ccb-clear

Clear CCB managed agent conversation context with `ccb clear`. Use when the user writes `$ccb-clear`, `$ccb_clear`, or asks to clear/reset one or more CCB agent contexts without restarting or deleting project state.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./inherit_skills/claude_skills/ccb-clear/SKILL.md

Quality

Content

68%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 body is highly actionable with clean, executable command examples and clear rules, but a verbose environment-specific paragraph with absolute local paths adds noise, and the batch clear operation lacks a validation/confirmation checkpoint, capping workflow clarity.

Suggestions

Remove or generalize the source-checkout paragraph and its machine-specific absolute paths ('/home/bfly/yunwei/...'); move any environment-disambiguation guidance to a separate reference file if truly needed.

Add a validation/confirmation step before clearing, e.g. list the target panes/agents and confirm with the user when 'ccb clear' would target all mounted agents, to lift workflow clarity above the destructive/batch cap.

Add a section header (e.g. '## Scope') to the source-checkout note so all top-level content lives under a clear heading.

Dimension	Reasoning	Score
Conciseness	The Commands and Rules sections are lean and efficient, but the source-checkout paragraph inlines machine-specific absolute paths ('/home/bfly/yunwei/...') and environment variables that pad the skill without earning their place, landing it at 'mostly efficient with some unnecessary explanation'.	3 / 5
Actionability	Provides copy-paste-ready executable commands covering the common cases ('command ccb clear', 'command ccb clear "$AGENT"', 'command ccb clear agent1 agent2') plus concrete rules on targeting, making the guidance fully actionable.	5 / 5
Workflow Clarity	Though the single action is unambiguous (which would normally allow a 5 for a simple skill), `ccb clear` is a batch operation targeting all mounted agents by default and lacks a validation/confirmation checkpoint before clearing, so the destructive/batch cap of 3 applies.	3 / 5
Progressive Disclosure	A short, single-purpose skill with clear Commands and Rules sections and no need for external references; the unheaded source-checkout paragraph sitting between the intro and Commands is a minor organization gap that keeps it just below a 5.	4 / 5
	Total	15 / 20 Passed

Description

82%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 concise, well-targeted description that clearly states both the capability and the trigger conditions with concrete, user-natural phrases and explicit boundaries. The only weakness is that, being single-purpose, it lists just one concrete action rather than a broader set.

Dimension	Reasoning	Score
Specificity	Names the domain ('CCB managed agent conversation context') and one concrete action ('Clear ... with `ccb clear`'), but it is a single-purpose skill with only one main action rather than several listed actions, matching the 'domain + 1-2 concrete actions' anchor.	3 / 5
Completeness	Explicitly answers both 'what' ('Clear CCB managed agent conversation context with `ccb clear`') and 'when' ('Use when the user writes `$ccb-clear`... or asks to clear/reset...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('$ccb-clear', '$ccb_clear', 'clear/reset ... agent contexts') with good coverage of token variants and synonyms, missing only a few natural phrasings to reach comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (CCB agent context clearing) with explicit boundary guidance ('without restarting or deleting project state') and distinct trigger tokens, giving minimal conflict risk with other skills.	5 / 5
	Total	17 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: SeemSeam/claude_codex_bridge
Path: inherit_skills/claude_skills/ccb-clear/SKILL.md
Commit: 01d5b1c

Reviewed: about 20 hours 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.