agent-tuning

Use when changing agent model or effort configuration, adapter mappings, or eval candidate profiles.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-tuning/SKILL.md

Quality

Content

80%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.

An efficient, well-structured internal reference that communicates invariants through concrete named symbols and a regression test list. Its only real weakness is that it is a rule set rather than a sequenced workflow, so workflow clarity is merely adequate.

Suggestions

Add a short numbered 'Adding a new harness' sequence (declare mapping in agentcfg → verify via TestReplayPinsCandidateModelAndEffortOnTheHarness) to lift workflow clarity above 3.

Include one worked before/after example of mapping a model+effort request to a harness's native flags to make the actionability fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Lean, dense reference prose with no padding and no explanation of concepts Claude already knows; every token earns its place and it assumes full competence.	5 / 5
Actionability	Provides concrete, actionable directives with named symbols ('agentcfg', 'agent.NewWithOptions', 'agentcfg.ServedMatchesRequested') and explicit do/don't rules, but lacks worked examples showing exactly how to add a new harness end-to-end.	4 / 5
Workflow Clarity	The body is a set of architectural invariants rather than a sequenced workflow; the 'Regressions' bullet supplies an implicit verification checkpoint, but there is no explicit ordered process with validation steps.	3 / 5
Progressive Disclosure	Under 50 lines, well-organized into focused bullets, self-contained, with a single clearly signaled one-level-deep reference link to eval.md — meeting the simple-skill exception for a top score.	5 / 5
	Total	17 / 20 Passed

Description

78%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 concise, well-targeted description with an explicit 'Use when' trigger and concrete domain actions; its main limitation is that the 'what' and 'when' are fused into one clause rather than separately elaborated.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'changing agent model or effort configuration, adapter mappings, or eval candidate profiles' — but the actions are slightly abstract rather than fully spelled out, leaving minor coverage gaps.	4 / 5
Completeness	Both 'what' and 'when' are present via the explicit 'Use when changing...' clause, but the what and when are merged into a single sentence rather than separately and richly stated, so it falls short of the top anchor.	4 / 5
Trigger Term Quality	Good keyword coverage with natural domain terms ('agent model', 'effort configuration', 'adapter mappings', 'eval candidate profiles') a user in this codebase would say, though synonyms and common variations are absent.	4 / 5
Distinctiveness Conflict Risk	It targets a clear, narrow niche (agent tuning config) with distinct triggers, making conflict with other skills unlikely.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: kunchenguid/no-mistakes
Path: .agents/skills/agent-tuning/SKILL.md
Commit: 9a464c2

Reviewed: 2 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.