CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

zizmor

Audit GitHub Actions workflows, composite actions, Dependabot configs, and pre-commit configs for security findings using zizmor — template injection, credential persistence, unpinned uses, over-broad permissions, impostor commits. Covers local CLI, auto-fix, zizmor.yml policy, severity-based CI gates, SARIF upload, and pre-commit. Use when asked to "audit my workflows", "run zizmor", "is this workflow safe", "check for template injection", "pin my actions", or "set up a zizmor CI gate". Workflow syntax and shell errors → /platform-skills:github-actions (actionlint). IaC misconfig → /platform-skills:checkov. Image and dependency CVEs → /platform-skills:trivy. Keeping SHA pins fresh → /platform-skills:renovate.

Quality

94%

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

The canonical home for this skill is zizmor in nitinjain999/platform-skills

SKILL.md
Quality
Evals
Security

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 strong, highly actionable command body: executable commands per mode, explicit validation and re-audit loops, and disciplined never/always rules grounded in real tool behavior. The main weaknesses are repeated pinning-policy rationale across sections and a referenced bundle file (references/zizmor.md) that is not present in the bundle.

Suggestions

State the SHA-vs-ref pinning rationale once (Layer 3) and reference it from config mode and 'Always do these' instead of restating the reasoning three times.

Ensure references/zizmor.md ships with the bundle and contains the named sections the body points to ('Triage decision tree', 'Repository patterns', 'CI integration', 'Worked baseline config', audit catalogue), or adjust the body if the file is not bundled.

Collapse the duplicated ownership-boundary routing (top table, wizard lines, and intent-classification rows) into one canonical routing table.

DimensionReasoningScore

Conciseness

The body is information-dense with no known-concept padding, but the SHA-pinning rationale is repeated across Layer 3, the config-mode walkthrough, and 'Always do these', and the ownership-boundary table is restated in the wizard and intent-classification sections. That trimmable redundancy matches the 4 anchor rather than the 5 anchor's 'every token earns its place'.

4 / 5

Actionability

Every mode ships copy-paste-ready commands with exact flags (`zizmor --strict-collection .`, `uvx zizmor@1.29.0`, the full `--persona=auditor --min-confidence=low --collect=all --no-ignores` audit invocation, a dirty-tree guard, concrete zizmor.yml policy blocks, and the pre-commit YAML), plus precise exit-code semantics — matching the 5 anchor's fully executable, common-case-covering guidance.

5 / 5

Workflow Clarity

Mode dispatch, a three-layer wizard, and per-mode flows are clearly sequenced with explicit validation checkpoints and feedback loops: refuse on a dirty tree, show the diff, re-audit what remains after every fix, and 'run the audit again and report what remains'. This matches the 5 anchor's explicit validation and error-recovery structure; the 4 anchor would imply missing checkpoints.

5 / 5

Progressive Disclosure

References to `references/zizmor.md` are one level deep and well signaled with named target sections ('Triage decision tree', 'Repository patterns', 'CI integration', 'Worked baseline config'), and the SKILL.md/reference split is sensible — but no `references/` directory exists in the bundle, so the single referenced file is missing and navigation dead-ends. This lands on the 4 anchor ('minor organization gaps') rather than 5.

4 / 5

Total

18

/

20

Passed

Description

100%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.

An exemplary description: concrete capabilities, explicit trigger phrases in natural user language, and explicit routing away from adjacent tools. Both the what and the when are answered clearly and in third person.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — auditing workflows, composite actions, Dependabot and pre-commit configs for named finding classes ('template injection, credential persistence, unpinned uses, over-broad permissions, impostor commits') plus operational coverage ('local CLI, auto-fix, zizmor.yml policy, severity-based CI gates, SARIF upload'). Third-person voice is used throughout, and no coverage gaps are evident, matching the comprehensive 5 anchor rather than the 4 anchor's 'minor gaps'.

5 / 5

Completeness

Explicitly answers what (two sentences of concrete capabilities and finding classes) and when ('Use when asked to…' with six quoted trigger phrases), exactly matching the 5 anchor pattern; the 4 anchor would require a weaker or less explicit 'when' clause.

5 / 5

Trigger Term Quality

Includes natural user phrasings ('audit my workflows', 'run zizmor', 'is this workflow safe', 'check for template injection', 'pin my actions', 'set up a zizmor CI gate') plus synonyms and file-level terms (zizmor.yml, Dependabot configs, pre-commit configs), matching the 5 anchor's comprehensive natural-term coverage.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (zizmor security auditing of GitHub Actions) and actively disambiguates adjacent tools ('Workflow syntax and shell errors → /platform-skills:github-actions (actionlint). IaC misconfig → /platform-skills:checkov…'), minimizing overlap risk with closely related skills.

5 / 5

Total

20

/

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

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 7 missing

Warning

Total

14

/

16

Passed

Repository

nitinjain999/platform-skills

Path

plugins/platform-skills/skills/zizmor/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.