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

83%

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

Quality

Content

80%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.

A lean, highly actionable single-purpose skill with copy-paste commands and precise guardrails. Its main weakness is the missing validation/confirmation step for a batch, destructive clear operation, plus a tangential environment-specific paragraph that inflates the token budget slightly.

Suggestions

Add a pre-flight validation step for the batch case, e.g. list the agents that will be targeted (`command ccb status` or equivalent) and confirm with the user before `ccb clear` wipes all mounted agents' contexts.

Add a post-run verification step, e.g. check the command output for per-agent success/failure and report any agent whose context was not cleared, rather than only relaying raw output.

Move the CCB source-checkout / external test-project paragraph into a separate note or trim it, since it pertains to source testing workflows rather than the clear-context task the skill performs.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept explanations Claude already knows, and every line is operational. It sits at 4 rather than 5 because the source-checkout/external-test-project paragraph ("In the CCB source checkout... /home/bfly/yunwei/...") is tangential environment-specific detail that adds tokens without serving the clear-context task.	4 / 5
Actionability	Three copy-paste-ready command forms (`command ccb clear`, `command ccb clear "$AGENT"`, `command ccb clear agent1 agent2`) cover the all/one/many cases, and the rules give concrete do/don't guidance including post-run behavior. Fully executable for the common cases.	5 / 5
Workflow Clarity	The run-then-report sequence is unambiguous for a simple skill, but `ccb clear` is a batch operation across all mounted agent panes with a destructive effect (wiping provider conversation context), and the body contains no validation checkpoint before or after the operation ("After running the command, report the command output" is reporting, not verification). Per the rubric's cap for batch/destructive operations without validation, workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	The skill is under 50 lines, no bundle files exist or are needed, and the content is organized into clear Commands and Rules sections with no inlined content that belongs in separate files. Per the simple-skill exception this matches the top anchor.	5 / 5
	Total	17 / 20 Passed

Description

87%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 strong description: third-person voice, exact command, explicit what-and-when with literal trigger tokens, and a clear non-destructive boundary. The only minor gap is limited natural-phrase synonym coverage beyond the two command spellings.

Dimension	Reasoning	Score
Specificity	Names the exact command (`ccb clear`), the target scope ("one or more CCB agent contexts"), and a non-destructive boundary ("without restarting or deleting project state"). It stays at 4 rather than 5 because the skill performs only one operation, so there is no broader set of concrete actions to cover, and at 3 because it specifies command, scope, and boundary rather than just 1-2 bare actions.	4 / 5
Completeness	Explicitly answers what ("Clear CCB managed agent conversation context with `ccb clear`") and when ("Use when the user writes $ccb-clear, $ccb_clear, or asks to clear/reset...") with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Includes both literal trigger spellings ("$ccb-clear", "$ccb_clear") plus natural phrases ("asks to clear/reset one or more CCB agent contexts"). Not 5 because a few plausible natural variations (e.g., wipe/fresh context) are absent, though coverage is strong.	4 / 5
Distinctiveness Conflict Risk	The CCB-specific domain and literal `$ccb-clear`/`$ccb_clear` trigger tokens carve a clear niche with minimal overlap risk against generic clearing or reset skills.	5 / 5
	Total	18 / 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: 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.