Name: github-release-management
Rating: 61.2 (1 reviews)
Author: ruvnet

github-release-management

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

1.62x

Quality

49%

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

The canonical home for this skill is github-release-management in ruvnet/agentic-flow

Quality

Content

45%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.

The body provides abundant concrete commands and well-validated release/hotfix workflows, but it is markedly verbose and pseudocode-heavy in its swarm-coordination blocks, and its claimed 'progressive disclosure' is illusory because everything is inlined into a single 1000+ line file with no reference files.

Suggestions

Move the large YAML configs and full GitHub Actions workflows into reference files (e.g. references/release-workflow.yml, references/release-config.yml) and link to them from SKILL.md so progressive disclosure is real rather than labeled.

Replace the pseudocode 'Single Message' JavaScript blocks (Write("...", "[updated version]"), mcp__claude-flow__swarm_init {...}) with actual executable commands or clearly label them as illustrative tool-call sequences.

Trim the redundant four-level structure and repeated capability lists to reduce the body to a lean overview plus pointed references.

Dimension	Reasoning	Score
Conciseness	The ~1080-line body is noticeably verbose, dumping enormous inline YAML configs, full GitHub Actions workflows, and repeated four-level 'Progressive Disclosure' sections that could be trimmed or moved to references rather than inlined.	2 / 5
Actionability	Bash and YAML blocks are executable, but many JavaScript 'Single Message' blocks are pseudocode with non-executable placeholders like Write("package.json", "[updated version]") and mcp__claude-flow__swarm_init { ... }, fitting the 'pseudocode instead of executable code' anchor.	3 / 5
Workflow Clarity	The release and hotfix workflows show clear sequencing with explicit validation checkpoints (lint/typecheck/test/build, security scan, post-release smoke tests), rollback feedback loops, and checklists, with only minor gaps in the hand-wavy swarm-coordination steps.	4 / 5
Progressive Disclosure	No bundle files exist and the named 'Progressive Disclosure: Level 1-4' sections are all inlined in one monolithic file; large content that clearly belongs in separate reference files (full workflows, 100-line YAML configs, command catalog) is not split out.	2 / 5
	Total	11 / 20 Passed

Description

53%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.

The description clearly conveys what the skill does and occupies a distinct niche, but it is padded with buzzwords ("AI swarm coordination", "comprehensive orchestration") and omits any explicit "Use when" trigger guidance, capping completeness and trigger-term quality at the mid level.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g. 'Use when creating, publishing, or rolling back a GitHub release, generating changelogs, or cutting version tags').

Trim buzzword framing ('Comprehensive', 'AI swarm coordination', 'orchestration') in favor of concrete verbs (cut, publish, roll back, generate changelog).

Include common synonyms users actually say — publish, changelog, release notes, semver, tag — to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete action domains ("automated versioning, testing, deployment, and rollback management") but wraps them in buzzword padding ("Comprehensive... orchestration with AI swarm coordination") that the rubric penalizes, keeping it below the 4 anchor.	3 / 5
Completeness	The "what" is clear (release orchestration across versioning/testing/deployment/rollback) but there is no "Use when..." or equivalent explicit trigger guidance, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant natural terms appear ("GitHub release", "deployment", "rollback", "versioning") but common variations users say are missing (publish, changelog, tag, semver, release notes) and "AI swarm coordination" is technical jargon rather than a user trigger.	3 / 5
Distinctiveness Conflict Risk	"GitHub release" is a clear niche with distinct triggers, with only minor overlap risk against closely related skills like github-workflow-automation and deployment-orchestration.	4 / 5
	Total	13 / 20 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/ruvector
Path: .claude/skills/github-release-management/SKILL.md
Commit: 74d2a60

Reviewed: 3 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.