CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

76

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

—

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

93%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 lean, highly actionable audit workflow: exact paths and commands, non-obvious policy callouts, and explicit validation. The only gap is the absence of an error-recovery loop after the validation commands fail.

DimensionReasoningScore

Conciseness

Every line is dense, imperative, and project-specific — e.g., 'a change adding a table read needs its posthog-cloud-infra SELECT grant landed in every environment first' and 'An `ai_product` event property does not replace product authentication'. No concept explanations Claude already knows and no padding; each token earns its place.

5 / 5

Actionability

Fully executable: exact commands ('gh api repos/PostHog/ai-gateway/commits/main', the oxfmt/markdownlint-cli2/git diff --check validation block) and precise file paths per gateway for both request and response behavior. Copy-paste ready with specific inspection targets covering the common cases.

5 / 5

Workflow Clarity

Clear five-step sequence (record revisions → inspect contracts → classify evidence → update record → validate) with an explicit validation block of concrete commands. Not score 5 because there is no fix-and-retry feedback loop stating what to do when validation fails; not score 3 because validation checkpoints are explicit, not implicit.

4 / 5

Progressive Disclosure

No bundle files exist and none are needed: the ~60-line body is all execution-time guidance, well-sectioned, with clear one-level pointers to the PARITY.md output target and the sibling migration skill. Nothing that belongs in a separate file is inlined, and references are clearly signaled.

5 / 5

Total

19

/

20

Passed

Description

96%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: concrete actions with named artifacts, an explicit multi-clause 'Use when' trigger set, and an explicit non-goal boundary. The only weakness is the broad 'reviewing a Python gateway change' trigger, which slightly overlaps general code-review skills.

DimensionReasoningScore

Specificity

Names concrete actions with specific artifacts — 'Audits services/llm-gateway against PostHog/ai-gateway and updates services/llm-gateway/PARITY.md from current implementation evidence' — and adds an explicit scope boundary ('does not migrate callers'). Coverage is complete for the skill's narrow job; not score 4 because there is no coverage gap.

5 / 5

Completeness

Both 'what' (audit both gateways and update PARITY.md from implementation evidence) and 'when' (explicit 'Use when...' with three concrete trigger clauses) are clearly answered, matching the top anchor. Not score 4 because the 'when' is fully explicit rather than improvable.

5 / 5

Trigger Term Quality

Three explicit trigger clauses cover natural user phrasings across the domain: 'changes auth, attribution, billing, endpoints, providers, models, routing, or metadata', 'reviewing a Python gateway change', and 'refresh, verify, or report gateway parity'. Comprehensive for this domain; no common variation is missing.

5 / 5

Distinctiveness Conflict Risk

A clear niche (LLM gateway parity auditing) with explicit disambiguation from the sibling migration skill, but 'when reviewing a Python gateway change' is a trigger a general code-review skill could also claim, giving minor overlap risk. Not score 5 because of that overlap; not score 3 because the niche and named repos are highly specific.

4 / 5

Total

19

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

PostHog/posthog

Path

.agents/skills/auditing-llm-gateway-parity/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.