api-filters

Add, modify, or convert AIP-style query-parameter filters on v3 list endpoints. Use when adding filterable fields to a list API, wiring filter parsing into a handler, converting API filters into pkg/filter predicates, or debugging filter parsing/validation behavior.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%Weight 40%Scale 1-3

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

A high-quality, actionable skill body with executable code, precise file references, and a well-sequenced workflow with mandatory verification steps. The main weakness is progressive disclosure: substantial inline reference material could be moved into bundle files to slim the SKILL.md overview.

Suggestions

Move the full API-layer type table and filter grammar block into a references/ file (e.g. GRAMMAR.md or TYPES.md), leaving a concise summary plus a one-level-deep pointer in SKILL.md.

Deduplicate the 'validation belongs on pkg/filter' and dot-notation explanations, which each appear in multiple sections, to tighten the body further.

Consider extracting the long reference-files list and error-message catalog into a separate reference doc so the main skill stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Dense and assumes Go/AIP/Ent competence with no filler about what filters or libraries are; tables and grammar are reference data rather than padded explanation, though a few points (validation-on-pkg/filter, dot-notation) recur across sections.	3 / 3
Actionability	Provides executable Go snippets, exact file paths with line numbers, concrete commands like 'make gen-api', and real helper signatures that are effectively copy-paste ready.	3 / 3
Workflow Clarity	A clear six-step sequence with explicit validation checkpoints — mandatory service-level tests in Step 5 ('ALWAYS add service level tests') and detailed test-coverage checklists in Step 6 — giving strong feedback loops for verifying the work.	3 / 3
Progressive Disclosure	Well-organized into clear sections, but the ~350-line body inlines heavy reference material (full type tables, the filter grammar) that could be split into a bundle reference file, and no bundle files exist to offload it.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 specific, third-person, and well-scoped, with an explicit 'Use when' trigger clause covering both what the skill does and when to invoke it. It is a strong, low-conflict description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Add, modify, or convert AIP-style query-parameter filters', 'wiring filter parsing into a handler', 'converting API filters into pkg/filter predicates' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Add, modify, or convert...') and when via a 'Use when...' clause enumerating four concrete triggers.	3 / 3
Trigger Term Quality	Covers natural developer phrasing such as 'adding filterable fields to a list API', 'wiring filter parsing into a handler', and 'debugging filter parsing/validation behavior' that a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Scoped to a clear niche — AIP-style query-parameter filters on v3 list endpoints — with distinct triggers unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

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

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: openmeterio/openmeter
Path: .agents/skills/api-filters/SKILL.md
Commit: 5936703

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.