CtrlK
BlogDocsLog inGet started
Tessl Logo

auditing-llm-gateway-parity

Audits services/llm-gateway against PostHog/ai-gateway and updates services/llm-gateway/PARITY.md from current implementation evidence. Use when either gateway changes auth, attribution, billing, endpoints, providers, models, routing, or metadata; when reviewing a Python gateway change; or when asked to refresh, verify, or report gateway parity. This skill updates the parity record but does not migrate callers.

69

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 well-structured, token-efficient audit workflow with concrete file paths and executable validation commands. Main gaps are the absence of an explicit fix-and-retry feedback loop in the validate step and no worked classification example.

Suggestions

Add an explicit feedback loop after the Validate commands: 'If oxfmt or markdownlint report issues, fix them and re-run until clean before considering the audit complete.'

Include one short worked example of classifying a single contract difference (e.g. a streaming header mismatch) into the Supported/Blocking/Verify buckets to anchor the classification step.

Consider extracting the per-gateway contract inspection file lists into a reference file so the SKILL.md body stays a concise overview.

DimensionReasoningScore

Conciseness

Lean and dense throughout: it assumes Claude's competence, never explains what a gateway or billing is, and every section adds concrete audit guidance (file paths, classification rules, policy caveats). Each token earns its place.

5 / 5

Actionability

Provides specific file paths to inspect for both gateways and copy-paste-ready validation commands ('gh api repos/PostHog/ai-gateway/commits/main', oxfmt, markdownlint-cli2, git diff --check). Not a 5 because the core comparison work is judgment-based inspection across many files with no worked end-to-end example of classifying a specific difference.

4 / 5

Workflow Clarity

A clear five-step sequence (record revisions, inspect contracts, classify, update record, validate) with an explicit validation block. Not a 5 because the validate step lists commands without spelling out the fix-and-retry feedback loop for when linting/formatting fails.

4 / 5

Progressive Disclosure

Well-organized into clear section headers in a single self-contained file with no nested or buried references, and nothing that clearly belongs in a separate file. Not a 5 because the file exceeds the simple-skill threshold and the per-gateway contract inspection lists could plausibly live in dedicated reference files.

4 / 5

Total

17

/

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.

A strong, specific description with an explicit 'Use when' trigger clause and a clear scope boundary. It cleanly answers both what the skill does and when to invoke it, with low conflict risk.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Audits services/llm-gateway against PostHog/ai-gateway', 'updates ... PARITY.md from current implementation evidence') plus a comprehensive list of contract types (auth, attribution, billing, endpoints, providers, models, routing, metadata), with only minor coverage gaps. Not a 5 because the core verbs are essentially audit + update rather than a broad set of distinct operations.

4 / 5

Completeness

Clearly answers both 'what' (audits and updates the parity record) and 'when' via an explicit 'Use when...' clause with multiple concrete trigger phrases, matching the anchor for explicit what-and-when coverage.

5 / 5

Trigger Term Quality

Good natural trigger coverage with phrases a user would say ('when reviewing a Python gateway change', 'refresh, verify, or report gateway parity') plus an explicit list of changed contract areas. Not a 5 because it lacks synonyms and common shorthand variations users might phrase the request in.

4 / 5

Distinctiveness Conflict Risk

A narrow, specific niche (LLM gateway parity auditing between two named gateways) with distinct triggers and an explicit boundary ('does not migrate callers'), giving minimal conflict risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
PostHog/posthog
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.