CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-trainer-model

Add a new trainable base model to BOTH trainers end-to-end — the in-app trainer (main Next.js app, src/) and the Training Studio (apps/training-studio). Orchestrates add-ecosystem (if the base model is missing) and add-training-support (main-app wiring), then mirrors the model into the Training Studio catalog, which nothing else covers. New model families default to AI-Toolkit; preserve the Studio engines documented in apps/training-studio/CLAUDE.md. Use when onboarding a new model family for training, or a new version of one — e.g. ZImage, MiniMax H3, a new Flux/Wan variant. Always checks whether @civitai/orchestration-client ships the ecosystem's training input type first.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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 an unusually actionable, well-sequenced workflow: exact greps and commands, a plan-confirmation checkpoint, typecheck/gate-test validation with iterate-until-clean loops, and deep repo-specific gotchas throughout. Its weaknesses are moderate repetition of the feature-flag gating policy and the absence of any reference files to offload the detailed catalog-mirror spec and verification steps.

DimensionReasoningScore

Conciseness

The body is dense with repo-specific facts Claude could not know ('a 4-line re-export shim (grepping it finds nothing, for every model)', 'fail-closed', 'NEVER `check`'), with almost no explanation of known concepts. However the flag-gating policy is restated roughly three times (the intro, the 🔴 callout, Step 3 item 1) and the Step 5 verification section runs long — matches the 4 anchor (efficient, minor trims possible), not 5 due to that repetition, not 3 since the padding is limited.

4 / 5

Actionability

Concrete executable commands throughout: 'grep -niE "<name>" packages/civitai-shared/src/basemodel.constants.ts', 'pnpm --filter @civitai/training-studio-app run typecheck', 'pnpm exec vitest run --project unit* src/utils/__tests__/new-training-models.test.ts', plus exact file lists and a fill-in plan template. Copy-paste ready with specific error-recovery steps ('mossImage → moss', the CONTINUE_FROM_ECOSYSTEM fix); matches the 5 anchor.

5 / 5

Workflow Clarity

Clear Step 0–5 sequence gated on 'Do not touch any file until all three are answered', an explicit confirm-the-plan checkpoint, and validation with feedback loops: both typechecks plus the gate test with 'Iterate until both are clean', a listed common-failures set, and a concrete verify step (dev login, embed check, non-mod gate check). Matches the 5 anchor (explicit validation steps and error-recovery loops).

5 / 5

Progressive Disclosure

Good structure: numbered steps, a recap table mapping concerns across the two trainers, and clearly signaled delegation to sibling skills ('follow it, do not re-derive it here') and to apps/training-studio/CLAUDE.md. But there are no bundle reference files at all — the catalog field-by-field spec (Step 3) and the long verification procedure (Step 5) are inlined in a ~245-line SKILL.md — matching the 4 anchor (good structure, minor organization gaps) rather than 5 (appropriately split content).

4 / 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.

The description is highly specific, in third person, and explicitly states both what the skill does across both trainers and when to use it, with concrete example model names as triggers. Its only weakness is that a few natural phrasings (e.g. 'LoRA', 'make it trainable') are absent, keeping trigger coverage just short of comprehensive.

DimensionReasoningScore

Specificity

Quotes: 'Add a new trainable base model to BOTH trainers end-to-end', 'Orchestrates add-ecosystem... and add-training-support', 'mirrors the model into the Training Studio catalog', 'Always checks whether @civitai/orchestration-client ships the ecosystem's training input type first' — multiple concrete actions in third person covering the full scope. Matches the 5 anchor (comprehensive, concrete actions); not 4 because there are no noticeable coverage gaps.

5 / 5

Completeness

Quotes: 'Add a new trainable base model to BOTH trainers... Orchestrates... mirrors the model into the Training Studio catalog' (clear what) and 'Use when onboarding a new model family for training, or a new version of one — e.g. ZImage, MiniMax H3, a new Flux/Wan variant' (explicit when with concrete triggers). Explicitly answers both what and when, matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

Quotes: 'onboarding a new model family for training, or a new version of one — e.g. ZImage, MiniMax H3, a new Flux/Wan variant', 'trainable base model' — good natural keywords plus concrete model names users would actually say. Falls between 4 and 5: solid coverage but misses common phrasings like 'LoRA', 'make it trainable', or 'training support', so not the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

Quotes: 'mirrors the model into the Training Studio catalog, which nothing else covers' and explicit orchestration of 'add-ecosystem' and 'add-training-support' — the description carves out a clear niche relative to its sibling skills. Minimal conflict risk; matches the 5 anchor.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository

civitai/civitai

Path

.claude/skills/add-trainer-model/SKILL.md

Reviewed

Table of Contents

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.