kiln-check-finetune-deprecation

Check Kiln's fine-tunable model list for deprecated or unsupported base models. Use when the user wants to audit fine-tuning support, check if fine-tune base models are still valid, or mentions fine-tune model deprecation.

Quality

82%

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

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, highly actionable audit skill with concrete commands, a real bundled script, and a clear phased workflow. The main improvements would be adding an explicit validate-fix-retry loop in the verify phase and pulling some inline interpretation prose into a separate reference.

Suggestions

Add an explicit validate-fix-retry loop to Phase 5 (e.g., 'if pytest fails, review failures, fix, and re-run until passing') to satisfy the destructive/batch feedback-loop expectation.

Consider moving the Background and Fireworks 'Interpreting results' detail into a short references/ doc, keeping SKILL.md as a leaner overview with a clearly signaled link.

Trim or collapse the illustrative Phase 3 report block to reduce token cost, since the actual counts vary and the format is self-evident from the field descriptions.

Dimension	Reasoning	Score
Conciseness	Dense and operational with no padding of concepts Claude already knows; the only trimmable material is the illustrative report block and some interpretive prose that earns most of its place.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands with concrete file paths, env vars, and API field names, backed by a real bundled check script covering the common cases.	5 / 5
Workflow Clarity	Five clearly sequenced phases plus a checklist and a pytest verification step, but Phase 5 lacks an explicit validate-fix-retry feedback loop for the batch/destructive remediation actions.	4 / 5
Progressive Disclosure	Well-organized into clear sections with a single one-level-deep bundle script referenced by concrete path; minor gap is that some inline Background/interpretation prose could live in separate reference files.	4 / 5
	Total	17 / 20 Passed

Description

82%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, well-targeted description that clearly answers both what the skill does and when to use it, with natural trigger phrases and minimal conflict risk. The only weakness is that it lists a single core action rather than enumerating several concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain (Kiln fine-tunable models) and one concrete action (checking for deprecated/unsupported base models), but does not enumerate multiple specific actions, matching the '1-2 concrete actions' anchor.	3 / 5
Completeness	Explicitly states both what it does and when to use it, with a concrete 'Use when...' clause listing multiple trigger conditions.	5 / 5
Trigger Term Quality	Includes natural trigger phrases a user would say ('audit fine-tuning support', 'check if fine-tune base models are still valid', 'mentions fine-tune model deprecation'), though it leans heavily on 'fine-tune' and lacks synonym variety.	4 / 5
Distinctiveness Conflict Risk	Targets a narrow, specific niche (Kiln fine-tune base-model deprecation auditing) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	17 / 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: Kiln-AI/Kiln
Path: .agents/skills/kiln-check-finetune-deprecation/SKILL.md
Commit: ff39535

Reviewed: ~22 hours 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.