github-workflow-automation

Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management

Quality

41%

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-workflow-automation/SKILL.md

Quality

Content

38%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 is an overstuffed, buzzword-heavy catalog whose code examples are systematically corrupted (slashes and closing tags broken) and therefore non-executable as written, with no validation checkpoints for its batch/destructive operations. Despite claiming progressive disclosure, it is a monolith with no bundle files and no real external references.

Suggestions

Fix the systematic corruption: restore '/' in all paths/URLs (e.g. .github/workflows/ci.yml, actions/checkout@v3) and close tags properly (</summary>, </details>) so examples are executable.

Move the workflow templates, command reference, and real-world examples into separate reference files under references/ and replace the inlined blocks with one-level-deep links, honoring the progressive_disclosure claim.

Add explicit validate-then-proceed checkpoints (e.g. verify gh auth, dry-run workflow, confirm before batch PR creation/deploy) to the batch and deployment workflows.

Trim marketing fluff ('intelligent', 'comprehensive', 'self-organizing, adaptive') and consolidate repeated command patterns to respect the token budget.

Dimension	Reasoning	Score
Conciseness	The ~1000-line body is noticeably verbose and heavily padded with marketing fluff ('comprehensive', 'self-organizing, adaptive', 'intelligent', 'AI swarm coordination') and repeated command/template patterns, matching the score-2 anchor 'Noticeably verbose; several unnecessary explanations or padded sections'. It is not 1 because it does not belabor basic concepts Claude already knows (e.g. defining what GitHub Actions is), and not 3 because the padding is pervasive rather than a few trimmable spots.	2 / 5
Actionability	The body is dense with concrete bash/YAML/JS commands, but as written they are non-executable: every path slash is corrupted to '$' (e.g. '.github$workflows$ci.yml', 'actions$checkout@v3') and closing tags are malformed ('<$summary>', '<$details>'), reducing real code to effectively pseudocode, matching the score-3 anchor 'Some concrete guidance but incomplete; pseudocode instead of executable code'. It is not 4 because the corruption means the examples do not run as-is, and reliance on unverified tools (ruv-swarm, claude-flow@alpha) adds gaps.	3 / 5
Workflow Clarity	A rough sequence exists (Quick Start commands, Integration Checklist) but there are no validation/feedback checkpoints for the destructive and batch operations the skill promotes (concurrent PR creation, auto-deploy, auto-merge), so per the judging guidelines workflow_clarity is capped at 3, matching 'Steps listed but validation gaps; checkpoints missing or implicit'. It is not 2 because some sequenced steps are present, and capped from 4 by the missing validation on risky batch operations.	3 / 5
Progressive Disclosure	Despite frontmatter claiming 'progressive_disclosure: true', no bundle files exist (no references/, scripts/, or assets/) and the body is a monolithic wall where content that belongs in separate files — 8 workflow templates, a command reference, real-world examples, best practices — is all inlined behind broken <details> tags, matching the score-2 anchor 'Minimal structure; content that clearly belongs in separate files is inlined'. It is not 3 because there are no real external references at all, only broken inline collapsibles.	2 / 5
	Total	10 / 20 Passed

Description

45%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 identifies a clear domain but relies on buzzword-laden abstractions instead of concrete actions and omits any 'Use when...' trigger guidance. It is distinguishable but has non-trivial overlap with adjacent CI/CD and release-automation skills.

Suggestions

Replace abstract phrases ('AI swarm coordination', 'intelligent CI/CD pipelines') with concrete actions such as 'generate, optimize, and analyze GitHub Actions workflows; manage PRs, issues, and releases'.

Add an explicit trigger clause, e.g. 'Use when the user asks to create or optimize GitHub Actions workflows, debug failed CI runs, or coordinate multi-repo CI/CD.'

Include natural synonyms and file extensions users actually say (GitHub Actions, .github/workflows, CI/CD, pipelines, workflow YAML) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('GitHub Actions workflow automation') but its actions are generic abstractions — 'AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management' — rather than concrete operations like generate/optimize/analyze, matching the score-2 anchor 'Names the domain but actions are minimal or generic'. It does not reach 3 because no genuinely concrete actions are listed, only buzzword-level categories.	2 / 5
Completeness	It gives a recognizable 'what' (GitHub Actions automation across CI/CD and repo management) but provides no 'when' — there is no 'Use when...' clause or equivalent trigger guidance, so per the judging guidelines completeness is capped at 3, matching 'Has a clear what but when is missing or only weakly implied'. It is not 2 because the what is identifiable rather than extremely vague.	3 / 5
Trigger Term Quality	It includes some natural keywords a user might say ('GitHub Actions', 'CI/CD pipelines', 'repository management') but misses common variations and synonyms, and leans on jargon ('AI swarm coordination') users would not naturally say, fitting the score-3 anchor 'Some relevant keywords but missing common variations or synonyms'. It is not 4 because natural trigger phrasing and synonyms are largely absent.	3 / 5
Distinctiveness Conflict Risk	'GitHub Actions workflow automation' is a recognizable niche, but broad buzzwords ('intelligent CI/CD', 'comprehensive repository management') and the body's own Related Skills list (ci-cd-optimization, release-coordination, swarm-coordination) signal real overlap risk, matching the score-3 anchor 'Somewhat specific but could still overlap with similar skills'. It is not 4 because the overlap with adjacent CI/CD and release skills is more than minor.	3 / 5
	Total	11 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1066 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: ruvnet/ruflo
Path: .agents/skills/github-workflow-automation/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.