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

86%

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

85%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.

Highly actionable content with excellent workflow sequencing and validation feedback loops. The main gap is structural: everything lives in one monolithic SKILL.md, with the migration-specific rules inlined instead of split into a one-level-deep reference file.

Suggestions

Move the 'Migration and Data Conversion Tasks' section (the four [E] criteria and their [E]: MISSING message catalog) into a separate reference file (e.g., references/migration-criteria.md) and link to it from SKILL.md, keeping the top-level body focused on the CLEAR/CoVe core.

Trim the 'When to Use This Skill' section, which largely restates the frontmatter description, and fold the thin 'Linting Rules' section into the Reflective checklist to remove filler.

Surface the `/dh:test-designer` dependency more clearly (e.g., a short 'Related skills' note) instead of embedding it mid-paragraph in the Explicit section.

Dimension	Reasoning	Score
Conciseness	Mostly lean and directive (bulleted CLEAR/CoVe rules, a copy-paste template) with no padding explaining concepts Claude already knows. Minor over-explanation remains: the 'When to Use This Skill' section restates the description, and the two-line 'Linting Rules' section adds little beyond 're-check the letters above'.	4 / 5
Actionability	Fully executable guidance: a complete copy-paste task prompt template, concrete commands (`git add <file1> [file2 ...]` commit rules, `grep -h "^status:" real_data/*.md \| sort -u`, `uv run plugins/development-harness/scripts/verify_migration_fidelity.py`), and exact `[E]: MISSING` messages the scorer should emit.	5 / 5
Workflow Clarity	Explicit 'Order of operations' sequence, a 5-step CoVe loop with a revision feedback rule ('If any check fails or uncertainty remains, revise'), a lint checklist applied before finalizing, and acceptance criteria used as quality gates — clear sequencing with explicit validation checkpoints and error-recovery loops.	5 / 5
Progressive Disclosure	A single 280-line file with no bundle files or references. Section headers give decent in-file navigation, but the specialized migration rules (~70 lines of conditionally-relevant criteria and `[E]: MISSING` message catalog) are inlined content that clearly belongs in a separate reference file, and the `/dh:test-designer` mention is a buried external reference.	3 / 5
	Total	17 / 20 Passed

Description

87%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 description: third-person voice, explicit what and when clauses, named frameworks, and concrete trigger artifacts. The only weaknesses are mildly abstract action phrasing and a few missing natural synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Applies CLEAR... to structure and write agent task prompts, then adds CoVe (Chain of Verification) checks'), but the actions are framework applications rather than a fully enumerated list of operations, leaving minor gaps versus the comprehensive anchor.	4 / 5
Completeness	Explicitly answers both what ('Applies CLEAR... to structure and write agent task prompts, then adds CoVe... checks') and when ('Use when orchestration or planning agents are producing...', reinforced by 'Activates on draft task prompts, swarm plans, migration tasks, and multi-step plans') 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'. A few natural synonyms users might say (e.g., 'agent instructions', 'worker prompts', 'plan review') are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche — authoring worker-agent task prompts with named frameworks (CLEAR, CoVe) and distinctive artifacts (TASK.md, swarm plans) — with trigger terms unlikely to fire for unrelated skills.	5 / 5
	Total	18 / 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: 3e0b2af

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.