4 / 5
Completeness	Explicitly answers both what ("Applies CLEAR... to structure and write agent task prompts, then adds CoVe checks") and when ("Use when... Activates on draft task prompts, swarm plans, migration tasks") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage ("task plans, task prompts, TASK.md instructions", "draft task prompts, swarm plans, migration tasks, and multi-step plans"), though the phrasing leans technical ("orchestration or planning agents") and a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	The CLEAR+CoVe task-design niche is mostly distinct with specialized triggers, but "multi-step plans" and general planning language create minor overlap risk with broad planning skills.	4 / 5
	Total	17 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Jamie-BitFlight/claude_skills
Path: plugins/development-harness/skills/clear-cove-task-design/SKILL.md
Commit: 4e1e73b

Reviewed: ~13 hours 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.