CtrlK
BlogDocsLog inGet started
Tessl Logo

gitops-repo-audit

Audit and validate Flux CD GitOps repositories by scanning local repo files (not live clusters) — runs Kubernetes schema validation, detects deprecated Flux APIs, reviews RBAC/multi-tenancy/secrets management, and produces a prioritized GitOps report. Use when users ask to audit, analyze, validate, review, or security-check a GitOps repo.

78

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

The content is a well-structured, actionable audit workflow: lean prose, executable scripts with validation feedback loops, and a clean progressive-disclosure design where every referenced bundle file actually exists. It neither over-explains basic concepts nor buries detail inline.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: it assumes Claude's competence, omits explanations of what Flux/K8s is, and every line (scripts, commands, grep examples) earns its place without padding.

3 / 3

Actionability

Provides fully executable, copy-paste-ready guidance — 'scripts/discover.sh -d <repo-root>', the mktemp-based validate.sh invocation, and concrete grep examples against the field index — rather than vague direction.

3 / 3

Workflow Clarity

A clear six-phase sequence with explicit validation checkpoints and feedback loops: the validation script exits non-zero with a count, mktemp fallback is handled, and 'before recommending any YAML changes, verify the exact field names' gates the next step.

3 / 3

Progressive Disclosure

The body is an overview that points one level deep to six real reference files (all present in references/) and nineteen real schema field-index files (all present in assets/schemas/), each clearly signaled in a 'Loading References' section and a CRD table.

3 / 3

Total

12

/

12

Passed

Description

100%

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 is concise, specific, and complete: it names concrete actions, provides natural trigger terms, answers both what and when, and is clearly distinguishable from neighboring skills. It is written in third person with no fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'runs Kubernetes schema validation', 'detects deprecated Flux APIs', 'reviews RBAC/multi-tenancy/secrets management', and 'produces a prioritized GitOps report' — matching the level-3 anchor exactly.

3 / 3

Completeness

Explicitly answers both what (the validation/review/report actions) and when via an explicit 'Use when users ask to audit, analyze, validate, review, or security-check a GitOps repo' clause.

3 / 3

Trigger Term Quality

Covers natural trigger terms a user would say — 'audit, analyze, validate, review, or security-check a GitOps repo' — giving good coverage of common phrasings.

3 / 3

Distinctiveness Conflict Risk

Carves a clear niche — Flux CD GitOps repo scanning of local files (not live clusters) — with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 19 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 20 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
fluxcd/agent-skills
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.