make-github-actions-workflow

Create GitHub Actions workflows for CI, automation, or PR management. Use when asked to create, scaffold, or add a GitHub Actions workflow (.yml file under .github/workflows/).

Quality

91%

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

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, highly actionable skill body with executable code, clear sequencing, and explicit validation checkpoints that avoids teaching basics. Its one weakness is progressive disclosure: with no bundled reference files, all material lives inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude already knows GitHub Actions and skips basic explanations, jumping straight into repo-specific conventions and concrete code; every section (permissions, scripting, error handling, patterns) earns its tokens without padding.	3 / 3
Actionability	It provides fully executable JavaScript snippets (PR commenting, collaborator-permission check, SHA-tag duplicate prevention, base64 file reading) and a copy-paste YAML template with concrete conventions like actions/github-script@v8 and per_page: 100.	3 / 3
Workflow Clarity	A clear five-step sequence (understand requirements, choose trigger, write, add guards, validate) is capped by an explicit Step 5 validation checklist and a Step 1 requirement checklist, providing the checkpoints and feedback loop the rubric rewards.	3 / 3
Progressive Disclosure	There are no bundle files at all, so the ~180-line body is a monolithic single file with content (common patterns, detailed convention examples) that could plausibly be split out; the only references are external URLs rather than one-level-deep bundled files, so it is well-organized but not genuinely split.	2 / 3
	Total	11 / 12 Passed

Description

90%

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, well-scoped description that states concrete capabilities and provides an explicit, naturally-worded trigger clause with the canonical file location. The only soft spot is specificity, since the listed verbs describe one action rather than distinct capabilities.

Dimension	Reasoning	Score
Specificity	It names the domain and use cases ('Create GitHub Actions workflows for CI, automation, or PR management') and offers several verbs ('create, scaffold, or add'), but those verbs are near-synonyms of a single action rather than distinct capabilities, so it stops at naming domain and some actions without being comprehensive.	2 / 3
Completeness	It explicitly answers both what it does ('Create GitHub Actions workflows for CI, automation, or PR management') and when to use it via an explicit 'Use when...' clause, matching the anchor for clearly answering both.	3 / 3
Trigger Term Quality	'Use when asked to create, scaffold, or add a GitHub Actions workflow (.yml file under .github/workflows/)' mirrors how users actually phrase the request and includes the natural file extension and path, giving good coverage of terms users would say.	3 / 3
Distinctiveness Conflict Risk	The narrow niche of GitHub Actions workflow files under .github/workflows/ with concrete triggers makes it clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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: dotnet/efcore
Path: .agents/skills/make-github-actions-workflow/SKILL.md
Commit: 61317c9

Reviewed: 5 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.