kiln-check-deprecation

Check Kiln's model list for deprecated or sunset models across all providers. Use when the user wants to find deprecated models, check model availability, audit the model list for stale entries, or mentions model deprecation/sunset/end-of-life.

Quality

85%

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

88%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.

The body is a strong, highly actionable audit workflow with concrete commands, explicit validation/confirmation gates, and a helpful checklist. Its main weakness is a somewhat dense inline provider-quirk section that could be tightened or moved to a reference file.

Suggestions

Trim or relocate the per-provider API-quirk bullets (Fireworks detail API, OpenRouter ':exacto', Vertex version-suffix handling) into a references/PROVIDERS.md, since check_provider.py already handles them automatically.

Move the manual Bedrock and LiteLLM cross-reference sections into a references/MANUAL_CHECKS.md, keeping only a one-line pointer in Phase 2.

Tighten the 'Providers to skip' list into a single compact line since the rationale per entry is rarely needed at execution time.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and action-oriented with concrete commands throughout, but the provider-quirk bullets (e.g., Fireworks detail API, OpenRouter ':exacto', Vertex versioned aliases) explain behavior the script already handles and could be trimmed, fitting anchor 4 rather than 5.	4 / 5
Actionability	Fully executable guidance throughout — copy-paste bash commands with full script paths, env-var sourcing, jq pipelines for Bedrock/LiteLLM, grep for locating edit lines, and a concrete report table template — matching anchor 5.	5 / 5
Workflow Clarity	A clear 5-phase sequence (Extract → Check → Report → Mark → Verify) with explicit validation checkpoints (Phase 5 count check, 'Ask the user to confirm before making changes') and a final checklist; the destructive/batch cap is satisfied because validation is present, matching anchor 5.	5 / 5
Progressive Disclosure	Scripts are cleanly externalized one level deep via clear paths (scripts/extract_models.py, scripts/check_provider.py) and the body is well-sectioned by phase, but substantial provider-quirk and manual-check detail lives inline in SKILL.md rather than a separate reference file, fitting anchor 4 over 5.	4 / 5
	Total	18 / 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.

The description is well-crafted: it names a specific niche, uses third person, and pairs a clear 'what' with an explicit 'Use when' clause containing multiple natural trigger phrases and synonyms. Its only gap is listing a single broad action rather than several concrete ones.

Dimension	Reasoning	Score
Specificity	Quotes 'Check Kiln's model list for deprecated or sunset models across all providers' — names the domain and one concrete action (check/find deprecated models), but does not list several distinct actions, matching anchor 3 rather than 4.	3 / 5
Completeness	It clearly states the 'what' ('Check Kiln's model list for deprecated or sunset models across all providers') and an explicit 'when' ('Use when the user wants to find deprecated models... or mentions model deprecation/sunset/end-of-life') with concrete trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	Phrases like 'find deprecated models, check model availability, audit the model list for stale entries, or mentions model deprecation/sunset/end-of-life' give good natural-term coverage with synonyms, but a few common variations are absent, fitting anchor 4 over 5.	4 / 5
Distinctiveness Conflict Risk	The Kiln-specific model-deprecation audit niche with distinct triggers ('Kiln's model list', 'deprecated or sunset models across all providers') has minimal conflict risk with other skills, matching anchor 5.	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-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.