github-release-management

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

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

48%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 content is highly actionable in structure with clearly sequenced, validation-backed release workflows, but it is severely over-long, repetitive, and undermined by pervasive path-corruption that breaks executability. It is also monolithic, with no bundle files to split the dense reference material.

Suggestions

Fix the '$'-for-'/' path corruption throughout (e.g. 'repos/:owner/:repo/compare/', '/tmp/release-prs.json', '.github/workflows/release.yml') and replace placeholder strings with real example content so commands are copy-paste executable.

Collapse the repeated claude-flow command examples across Levels 1-4 and the Actions section into a single canonical set, moving the large YAML config and full GitHub Actions workflow into reference files under references/.

Trim conceptual/padded prose (e.g. capability bullet lists that restate what the commands already show) to bring the body closer to a lean overview that points to detail files.

Dimension	Reasoning	Score
Conciseness	At ~1060 lines the body is noticeably verbose with repeated near-duplicate claude-flow command blocks and large inlined configs/workflows, matching 'noticeably verbose; several unnecessary explanations or padded sections'; not a 1 because it largely avoids explaining basic concepts Claude already knows, not a 3 because the volume of redundancy is substantial rather than a few tightenable spots.	2 / 5
Actionability	Contains a wealth of concrete commands, but pervasive '$'-for-'/' path corruption (e.g. 'repos/:owner/:repo$compare/...') and placeholder strings (e.g. Write("package.json", "[updated version]")) make much of it non-executable as written, matching 'some concrete guidance but incomplete; missing key details'; not a 4 because copy-paste executability is broadly broken, not a 2 because genuinely executable gh/npm commands are present.	3 / 5
Workflow Clarity	Processes are clearly sequenced across levels and the GitHub Actions workflow, and validation checkpoints are present (pre-release lint/typecheck/tests/security scan, post-release smoke tests, health checks, --block-on-failure, staged-rollout metric gates), so the destructive-operation cap does not apply; not a 5 because some inline coordination JS blocks lack validation feedback loops, not a 3 because validation is genuinely present rather than missing.	4 / 5
Progressive Disclosure	Has good section/level headers but is a monolithic single file with no bundle files (references/scripts/assets absent) and broken external doc links ('../..$docs$sparc-methodology.md'), matching 'some structure but content that should be separate is inline; references not clearly signaled'; not a 4 because large configs/workflows that belong in separate files are inlined, not a 2 because the header structure provides real navigability.	3 / 5
	Total	12 / 20 Passed

Description

66%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 conveys a clear, reasonably specific 'what' with good natural trigger terms for the GitHub release domain, but omits any explicit 'when to use' guidance, which caps its completeness. Buzzword phrasing ('AI swarm coordination') slightly dilutes trigger-term quality.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when creating, publishing, or rolling back GitHub releases across single or multiple repositories.'

Drop or de-emphasize the jargon phrase 'AI swarm coordination' in favor of natural terms a user would actually say (e.g. 'coordinated multi-agent releases').

Sharpen the listed actions from high-level categories (versioning, testing) to more concrete verbs (e.g. 'generate changelogs, bump versions, publish packages, run pre-release validation').

Dimension	Reasoning	Score
Specificity	Names the domain ('GitHub release orchestration') and several concrete actions ('automated versioning, testing, deployment, and rollback management'), matching the 'lists several specific actions; minor gaps' anchor; not a 5 because the actions are high-level rather than maximally concrete, and not a 3 because four distinct actions are named.	4 / 5
Completeness	Provides a clear 'what' (release orchestration with versioning/testing/deployment/rollback) but no 'when' trigger guidance, so per the missing-'Use when...' rule it is capped at 3; not a 4 because there is no explicit usage trigger, not a 2 because the 'what' is clear rather than vague.	3 / 5
Trigger Term Quality	Includes several natural user terms ('release', 'versioning', 'deployment', 'rollback') matching 'good keyword coverage; a few natural terms missing'; not a 5 because 'AI swarm coordination' is jargon users would not naturally say and synonyms/extensions are absent, not a 3 because coverage goes well beyond a single domain keyword.	4 / 5
Distinctiveness Conflict Risk	The 'GitHub release' niche is mostly distinct from sibling skills (PR/issue/workflow management) with only minor overlap, matching 'mostly distinct; minor overlap risk'; not a 5 because the frontmatter lists overlapping related skills (workflow-automation, multi-repo-coordination), not a 3 because 'release' is a more specific niche than generic document/file handling.	4 / 5
	Total	15 / 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: 4 suspicious	Warning

	Total	13 / 16 Passed

Repository: ruvnet/ruflo
Path: .agents/skills/github-release-management/SKILL.md
Commit: b14c79e

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.