CtrlK
BlogDocsLog inGet started
Tessl Logo

clear-cove-task-design

Combine CLEAR (Concise, Logical, Explicit, Adaptive, Reflective) and CoVe (Chain of Verification) to write and lint agent task files that will be executed by worker agents. Use when orchestration or planning agents are producing task plans, task prompts, or TASK.md style instructions that must be unambiguous, verifiable, and resistant to hallucination.

80

Quality

76%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/development-harness/skills/clear-cove-task-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

75%

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 well-structured with a clear 'Use when' clause that explicitly defines both what the skill does and when to invoke it. Its main strength is the distinctive niche it carves out by combining named frameworks for a specific use case. The primary weakness is that the concrete actions could be more granular beyond 'write and lint', and the trigger terms, while relevant, lean toward specialized jargon that may not cover all natural user phrasings.

Suggestions

Expand the concrete actions beyond 'write and lint'—e.g., 'validate step dependencies, check for ambiguous instructions, ensure verifiable acceptance criteria'—to improve specificity.

Add more natural trigger term variations such as 'agent instructions', 'subtask definitions', 'task decomposition', or 'delegation prompts' to improve discoverability across different user phrasings.

DimensionReasoningScore

Specificity

The description names the domain (agent task files) and mentions specific frameworks (CLEAR, CoVe) and actions (write and lint), but the actual concrete actions are limited—'write and lint' are only two actions, and the CLEAR/CoVe acronym expansions add conceptual detail rather than concrete capabilities like 'validate step dependencies' or 'check for ambiguous instructions'.

2 / 3

Completeness

The description clearly answers both 'what' (combine CLEAR and CoVe to write and lint agent task files) and 'when' (when orchestration or planning agents are producing task plans, task prompts, or TASK.md style instructions that must be unambiguous, verifiable, and resistant to hallucination). The 'Use when' clause is explicit and detailed.

3 / 3

Trigger Term Quality

Includes some relevant terms like 'task plans', 'task prompts', 'TASK.md', 'orchestration', 'planning agents', and 'worker agents', which are useful triggers. However, these are fairly specialized terms; common variations like 'agent instructions', 'subtask', 'delegation', or 'task decomposition' are missing, and some users might not use these exact phrases.

2 / 3

Distinctiveness Conflict Risk

This skill occupies a very specific niche—combining two named frameworks (CLEAR and CoVe) for agent task file authoring and linting. The combination of orchestration agents, TASK.md, and the specific methodology makes it highly unlikely to conflict with other skills.

3 / 3

Total

10

/

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 files. Its main strengths are the concrete template, clear workflow sequencing, and specific linting/validation rules. The primary weakness is moderate verbosity — some sections explain concepts Claude already knows (what conciseness means, what CoVe is conceptually) and the migration section, while valuable, makes the file long enough to benefit from progressive disclosure into separate files.

Suggestions

Trim the CLEAR subsection explanations to just the actionable rules — Claude doesn't need definitions of 'concise' or 'logical'; focus on the specific task-writing rules under each letter.

Consider extracting the 'Migration and Data Conversion Tasks' section into a separate referenced file (e.g., MIGRATION_TASKS.md) to keep the main skill leaner and improve progressive disclosure.

DimensionReasoningScore

Conciseness

The skill is reasonably well-structured but includes some unnecessary elaboration. The CLEAR acronym explanations (Concise, Logical, Explicit, Adaptive, Reflective) are somewhat verbose given Claude already understands these concepts. The 'When to Use This Skill' and 'Success Criteria' sections restate things that are implicit from the template and guidelines. However, most content does earn its place.

2 / 3

Actionability

The skill provides a complete, copy-paste-ready task prompt template in markdown, concrete linting rules, specific verification procedures, and clear output responsibilities. The migration section includes exact example assertions and commands. The guidance is specific enough to produce consistent outputs.

3 / 3

Workflow Clarity

The workflow is clearly sequenced: CLEAR first to structure, then CoVe for accuracy, then linting rules before finalizing. The template provides explicit validation checkpoints (Acceptance Criteria, Verification Steps, CoVe Checks). The linting rules serve as a pre-finalization validation gate with explicit pass/fail criteria. The migration section adds mandatory criteria with scorer behavior for failures.

3 / 3

Progressive Disclosure

The content is entirely self-contained in one file with no references to external documents, which is appropriate for the complexity level. However, at ~200+ lines, the migration-specific section and the detailed CLEAR breakdown could benefit from being split into referenced files. The document is well-sectioned but borders on monolithic for a single SKILL.md.

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
Jamie-BitFlight/claude_skills
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.