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 files, 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

82%

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

81%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 and workflow-clear, with a complete template, concrete commands, and explicit validation/feedback loops including a deletion gate for destructive migration work. Its main weakness is conciseness: the linting section duplicates the CLEAR criteria and the file could be trimmed.

Suggestions

Remove or compress the 'Linting Rules for Task Quality' section since it restates the C/L/E/A/R criteria already covered in 'CLEAR Guidelines for Task Prompts'; reference that section instead.

Tighten the 'When to Use This Skill' list and 'Your Output Responsibilities' sections, which overlap with the 'Combined Model' order-of-operations and the template's Handoff section.

Consider extracting the specialized 'Migration and Data Conversion Tasks' block into a references/ file linked from the body, which would improve progressive disclosure and shorten the main SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and uses tight bullets, but the 'Linting Rules for Task Quality' section restates the CLEAR C/L/E/A/R criteria already defined above and the file runs long, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the lean 4.	3 / 5
Actionability	Provides a copy-paste-ready Task Prompt Template plus concrete executable commands (the git add/commit block, 'verify_migration_fidelity.py', 'grep -h "^status:"', 'assert set(source_sections) == ...'), covering common cases fully, matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	Sequences the process explicitly ('Order of operations' 1-3, CoVe steps 1-5) with validation checkpoints and feedback loops ('If any item fails, revise the task prompt', the migration deletion gate conditioned on zero-data-loss), satisfying the 'clear sequence with explicit validation steps and feedback loops' anchor; the destructive-operation cap does not apply since verification is emphatically present.	5 / 5
Progressive Disclosure	No bundle files exist, so all content is inline, but it is well-organized under clear section headers with no nested references and reasonable placement of the specialized migration block; this fits 'good structure; most content appropriately placed' rather than a 3 (which requires buried/unclearly-signaled references) or a 5 (which requires well-signaled one-level external references that are absent here).	4 / 5
	Total	17 / 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.

The description is strong: it explicitly states what the skill does and when to use it, uses third-person voice, and packs in concrete trigger terms with minimal fluff. Its only weakness is that the named actions (applying frameworks) are slightly more abstract than a fully concrete verb inventory.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'structure and write agent task files', 'adds CoVe (Chain of Verification) checks', and applies the named CLEAR framework — with only minor abstraction gaps, matching the 'several specific actions' anchor rather than the fully concrete verb list of a 5.	4 / 5
Completeness	Explicitly answers both 'what' ('Applies CLEAR... to structure and write agent task files, then adds CoVe checks') and 'when' with concrete trigger clauses ('Use when orchestration or planning agents are producing...', 'Activates on draft task prompts, swarm plans, migration tasks...'), matching the anchor that clearly answers both with concrete triggers.	5 / 5
Trigger Term Quality	Covers natural terms the target audience would say — 'task plans', 'task prompts', 'TASK.md', 'swarm plans', 'migration tasks', 'multi-step plans' — giving good keyword coverage, though a few common synonyms are absent so it stops short of the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (CLEAR + CoVe for worker-agent task files) with distinct triggers like 'TASK.md' and 'swarm plans', but has minor overlap risk with general planning/orchestration skills, fitting 'mostly distinct; minor overlap risk' rather than the minimal-conflict 5.	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: c337daf

Reviewed: 3 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.