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.
67
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
85%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured description that clearly defines both what the skill does and when to use it, with explicit trigger conditions and a distinctive niche. Its main weakness is the heavy reliance on specialized terminology (CLEAR, CoVe, orchestration agents) that may not match how users naturally phrase their requests. The description is thorough but could benefit from including more natural-language trigger terms alongside the technical ones.
Suggestions
Add more natural-language trigger variations alongside the jargon, e.g., 'writing instructions for AI agents', 'making task plans clear and testable', or 'improving agent prompts' to improve discoverability when users don't use the exact framework names.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: structuring/writing agent task files using CLEAR methodology, adding CoVe checks, and specifies the types of artifacts it operates on (task plans, task prompts, TASK.md instructions, swarm plans, migration tasks, multi-step plans). | 3 / 3 |
Completeness | Clearly answers both 'what' (applies CLEAR framework to structure task files, adds CoVe verification checks) and 'when' (explicitly states 'Use when orchestration or planning agents are producing task plans...' and 'Activates on draft task prompts, swarm plans, migration tasks...'). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'task prompts', 'TASK.md', 'swarm plans', 'migration tasks', 'multi-step plans', but relies heavily on specialized jargon (CLEAR, CoVe, 'orchestration agents') that users may not naturally use. Missing simpler trigger terms a user might say like 'write instructions for an agent' or 'plan tasks'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: the combination of CLEAR methodology, CoVe verification, and the specific focus on agent task file authoring creates a unique identity that is unlikely to conflict with general writing, planning, or coding skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill that provides a complete framework for writing agent task prompts with clear workflows, validation checkpoints, and a ready-to-use template. Its main weakness is that all content is packed into a single file without progressive disclosure to supporting references, and there is some redundancy and light verbosity that could be trimmed. The migration-specific section is a valuable addition but contributes to the monolithic feel.
Suggestions
Extract the Migration and Data Conversion Tasks section into a separate MIGRATION.md reference file and link to it from the main skill, reducing the monolithic structure.
Remove redundant framing sentences (e.g., 'Treat every task file as an LLM prompt with operational consequences', the Success Criteria section that restates CLEAR properties) to improve token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and well-structured, but contains some redundancy (e.g., success criteria at the end largely restates what CLEAR+CoVe already cover) and explanatory framing that Claude doesn't need (e.g., 'Treat every task file as an LLM prompt with operational consequences'). The migration section is thorough but adds significant length; some of the inline lint-failure message templates could be trimmed. | 2 / 3 |
Actionability | The skill provides a complete, copy-paste-ready task prompt template in markdown, concrete examples of acceptance criteria and verification commands, specific grep/assert examples for migration tasks, and a clear scoring/linting checklist. The guidance is fully executable and specific rather than abstract. | 3 / 3 |
Workflow Clarity | The skill defines a clear order of operations (CLEAR → CoVe → verbosity control), provides a canonical section ordering (Context → Objective → ... → Handoff), includes explicit validation/linting rules to apply before finalizing, and has feedback loops (CoVe's generate → verify → revise cycle, plus the 'if any item fails, revise' linting step). The migration section adds a deletion gate as a separate checkpoint. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear headers and logical sections, but it is monolithic — everything lives in a single file with no references to supporting documents. The migration section and CoVe guidelines could be split into separate reference files. For a skill of this length (~200+ lines), inline presentation of all content reduces scannability. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Jamie-BitFlight/claude_skills
- Commit
4e61312
- Reviewed
Table of Contents
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.