github-actions-templates

Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.

1.13x

Quality

68%

Does it follow best practices?

Impact

98%

1.13x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/cicd-automation/skills/github-actions-templates/SKILL.md

The canonical home for this skill is github-actions-templates in wshobson/agents

Quality

Content

53%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 delivers genuinely useful, mostly executable workflow templates organized by clear use-case sections, and its description of trigger conditions is honest. Its two structural problems are that every referenced bundle file is missing (so the skill is effectively a monolith of ~330 lines of inline YAML with broken pointers) and that it offers no guidance for choosing, adapting, or validating a generated workflow.

Suggestions

Actually create the referenced bundle files (assets/test-workflow.yml, assets/deploy-workflow.yml, assets/matrix-build.yml, references/common-workflows.md) and move the full inline YAML for patterns 1, 2, and 4 into them, keeping only a short summary plus the pointer in SKILL.md to remove the duplication.

Add a brief selection/adaptation workflow with a validation checkpoint, e.g.: pick the closest pattern, customize triggers/steps, then validate with `actionlint` or `act --list` before committing.

Fix the placeholder production deploy example (replace "# Deployment commands here" with a concrete deploy command) and pin the Trivy/Snyk actions to tagged versions instead of @master, consistent with the skill's own best-practice #1.

Dimension	Reasoning	Score
Conciseness	The body is code-heavy with almost no concept-explaining padding, but each pattern inlines a complete workflow YAML and then also points to an asset file holding the same content ("Reference: See `assets/test-workflow.yml`"), and the 10-item "Workflow Best Practices" list is largely generic. Mostly efficient with noticeable duplication — the 3 anchor; not 4 because the inline/asset duplication is a genuine token inefficiency.	3 / 5
Actionability	Patterns 1-4 plus the reusable-workflow, security-scan, and approval-gate examples are copy-paste-ready executable YAML. It falls short of 5 because the production deploy example is a placeholder ("echo \"Deploying to production...\"" with "# Deployment commands here") and the Trivy/Snyk steps pin @master, contradicting the skill's own "use specific action versions" practice. Well above the 3 anchor's pseudocode level.	4 / 5
Workflow Clarity	Templates are grouped by use case and the Kubernetes pattern includes verification steps ("kubectl rollout status", "Verify deployment"), but the skill gives no process for selecting or adapting a pattern and no workflow validation checkpoint (e.g., YAML lint or actionlint). Steps exist within patterns but validation at the skill level is implicit — the 3 anchor; not 4 because those checkpoints are missing.	3 / 5
Progressive Disclosure	References are clearly signaled ("Reference: See `assets/test-workflow.yml`" and a "Reference Files" section), but no assets/ or references/ directories exist — all four referenced paths are phantom, and the full workflow content that belongs in those files is inlined in the body instead. This matches the 2 anchor (content that clearly belongs in separate files is inlined); not 3, because navigation to the referenced material actually fails rather than merely being improvable.	2 / 5
	Total	12 / 20 Passed

Description

83%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: it states concrete capabilities in third person and pairs them with an explicit, well-phrased "Use when" trigger clause. The main residual weaknesses are slightly incomplete action coverage (body covers security scanning and matrix builds that the description omits) and a couple of broad trigger phrases that could overlap with other CI/CD skills.

Dimension	Reasoning	Score
Specificity	"Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications" names the domain and several concrete actions (testing, building, deploying), with minor gaps — security scanning, matrix builds, and Kubernetes deployment from the body are not mentioned. It exceeds the 3 anchor (only 1-2 actions) but falls short of the 5 anchor's comprehensive coverage.	4 / 5
Completeness	It explicitly answers both questions: the "what" is "Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications" and the "when" is "Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates" — concrete trigger phrases matching the 5 anchor. Not 4, since the when-clause is already explicit and specific.	5 / 5
Trigger Term Quality	"GitHub Actions", "CI/CD", "automating development workflows", and "reusable workflow templates" are natural phrases users would say. A few natural terms are missing (e.g., "pipeline", ".github/workflows"), so it matches the 4 anchor rather than the 5 anchor's comprehensive synonym/extension coverage.	4 / 5
Distinctiveness Conflict Risk	GitHub Actions is a clear, distinct niche, but the triggers "setting up CI/CD" and "automating development workflows" are broad enough to overlap with closely related CI/CD skills (e.g., GitLab CI). Mostly distinct with minor overlap risk — the 4 anchor; not 5 because not all triggers are GitHub-Actions-specific.	4 / 5
	Total	17 / 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: 7 missing	Warning

	Total	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Path: tests/ext_conformance/artifacts/agents-wshobson/cicd-automation/skills/github-actions-templates/SKILL.md
Commit: a65ce00

Reviewed: 6 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.