ccb-compact

Compact one or more CCB managed agent contexts with `ccb compact` without restarting or deleting state.

Quality

76%

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-compact/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.

A tight, highly actionable single-purpose skill with excellent conciseness and structure. Its only real gap is the absence of a verification checkpoint for batch multi-agent compaction.

Suggestions

Add a verification step after batch compaction, e.g., confirm each named agent reports a successful native compact result before considering the run complete.

Specify what to do when an agent is busy or queued (the skill notes they are blocked) — e.g., report which agents were skipped and whether to retry.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding; every line earns its place, and the DSH/Web-command detail is non-obvious domain knowledge Claude would not already have.	5 / 5
Actionability	Fully executable, copy-paste-ready commands covering the common cases (single, variable, and multiple named agents), with concrete reporting instruction.	5 / 5
Workflow Clarity	The skill supports batch compaction of multiple agents but lacks an explicit validate/verify checkpoint confirming each agent compacted successfully, so workflow clarity is capped at 3 per the batch-operation guideline.	3 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no external references needed, and well-organized with a command block plus a focused notes paragraph, meeting the simple-skill exception.	5 / 5
	Total	18 / 20 Passed

Description

65%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 specific, concise description with a clear niche and low conflict risk, but it omits explicit 'when to use' trigger guidance and lists only one action. Adding a 'Use when...' clause would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when compacting CCB agent contexts without losing state').

Mention a second concrete action or outcome (e.g., reporting compact results) to broaden specificity beyond the single 'compact' action.

Include common synonyms or variations users might say (e.g., 'shrink', 'reduce context') to strengthen trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('CCB managed agent contexts') and one concrete action ('Compact... with `ccb compact`') plus a state-preserving boundary, but only a single action rather than comprehensive coverage.	3 / 5
Completeness	Clearly states what the skill does, but provides no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes the natural command phrase users would say ('compact', 'ccb compact', 'agent contexts'); a few synonymous trigger terms are missing but coverage is good.	4 / 5
Distinctiveness Conflict Risk	Targets a specific CCB niche with a distinct command trigger ('ccb compact') and explicit non-substitutes, giving minimal conflict risk with other skills.	5 / 5
	Total	15 / 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-compact/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.