github-agentic-workflows

Authors, reviews, installs, and debugs GitHub Agentic Workflows in repositories, including workflow markdown, frontmatter, gh aw compile and run flows, safe outputs, security guardrails, and operational patterns. Use when creating or maintaining GH-AW automation. Don't use for standard deterministic GitHub Actions YAML, generic CI pipelines, or non-GitHub automation systems.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%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.

A well-structured operational skill: fully actionable commands, clear step sequencing with validation gates, and conditionally-gated one-level references. The main improvements are moving version-pinned and edge-case detail out of the main body and into the existing reference files.

Suggestions

Move version-sensitive compiler details (e.g., the 'gh aw v0.58.3' engine/tool schema notes) into references/troubleshooting.md or a dedicated compatibility section so they don't age the main body.

Trim Steps 3-6 by relocating rarely-needed edge-case guidance (matrix concurrency, wrapper permission inheritance, force-delete host repo) into references/security-and-operations.md or troubleshooting.md, keeping the main body to the core path.

Consider adding a short 'Quick reference' section mapping each task mode to its reference file so navigation is even more direct.

Dimension	Reasoning	Score
Conciseness	The body is lean and imperative with no padding and no explanation of concepts Claude already knows, but it inlines time-sensitive version-pinned facts ('In `gh aw v0.58.3`, `engine.max-turns` is not supported for Copilot...') outside any 'old patterns'/'deprecated' section.	4 / 5
Actionability	Concrete, executable commands throughout ('gh aw validate --strict', 'gh aw fix --write', 'gh aw trial ./.github/workflows/<workflow>.md', 'gh secret list -R <host-repo>') with specific, non-obvious operational details covering the common cases.	5 / 5
Workflow Clarity	Six clearly sequenced steps with explicit validation checkpoints ('Run gh aw validate --strict before treating a workflow as ready', compile only after validation succeeds) and a dedicated Error Handling section providing fix-then-retry feedback loops.	5 / 5
Progressive Disclosure	Four real, one-level-deep reference files (verified present: authoring.md, examples.md, security-and-operations.md, troubleshooting.md) each gated by an explicit read condition, plus an assets template and a script. However, the 90-line body inlines substantial operational detail (e.g., compiler-version quirks, auth edge cases) that could be split into the references.	4 / 5
	Total	18 / 20 Passed

Description

92%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.

A strong description: third-person, specific, comprehensive, with explicit positive and negative trigger guidance. The only gap is a few missing natural synonym phrases users might use when asking for this skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Authors, reviews, installs, and debugs') and enumerates the concrete surfaces ('workflow markdown, frontmatter, gh aw compile and run flows, safe outputs, security guardrails, and operational patterns'), giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (author/review/install/debug with concrete artifacts) and when ('Use when creating or maintaining GH-AW automation'), plus negative triggers ('Don't use for standard deterministic GitHub Actions YAML, generic CI pipelines, or non-GitHub automation systems').	5 / 5
Trigger Term Quality	Includes natural terms users would say ('GitHub Agentic Workflows', 'GH-AW automation', 'GitHub Actions YAML'), but misses a few common synonyms users might use such as 'Copilot agents', 'agentic Actions', or '.md workflows'.	4 / 5
Distinctiveness Conflict Risk	Clear niche (GitHub Agentic Workflows) with explicit exclusion of adjacent territories (standard Actions YAML, generic CI pipelines, non-GitHub automation), making wrong-skill triggers unlikely.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: webmaxru/web-ai-agent-skills
Path: .github/skills/github-agentic-workflows/SKILL.md
Commit: 8d120d6

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.