ccb-github

Maintain this CCB project's GitHub-facing release and npm publication surface. Use when preparing, publishing, auditing, or fixing CCB releases; updating README.md, README/zh.md, localized README files, CHANGELOG.md, VERSION, package.json, GitHub release notes/assets, repository description/topics, npm registry state, or GitHub Actions release/test status.

Quality

88%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, highly actionable release runbook with strong sequencing and validation, weakened mainly by redundancy across sections and a monolithic structure that keeps detail-heavy checklists inline.

Suggestions

Deduplicate npm auto-completion requirements: state them once and cross-reference from the Decision Tree, Execution Contract, and Publish Sequence to reduce repetition.

Move the Recovery Runbook and full Release Preparation Checklist into a reference file linked from SKILL.md to improve progressive disclosure and shorten the main body.

Extract time-sensitive specifics (e.g., Node 24, exact workflow filenames) into a clearly labeled configuration/standards section so they don't inflate the prose.

Dimension	Reasoning	Score
Conciseness	The body is dense and directive without over-explaining known concepts, but repeats npm auto-completion requirements across several sections and embeds time-sensitive specifics (Node 24, exact flags), so it could be tightened.	2 / 3
Actionability	Provides fully executable commands (checker phases, gh/npm view/git, git show checks) with exact paths, package names, and workflow filenames, copy-paste ready.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (Execution Contract, Publish Sequence) with explicit validation checkpoints ('fix every FAIL before tag'), a recovery runbook, and stop conditions forming feedback loops.	3 / 3
Progressive Disclosure	Bundled scripts exist and are referenced via a clean one-level entry point, but the ~282-line body is largely monolithic with lengthy checklists and runbooks inline rather than split into separate reference files.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 focused, third-person description with concrete actions, an explicit trigger clause, and broad coverage of user-facing terms. It clearly distinguishes this skill's niche from others.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('preparing, publishing, auditing, or fixing') and enumerates specific files (README.md, CHANGELOG.md, VERSION, package.json, release notes/assets) in third-person voice.	3 / 3
Completeness	Explicitly answers both 'what' (maintain release and npm publication surface, named files) and 'when' with an explicit 'Use when...' clause.	3 / 3
Trigger Term Quality	Natural trigger clause 'Use when preparing, publishing, auditing, or fixing CCB releases' plus common user terms (releases, README, CHANGELOG, npm, GitHub Actions) gives good coverage.	3 / 3
Distinctiveness Conflict Risk	Niche is highly specific to one CCB project's GitHub/npm release surface, making conflict with unrelated skills unlikely.	3 / 3
	Total	12 / 12 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: SeemSeam/claude_codex_bridge
Path: dev_tools/skills/ccb-github/SKILL.md
Commit: 9f3727c

Reviewed: about 13 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.