clarity
Establish clarity before starting work. Use when beginning any significant task, when input is vague or stream-of-consciousness, or when requirements seem unclear. Handles messy voice input efficiently. This is the first system in the 5-system framework.
69
41%
Does it follow best practices?
Impact
85%
1.26xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/1-clarity/SKILL.mdQuality
Discovery
32%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 fails to articulate what concrete actions this skill performs, relying on abstract language like 'establish clarity.' While the 'when' triggers are partially defined, the scope is so broad ('any significant task') that it would conflict with many other skills. The reference to a '5-system framework' is internal jargon that doesn't help Claude select this skill appropriately.
Suggestions
Replace 'establish clarity' with specific concrete actions the skill performs, e.g., 'Parses ambiguous or stream-of-consciousness input into structured requirements, generates clarifying questions, and produces a confirmed task brief before work begins.'
Narrow the trigger scope from 'any significant task' to more specific scenarios, e.g., 'Use when the user's request is ambiguous, contains multiple possible interpretations, or is raw voice-transcribed text that needs structuring.'
Remove the '5-system framework' reference as it provides no selection value and replace with distinctive trigger terms like 'requirements gathering', 'task scoping', or 'input parsing'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'establish clarity' and 'beginning any significant task' without listing concrete actions. It doesn't specify what the skill actually does—no mention of asking clarifying questions, parsing requirements, creating structured summaries, or any other tangible action. | 1 / 3 |
Completeness | The 'when' is reasonably well-covered with 'Use when beginning any significant task, when input is vague or stream-of-consciousness, or when requirements seem unclear.' However, the 'what' is extremely weak—'establish clarity' is not a concrete description of what the skill does. The mention of '5-system framework' adds no actionable information. | 2 / 3 |
Trigger Term Quality | It includes some relevant trigger terms like 'vague', 'unclear', 'voice input', and 'requirements', which users might naturally mention. However, it misses common variations like 'ambiguous', 'confusing request', 'what do you mean', 'clarify', or 'interpret my request'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Beginning any significant task' is extremely broad and would conflict with virtually any other skill that involves task initiation. The description lacks a clear niche—any skill could claim to handle unclear requirements or vague input. | 1 / 3 |
Total | 6 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has a solid core concept—tiered clarity based on input ambiguity—and the messy input example is genuinely useful. However, it suffers from explaining things Claude already knows (how to ask clarifying questions) and the Full Clarity Protocol is largely generic project management questions that don't add unique value. The output template is helpful but the transition criteria and validation steps are underdeveloped.
Suggestions
Remove or drastically condense Steps 1-4 of the Full Clarity Protocol—Claude already knows how to ask clarifying questions. Instead, focus on the unique value: the tiered decision framework and the specific output format.
Add a validation step after generating active-context.md, such as 'Confirm the active-context.md summary with the user before proceeding to execution.'
Link the transition references to actual file paths (e.g., 'Proceed to **Identity System** → See [IDENTITY.md](IDENTITY.md)') rather than just naming them.
Move the active-context.md template to a separate reference file and just describe the required sections inline to reduce the skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some efficient sections (Messy Input Protocol is well-structured) but the Full Clarity Protocol is verbose with questions Claude would naturally know to ask. The output template with placeholder items adds bulk. The 'Efficiency Rules' section is a nice touch for brevity, but the overall document could be tightened. | 2 / 3 |
Actionability | The messy input example is concrete and actionable, and the output template for active-context.md is specific. However, the Full Clarity Protocol (Steps 1-4) is mostly a list of generic questions to ask rather than executable guidance—Claude already knows how to ask clarifying questions. The transition section is vague about how to decide which system to proceed to. | 2 / 3 |
Workflow Clarity | The tiered approach (clear → slightly unclear → very unclear) is a good decision framework, and the steps are sequenced. However, there's no validation checkpoint—no step to verify that the active-context.md output is correct or that the user has actually confirmed understanding before proceeding. The transition criteria ('if there might be blockers') are too vague to be reliable decision points. | 2 / 3 |
Progressive Disclosure | The skill has reasonable structure with the Messy Input Protocol separated from the Full Clarity Protocol. However, the full protocol's detailed question lists and the large output template could be split into a referenced file. References to other systems (Identity, Priority, Execution, Reset) are mentioned but not linked to actual files. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- majiayu000/claude-skill-registry-data
- Commit
6770aaa
- 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.