CtrlK
BlogDocsLog inGet started
Tessl Logo

clarification-broker

Compress planner candidate questions into a compact frontdesk-facing clarification batch and normalize answers back to planner.

53

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./docs/plantree/plans/agentic-loop-workflow/drafts/agentroles.ccb_clarification_broker/skills/clarification-broker/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 content is admirably concise and well-structured for a simple broker skill, but its rules stay at the directive level without the concrete decision criteria or validation steps needed to make the workflow fully executable.

Suggestions

Add a short ordered workflow (e.g., collect candidate questions -> dedupe -> defer later-phase -> emit batch -> normalize answers) so the sequence is explicit.

Spell out concrete decision criteria for 'already-answerable' and 'later-phase' questions rather than leaving them to judgment.

Include a validation checkpoint confirming the batch does not alter authoritative task state before returning to the planner.

DimensionReasoningScore

Conciseness

The body is lean and efficient with no concept explanations or padding; every section (Inputs, Outputs, Rules) earns its place.

5 / 5

Actionability

Rules are actionable directives ('Remove duplicates', 'Defer later-phase questions') but lack concrete criteria for how to batch, dedupe, or decide what is already-answerable.

3 / 5

Workflow Clarity

Inputs/Outputs/Rules are listed but there is no explicit processing sequence or validation checkpoint; the task-state constraint is stated but not verified.

3 / 5

Progressive Disclosure

Under 50 lines with well-organized sections and no need for external references, satisfying the simple-skill exception for progressive disclosure.

5 / 5

Total

16

/

20

Passed

Description

46%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 states a clear purpose and two concrete actions but omits any trigger guidance, leaning on internal jargon rather than natural user terms. It is distinct within its niche yet would be hard to activate reliably from a user request.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the planner emits candidate clarification questions that must be batched for the user').

Replace or supplement jargon ('planner', 'frontdesk') with plain-language synonyms a user might actually say.

Broaden the action list slightly (e.g., dedup, defer, apply defaults) to lift specificity from 1-2 actions toward comprehensive coverage.

DimensionReasoningScore

Specificity

Names the domain and two concrete actions ('Compress...questions into a...batch' and 'normalize answers back to planner') but coverage is narrow and not comprehensive.

3 / 5

Completeness

The 'what' is clear, but there is no 'when'/'Use when...' clause; per the guideline a missing trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Terms like 'planner', 'frontdesk', and 'clarification batch' are system-internal jargon rather than natural phrases a user would say, and no 'Use when...' trigger is present.

2 / 5

Distinctiveness Conflict Risk

The broker role between planner and frontdesk is a fairly distinct niche with only minor overlap risk against general clarification skills.

4 / 5

Total

12

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
SeemSeam/claude_codex_bridge
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.