github-actions-validator

Comprehensive toolkit for validating, linting, and testing GitHub Actions workflow files, custom local actions, and public actions. Use this skill when working with GitHub Actions YAML files (.github/workflows/*.yml), validating workflow syntax, testing workflow execution with act, or debugging workflow issues.

Quality

86%

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

85%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.

Highly actionable and well-structured content: executable commands with verified flags, a clear five-step workflow with feedback loops, and exemplary one-level-deep reference organization. The main cost is token efficiency — duplicated command blocks and two near-identical reference tables inflate the body without adding guidance.

Suggestions

Merge the 'Reference Files Summary' table into the final 'References' table (or keep only one) — they cover the same six files with nearly identical content.

Drop the repeated validation commands from 'Validating Resource Types' and 'Quick Examples' since Quick Start already shows all four invocations; one pointer back would suffice.

Trim the 'CRITICAL: Assistant Workflow (MUST FOLLOW)' emphasis ('Skipping any step is non-compliant') to a plain heading — the numbered steps already enforce the sequence.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tables and commands, but there is real duplication: the same validation commands appear in Quick Start, Validating Resource Types, and Quick Examples, and the "Reference Files Summary" table largely repeats the final "References" table. The "CRITICAL ... Skipping any step is non-compliant" framing is padded emphasis Claude doesn't need, fitting the 'could be tightened' anchor at 3 rather than 4.	3 / 5
Actionability	Every instruction is a copy-paste-ready command ("bash scripts/validate_workflow.sh --lint-only .github/workflows/ci.yml") with verified flags (--lint-only, --test-only, --check-versions all exist in the script), plus a complete worked example with full YAML before/after — fully executable coverage of the common cases.	5 / 5
Workflow Clarity	A five-step mandatory workflow is explicitly sequenced (run script → consult reference per error → quote fix → verify actions → summarize), backed by an error-to-reference mapping table, and includes an explicit feedback loop ("Fix issues" then re-run validation in Example 2), matching the top anchor's validate-fix-retry pattern.	5 / 5
Progressive Disclosure	The body is a clear overview with well-signaled, one-level-deep references — all six referenced files (common_errors.md, runners.md, action_versions.md, act_usage.md, actionlint_usage.md, modern_features.md) exist in references/ and are navigated via tables with explicit "When to Use" columns; bulk detail (error catalogs, runner specs, version tables) is correctly split out.	5 / 5
	Total	18 / 20 Passed

Description

87%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 clearly and explicitly states what the skill does and when to use it, with concrete trigger phrases and file-path patterns that make false-positive triggering unlikely. The only weakness is minor: the opening "Comprehensive toolkit" is mild buzzword padding and a few natural synonyms (e.g., CI) are absent.

Dimension	Reasoning	Score
Specificity	Names three concrete actions ("validating, linting, and testing") across three resource types ("workflow files, custom local actions, and public actions"), matching the 'several specific actions; minor gaps' anchor rather than 5 because the verbs stay somewhat generic and don't name the underlying tools in the description itself.	4 / 5
Completeness	Explicitly answers both: what ("validating, linting, and testing GitHub Actions workflow files, custom local actions, and public actions") and when ("Use this skill when working with GitHub Actions YAML files (.github/workflows/*.yml), validating workflow syntax, testing workflow execution with act, or debugging workflow issues") with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Strong natural coverage — "GitHub Actions", "workflow", "YAML files", ".github/workflows/*.yml", "act", "debugging" — but common variations like "CI" or "CI pipeline" are missing, so it falls just short of the comprehensive-synonyms anchor at 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (GitHub Actions validation with named tooling and file paths) with distinct triggers like ".github/workflows/*.yml" and "act"; no plausible overlap with adjacent skills such as general YAML linting.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: pantheon-org/tekhne
Path: skills/ci-cd/github-actions/validator/SKILL.md
Commit: a1083f4

Reviewed: 2 hours 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.