Name: github-workflow-automation
Rating: 42.4 (1 reviews)
Author: administrakt0r

github-workflow-automation

Patterns for automating GitHub workflows with AI assistance, inspired by [Gemini CLI](https://github.com/google-gemini/gemini-cli) and modern DevOps practices.

Quality

43%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/github-workflow-automation/SKILL.md

The canonical home for this skill is github-workflow-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

46%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 a rich, concrete catalog of GitHub Actions patterns but is an unsplit ~840-line monolith with several non-executable snippets and no validation checkpoints on destructive workflows. It is actionable in places yet would benefit from splitting into reference files and adding verification steps.

Suggestions

Split each numbered section into one-level-deep reference files (e.g. references/pr-review.md, references/triage.md, references/git-ops.md) and keep SKILL.md as a concise overview pointing to them.

Add explicit validation/checkpoint steps to destructive and batch workflows — verify rollback target exists, dry-run rebase before force-push, confirm branch list before deletion.

Make code snippets fully executable by either defining the referenced helpers (analyzeIssue, ai.analyze, callAI, smartCherryPick's affectedFiles) or noting they are illustrative pseudocode.

Dimension	Reasoning	Score
Conciseness	The body avoids over-explaining known concepts and is mostly code, but ~840 lines of full inlined workflow files is lengthy; it is mostly efficient yet could be tightened by trimming redundant scaffolding, matching the 'mostly efficient but could be tightened' anchor rather than the lean 4.	3 / 5
Actionability	Most snippets are concrete copy-paste YAML, but several reference undefined helpers (analyzeIssue, ai.analyze, ai.chat, affectedFiles, callAI), leaving them non-executable as written; this matches 'some concrete guidance but incomplete; missing key details' rather than the fully executable 4.	3 / 5
Workflow Clarity	Sequences are present, but destructive/batch workflows (rollback, force-push rebase, branch deletion) lack validation or verification checkpoints, so per the destructive-operations cap workflow_clarity cannot exceed 3 even though steps are listed.	3 / 5
Progressive Disclosure	No bundle files exist and the entire skill is a monolithic ~840-line single file with large blocks that clearly belong in separate reference files, matching the 'minimal structure; content that clearly belongs in separate files is inlined' anchor better than 3.	2 / 5
	Total	11 / 20 Passed

Description

41%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 names the GitHub-automation-with-AI niche but is generic: it enumerates no concrete capabilities and omits any 'Use when...' trigger guidance. It is reasonably distinct from other skills yet under-specified for triggering.

Suggestions

Replace 'Patterns for automating...' with enumerated concrete actions, e.g. 'Automates AI-powered PR reviews, issue triage and labeling, smart test selection, and rollback workflows in GitHub Actions.'

Add an explicit trigger clause, e.g. 'Use when setting up GitHub Actions that call an LLM for review, triage, deployment risk assessment, or git operations.'

Include natural user keywords such as 'GitHub Actions', 'CI/CD pipeline', 'pull request review', and 'issue triage' so the description matches what users actually say.

Dimension	Reasoning	Score
Specificity	The phrase 'Patterns for automating GitHub workflows with AI assistance' names the domain but lists no concrete actions (e.g. PR review, triage, rollback), matching the 'names the domain but actions are minimal or generic' anchor; it falls below 3 which requires 1-2 enumerated concrete actions.	2 / 5
Completeness	It states clearly what the skill covers ('automating GitHub workflows with AI assistance') but provides no 'Use when...' clause or equivalent trigger guidance, so per the judging guideline a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Only generic keywords ('GitHub workflows', 'AI assistance') appear with none of the natural user phrases ('GitHub Actions', 'CI/CD', 'PR review', 'issue triage'), matching the 'one or two generic keywords; missing natural phrases' anchor rather than 3 which needs more relevant coverage.	2 / 5
Distinctiveness Conflict Risk	'GitHub workflows with AI assistance' carves a mostly-distinct niche with only minor overlap against general DevOps or git skills, matching the 'mostly distinct; minor overlap risk' anchor better than 3 or 5.	4 / 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 (850 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/github-workflow-automation/SKILL.md
Commit: 57c135b

Reviewed: 4 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.