CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gh-actions-validator

Validate use when validating GitHub Actions workflows for Google Cloud and Vertex AI deployments. Trigger with phrases like "validate github actions", "setup workload identity federation", "github actions security", "deploy agent with ci/cd", or "automate vertex ai deployment". Enforces Workload Identity Federation (WIF), validates OIDC permissions, ensures least privilege IAM, and implements security best practices.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/devops/jeremy-github-actions-gcp/skills/gh-actions-validator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 is lean and well-sectioned but lacks executable guidance: instructions are high-level directives with no commands, the only code example is corrupted YAML, and bundle assets (scripts) are undiscoverable while one referenced file does not exist. Validation and error-recovery checkpoints are absent from the workflow.

Suggestions

Make the instructions executable: reference the bundled scripts directly (e.g., step 1: 'Run scripts/validate-workflow.sh .github/workflows/ and fix every finding before proceeding'; step 8: 'Provide scripts/setup-wif.sh output'), and replace the mangled 'Output' YAML with a complete, copy-paste-ready WIF workflow snippet.

Add a validation feedback loop: after auditing and again after deploying, include an explicit validate → fix → re-validate checkpoint (e.g., 'If validation fails, consult references/errors.md, fix the issue, and re-run the validator before continuing').

Fix bundle navigation: remove the dangling ${CLAUDE_SKILL_DIR}/docs/wif-setup.md reference (or add the file), and remove or integrate the orphaned references/ARD.md and references/PRD.md, which are never referenced from the body.

DimensionReasoningScore

Conciseness

The body is tight — no explanations of concepts Claude already knows, and the Overview is two efficient sentences — but the Prerequisites list could be trimmed and the broken, incomplete YAML in 'Output' wastes tokens on non-executable fragments, so it is not anchor 5.

4 / 5

Actionability

Steps name concrete specifics ('.github/workflows/', 'id-token: write', 'no owner/editor roles') but give no executable commands or code, and the 'Output' section is malformed, truncated YAML (a stray '--project=${{ secrets.GCP_PROJECT_ID }}' line with no command) — matching anchor 3's 'pseudocode instead of executable code; missing key details' rather than anchor 4.

3 / 5

Workflow Clarity

The 8 numbered steps form a clear sequence, but there are no validation checkpoints or feedback loops for the skill's own process (no 'run validation, fix, re-run' guidance), matching anchor 3 'sequence present but checkpoints missing or implicit' rather than anchor 4's 'most checkpoints present'.

3 / 5

Progressive Disclosure

The two body references (references/errors.md, references/examples.md) exist and are clearly signaled one level deep, but 'WIF setup guide in ${CLAUDE_SKILL_DIR}/docs/wif-setup.md' is a dangling reference to a file absent from the bundle, and the bundled scripts/validate-workflow.sh and scripts/setup-wif.sh are never mentioned despite directly implementing steps 1 and 8 — real navigation gaps, not the 'minor organization gaps' of anchor 4.

3 / 5

Total

13

/

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 with explicit trigger phrases and a clear, niche domain scope. Its main flaws are a malformed opening sentence ('Validate use when validating...') and one generic filler clause ('implements security best practices').

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Enforces Workload Identity Federation (WIF)', 'validates OIDC permissions', 'ensures least privilege IAM' — but 'implements security best practices' is generic filler and the opening 'Validate use when validating GitHub Actions workflows' is garbled, so it falls short of the comprehensive anchor 5.

4 / 5

Completeness

Both 'what' (enforces WIF, validates OIDC permissions, ensures least privilege IAM) and 'when' are explicitly stated, with the 'when' delivered as concrete trigger phrases ('Trigger with phrases like...'), matching the anchor-5 pattern; it is not anchor 4 because the 'when' is already maximally explicit and specific.

5 / 5

Trigger Term Quality

Explicit natural phrases are given — 'validate github actions', 'setup workload identity federation', 'github actions security', 'deploy agent with ci/cd', 'automate vertex ai deployment' — good coverage, though common variations like 'WIF', 'github actions workflow', or 'GCP deployment' are missing, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

The niche (GitHub Actions deploying to Google Cloud/Vertex AI via WIF) is distinct, but broad triggers like 'validate github actions' and 'github actions security' carry minor overlap risk with generic GitHub Actions linting/security skills, fitting anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

jeremylongshore/tons-of-skills-marketplace

Path

plugins/devops/jeremy-github-actions-gcp/skills/gh-actions-validator/SKILL.md

Reviewed

Table of Contents

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.