github-release-management

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

1.62x

Quality

47%

Does it follow best practices?

Impact

78%

1.62x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/github-release-management/SKILL.md

Quality

Content

35%

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

The body is an exhaustive, catalog-style monolith: heavy on claude-flow command examples and large inline configs, but padded with concepts Claude already knows and pseudocode MCP blocks. It has sequenced workflows and checklists but is far from token-efficient and does not split material across bundle files.

Suggestions

Trim sections that restate common knowledge (Core Capabilities, Best Practices, Performance Metrics, appendix checklists) to keep only what Claude would not already know.

Replace the non-executable '[Single Message]' MCP pseudocode and '[updated version]' placeholders with real, runnable code or remove them.

Move the large YAML configs and GitHub Actions workflows into references/ files and link to them one level deep so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The ~1060-line body restates obvious concepts (Core Capabilities bullets, Best Practices, Performance Metrics, appendix checklists) and pads with redundant sections; not a 2 because the verbosity is pervasive rather than a few tighten-able spots.	1 / 3
Actionability	Provides concrete copy-paste bash/gh commands, but the '[Single Message]' JavaScript MCP blocks use non-executable syntax and placeholders like '[v1.0.72 content]' and '[updated version]'; not a 3 because much of the code is pseudocode with missing details.	2 / 3
Workflow Clarity	Release steps are sequenced with TodoWrite checklists and validation commands appear, but destructive/batch operations (deploy, rollback) lack explicit validate-then-proceed feedback loops, which caps workflow clarity at 2; not a 1 because a sequence and some checkpoints are present.	2 / 3
Progressive Disclosure	Section headers (Quick Start, Levels 1-4) give structure, but all content is inline in one ~1060-line file with no references/scripts/assets bundle, and the only links target '../../docs/...' paths 2+ levels up that are not part of the bundle; not a 3 because content that should be split out (giant YAML configs, GitHub Actions workflows, appendices) remains inline.	2 / 3
	Total	7 / 12 Passed

Description

60%

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 names concrete release actions and a recognizable domain, but leans on buzzwords ('Comprehensive', 'AI swarm coordination') and omits any explicit 'when to use' trigger guidance. It is distinguishable but overlaps with related claude-flow skills.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when the user asks to cut a GitHub release, publish a version, or roll back a deployment.'

Drop buzzword padding ('Comprehensive', 'AI swarm coordination') and replace with concrete terms users actually say.

Sharpen distinctiveness from sibling skills by naming the release-specific scope (tags, changelogs, artifacts) that pr-management and workflow-automation do not cover.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'automated versioning, testing, deployment, and rollback management' — which matches the anchor for listing several specific actions; not reduced to 2 because the named actions are concrete rather than a single domain.	3 / 3
Completeness	Clearly states what the skill does but has no 'Use when...' clause or equivalent trigger guidance, which per the guidelines caps completeness at 2; not a 1 because the 'what' is well covered.	2 / 3
Trigger Term Quality	Includes relevant natural terms like 'GitHub release', 'deployment', 'versioning', and 'rollback', but pads with jargon users would not naturally say ('AI swarm coordination'); not a 3 because common variations and explicit trigger phrasing are missing.	2 / 3
Distinctiveness Conflict Risk	The 'GitHub release' niche is somewhat specific, but 'AI swarm coordination' and the listed related_skills (pr-management, workflow-automation, multi-repo-coordination) indicate overlap with sibling skills; not a 3 because conflict risk with similar skills remains.	2 / 3
	Total	9 / 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 — 13 / 16 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
relative_links	Relative link issues: 2 suspicious	Warning

	Total	13 / 16 Passed

Repository: ruvnet/agentic-flow
Path: .claude/skills/github-release-management/SKILL.md
Commit: d069fff

Reviewed: about 10 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.