github-release-management

Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management

1.62x

Quality

30%

Does it follow best practices?

Impact

78%

1.62x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/github-release-management/SKILL.md

Quality

Discovery

32%

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 attempts to cover a specific domain (GitHub releases) but relies heavily on buzzwords like 'orchestration' and 'AI swarm coordination' that obscure rather than clarify capabilities. The complete absence of a 'Use when...' clause is a significant weakness, and the listed actions mix specific (rollback management) with vague (coordination).

Suggestions

Add an explicit 'Use when...' clause with trigger terms like 'create release', 'publish version', 'GitHub tag', 'release notes', 'semantic versioning'

Remove or clarify 'AI swarm coordination' - either explain what this means concretely or remove the buzzword entirely

Add common file/format triggers users might mention like 'CHANGELOG', 'package.json version', or 'git tag'

Dimension	Reasoning	Score
Specificity	Names the domain (GitHub release) and lists several actions (versioning, testing, deployment, rollback management), but 'AI swarm coordination' and 'orchestration' are vague buzzwords that don't describe concrete actions.	2 / 3
Completeness	Describes what it does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing explicit trigger guidance caps this at 2, but the 'what' is also weakened by buzzwords.	1 / 3
Trigger Term Quality	Contains some relevant keywords like 'GitHub release', 'versioning', 'deployment', and 'rollback', but missing common variations users might say like 'release notes', 'publish release', 'tag', 'semantic versioning', or 'CI/CD'.	2 / 3
Distinctiveness Conflict Risk	GitHub release is somewhat specific, but 'testing' and 'deployment' are broad terms that could overlap with CI/CD skills, testing frameworks, or general deployment tools. 'AI swarm coordination' adds confusion rather than clarity.	2 / 3
	Total	7 / 12 Passed

Implementation

27%

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

This skill suffers from severe verbosity, attempting to be a comprehensive reference manual rather than a focused skill document. While it contains useful gh CLI examples and workflow patterns, the content is buried in repetitive sections, hypothetical tooling commands, and excessive boilerplate. The 'progressive disclosure' structure is cosmetic rather than functional, as everything remains in one massive file.

Suggestions

Reduce to ~100-150 lines focusing on core gh CLI release commands and one concrete swarm coordination example, moving advanced content to separate referenced files

Remove or verify all 'npx claude-flow github' commands - if these are hypothetical, replace with actual executable alternatives or clearly mark as planned features

Split into SKILL.md (quick start + overview), WORKFLOWS.md (multi-step processes), ENTERPRISE.md (advanced config), and TROUBLESHOOTING.md

Add explicit validation gates to all multi-step workflows: 'STOP: Verify X before proceeding to step Y'

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~1000+ lines with extensive repetition. Explains basic concepts Claude knows (what semantic versioning is, what changelogs are), includes redundant examples across multiple 'progressive disclosure levels' that repeat similar patterns, and contains excessive boilerplate like checklists and appendices that don't add actionable value.	1 / 3
Actionability	Contains many concrete code examples and bash commands, but relies heavily on hypothetical CLI commands (npx claude-flow github release-create, npx claude-flow@alpha) that may not exist or work as shown. The gh CLI examples are executable, but the custom tooling examples are pseudocode-like without verification they're real commands.	2 / 3
Workflow Clarity	Multi-step processes are listed but validation checkpoints are inconsistent. Some workflows show validation steps (like the GitHub Actions workflow), but many command sequences lack explicit 'validate before proceeding' gates. The emergency hotfix workflow lacks verification steps before deployment.	2 / 3
Progressive Disclosure	Despite being labeled 'Progressive Disclosure: Level 1-4', all content is in a single monolithic file. The 'levels' are just sections within the same document rather than separate files. References to external docs (SPARC guide, swarm patterns) exist but the skill itself is a wall of text that should be split across multiple files.	1 / 3
	Total	6 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1082 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: ruvnet/ruv-FANN
Commit: 46f6f8a

Reviewed: about 1 month 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.