test-reasoning

Validate that reasoning parameters are correctly serialized and sent to provider APIs. Use when the user asks to test reasoning serialization, run reasoning tests, verify reasoning config fields, or check that ReasoningConfig maps correctly to provider-specific JSON (OpenRouter, Anthropic, GitHub Copilot, Codex).

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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 tight, actionable skill body that externalizes its 423-line test script appropriately and provides copy-paste commands plus a thorough coverage table. Minor room to tighten the redundant intro and add error-recovery guidance for manual runs.

Suggestions

Drop or condense the opening line ('Validates that ReasoningConfig fields are correctly serialized...') since it duplicates the frontmatter description, letting the body start at Quick Start.

Add a short feedback loop for the manual path, e.g. 'If the expected JSON field is missing or wrong, check ReasoningConfig serialization in the provider adapter before re-running.'

Dimension	Reasoning	Score
Conciseness	Mostly lean with no over-explanation of concepts Claude already knows, but the opening line restates the frontmatter description, a minor redundancy that could be trimmed.	4 / 5
Actionability	Fully executable guidance: a copy-paste script invocation, a complete env-var command for manual runs, and an exhaustive coverage table supplying the concrete values to substitute.	5 / 5
Workflow Clarity	Clear run-then-inspect sequence with verification delegated to the script's JSON assertions, but no explicit error-recovery feedback loop is described for the manual path.	4 / 5
Progressive Disclosure	Well-organized ~50-line overview with a clearly signaled one-level reference to the bundled script (verified to exist at scripts/test-reasoning.sh) and cleanly separated external reference links.	5 / 5
	Total	18 / 20 Passed

Description

92%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 that clearly answers both what the skill does and when to use it, with concrete actions and named providers. The only minor gap is trigger-term synonym coverage, which is inherently limited by the narrow domain.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (validate/serialize/send, test, run, verify, check/map) across four named providers, giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly states what it does ('Validate that reasoning parameters are correctly serialized...') and when to use it with concrete 'Use when the user asks to...' trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases like 'run reasoning tests' and 'test reasoning serialization' plus provider keywords give good coverage, though the narrow domain lacks many synonyms or natural variations.	4 / 5
Distinctiveness Conflict Risk	Clear niche (ReasoningConfig mapping to provider-specific JSON for four named providers) with distinct, specific triggers that minimize overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tailcallhq/forgecode
Path: .forge/skills/test-reasoning/SKILL.md
Commit: 6ed5d37

Reviewed: 24 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.