ccb-clear

Clear one or more CCB managed agent contexts with `ccb clear` without deleting project state.

Quality

70%

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/dsh_skills/ccb-clear/SKILL.md

Quality

Content

87%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 exemplary in conciseness and actionability with copy-paste commands and only non-obvious domain guidance, but it lacks an explicit validation/verification step for a state-clearing batch operation.

Suggestions

Add an explicit verification step after running the command (e.g., confirm the targeted agents report cleared/no active context) to satisfy the destructive/batch validation checkpoint.

Clarify how a blocked ('Busy or queued agents') result should be reported and retried, giving a small feedback loop for the batch case.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient: three command forms and a short DSH-specific paragraph of non-obvious domain detail, with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	Three copy-paste-ready executable commands cover the common cases (clear all, clear one by variable, clear multiple named agents), supplemented by concrete boundary guidance.	5 / 5
Workflow Clarity	It is a single-command skill, but clearing agent contexts is state-losing and a batch variant (agent1 agent2) exists with no explicit validation/verification checkpoint, so the destructive/batch cap holds workflow clarity at 3.	3 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no external references needed, and well-organized with a clear title and command block; per the simple-skill exception this scores 5.	5 / 5
	Total	18 / 20 Passed

Description

53%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 is concise and third-person, clearly stating a single concrete action for a specific tool, but it omits any explicit 'when to use' trigger guidance and lacks natural trigger synonyms.

Suggestions

Add an explicit 'Use when...' clause naming the natural trigger phrases a user would say (e.g., clearing or resetting CCB agent contexts).

Include common synonyms or phrasings (e.g., 'reset', 'wipe context') to broaden natural trigger coverage.

Optionally enumerate a second concrete capability to lift specificity above a single action.

Dimension	Reasoning	Score
Specificity	Names the domain ('CCB managed agent contexts') and one concrete action ('Clear one or more... with `ccb clear`') plus a constraint ('without deleting project state'), but coverage is a single action rather than comprehensive.	3 / 5
Completeness	It clearly states what the skill does but provides no 'when'/'Use when...' trigger clause; the missing explicit trigger guidance caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	'clear', 'CCB', and 'agent contexts' are relevant keywords, but CCB is tool-specific jargon and natural synonyms/variations a user might say are missing.	3 / 5
Distinctiveness Conflict Risk	The named CCB tool and specific 'clear context' trigger make it mostly distinct with only minor overlap risk against general context-management skills, short of the clearly-niche anchor 5.	4 / 5
	Total	13 / 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/dsh_skills/ccb-clear/SKILL.md
Commit: 18bf0af

Reviewed: 7 days 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.