ccb-clear

Clear conversation context for one or more mounted CCB agents using ccb clear. Use when the user invokes /ccb-clear, $ccb-clear, or $ccb_clear, or asks Grok to clear or reset CCB agent context without restarting agents or deleting project state.

Quality

91%

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

93%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.

An exemplary lean, single-purpose skill body: executable commands for every invocation scope, crisp guardrails on what not to do ("Never substitute ccb kill, ccb -n, restart, direct tmux input, or file deletion"), and explicit ambiguity and error handling. The only gap is that a batch clear of live agent context lacks an explicit post-run validation step confirming each agent was actually cleared, which caps workflow clarity just short of perfect.

Dimension	Reasoning	Score
Conciseness	The ~40-line body is lean with zero concept explanation: every line is either an operational constraint ("Source validation uses /home/bfly/yunwei/ccb_source/ccb_test"), a ready command, or a behavioral rule. It assumes Claude's competence and matches the 'every token earns its place' anchor; nothing could be cut without losing information.	5 / 5
Actionability	All three usage modes get copy-paste-ready commands ("command ccb clear", "command ccb clear \"$AGENT\"", "command ccb clear agent1 agent2") covering the common cases of bare invocation, single named agent, and multiple named agents. This matches the fully-executable anchor exactly; nothing is pseudocode or hand-wavy.	5 / 5
Workflow Clarity	The sequence is clear with most checkpoints present: a pre-flight scope rule ("For ambiguous natural-language scope, ask which agents to clear instead of clearing all"), a run-once directive ("Run once, report the command output, then stop"), and an explicit error path ("If terminal permission is denied or cancelled, report that no clear was performed"). Because `ccb clear` is a batch/destructive-flavored operation on live agent context and there is no step verifying the clear actually succeeded per agent, it cannot reach 5; the checkpoints present keep it above 3.	4 / 5
Progressive Disclosure	This is a simple single-purpose skill under 50 lines with no external materials needed, and no references/scripts/assets bundle exists — so the simple-skill exception applies: the well-organized structure (intro, environment constraint, commands per scope, then a consolidated Rules list) earns 5 with no external references required.	5 / 5
	Total	19 / 20 Passed

Description

90%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 well-formed description: concrete action, explicit 'Use when...' triggers covering both invocation forms and natural-language requests, plus a helpful non-destructive qualifier ('without restarting agents or deleting project state'). Its only weakness is that it describes a single action rather than a broader capability set, which limits specificity.

Dimension	Reasoning	Score
Specificity	"Clear conversation context for one or more mounted CCB agents using ccb clear" names the domain and one concrete action with scope, but lists no additional actions — matching the '1-2 concrete actions, not comprehensive' anchor. It is well above 2 (the domain and action are concrete, not generic) but below 4, which expects several specific actions.	3 / 5
Completeness	It explicitly answers what ("Clear conversation context for one or more mounted CCB agents using ccb clear") and when ("Use when the user invokes /ccb-clear... or asks Grok to clear or reset CCB agent context") with concrete trigger phrases, mirroring the anchor-5 example. Not 4, because the when-clause is already fully explicit and specific.	5 / 5
Trigger Term Quality	The description covers the full invocation surface users would naturally say: "/ccb-clear", "$ccb-clear", "$ccb_clear", plus natural-language phrasing "asks Grok to clear or reset CCB agent context", including the clear/reset synonym pair. This matches the comprehensive-synonyms anchor; nothing relevant is missing for this skill's niche.	5 / 5
Distinctiveness Conflict Risk	"mounted CCB agents", "ccb clear", and the slash/dollar invocation forms give it a clear niche with distinct triggers unlikely to fire for unrelated skills. There is minor adjacency to other CCB management skills, but the explicit command names keep conflict risk minimal, fitting the anchor-5 example.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: SeemSeam/claude_codex_bridge
Path: inherit_skills/grok_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.