CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ai-models

Update Grida product model presets, native adapter compatibility and the pinned public Models dependency; distinguish canonical facts from live GG offerings. Use for model selection, client catalogue updates and model-discovery drift.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/ai-models/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 content is a lean, project-specific policy document with genuinely executable commands and explicit validation gates, scoring consistently at 4 across all dimensions. It falls short of 5 mainly through mild redundancy of governance rules, an unnumbered workflow with only implied error-recovery, and inline policy density that would benefit from a reference file.

Suggestions

Consolidate the facts-authoring guardrail (currently stated three different ways across sections 1–2) into a single 'Do not author facts locally' rule to save tokens.

Number the update workflow steps and annotate each command — e.g., note what '--bundle --check' gates and which command to re-run when a check fails — to make the feedback loop explicit.

Move the 'Discovery, execution and recovery' policy detail into a reference file (e.g., references/discovery.md) and keep SKILL.md as a shorter overview with a clearly signaled link.

DimensionReasoningScore

Conciseness

The body contains no padding or explanation of concepts Claude already knows — every line is project-specific policy ('Unknown prices/estimates remain unknown, never zero'). However, the facts-authoring guardrail is restated three ways ('Do not recreate an authored factual catalogue or GG allowlist in Grida', 'It is not a second facts authoring home', 'Source corrections belong in the public Models project, not local overrides'), which is minor redundancy that could be trimmed — anchor 4 rather than 5.

4 / 5

Actionability

A copy-paste-ready command block ('node scripts/ai-catalogue/generate.mjs --bundle --check', 'pnpm --filter @grida/ai test', 'cargo test -p grida-ai --locked') plus concrete paths and identifiers ('data/ai/presets.json', 'catalog.snapshot.legacy()', 'GRIDA-SEC-006') provide mostly executable guidance. Sections 1 and 3 are guardrail prose rather than steps, and the commands are unannotated (no note on what each gates or when to re-run), keeping it at anchor 4.

4 / 5

Workflow Clarity

The update workflow has a clear sequence — read data/ai/README.md, inspect the full old/new released diff, then generate → build → bundle → '--bundle --check' → test → typecheck → cargo test — with real validation checkpoints ('review intentional fixture changes rather than regenerating a baseline to hide drift'). Steps are unnumbered, the command block is a flat list, and error-recovery is implied rather than an explicit feedback loop, so it matches anchor 4 rather than 5.

4 / 5

Progressive Disclosure

Three well-organized sections, an ownership table that doubles as a navigation map, and clearly signaled one-level-deep references to data/ai/README.md and hosted-ai.md. There are no bundle reference files (scripts/ holds only an unreferenced pointer file), and the dense policy in 'Discovery, execution and recovery' (~30 lines of inline rules) is content that could live in a separate reference — anchor 4's 'minor organization gaps'.

4 / 5

Total

16

/

20

Passed

Description

71%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 third-person, explicit about both what the skill does and when to use it, and highly distinct within its niche. Its main weakness is trigger-term quality: the 'when' clause leans on internal jargon ('GG', 'model-discovery drift') rather than phrases a user would naturally say, which also keeps completeness just short of the top anchor.

Suggestions

Add natural-language synonyms to the 'Use for' clause, e.g., 'adding or changing supported AI models', 'model pricing updates', or 'model catalog changes'.

Rewrite 'model-discovery drift' in user-speakable form (e.g., 'when served models differ from the public model catalogue') so it matches what a user would actually type.

Spell out 'GG' (e.g., 'Grida Gateway') once in the description so trigger terms are recognizable without project context.

DimensionReasoningScore

Specificity

Phrases like 'Update Grida product model presets, native adapter compatibility and the pinned public Models dependency' and 'distinguish canonical facts from live GG offerings' name several concrete actions, but jargon-heavy phrasing ('GG offerings', 'native adapter compatibility') leaves minor coverage gaps, matching the 'several specific actions; minor gaps' anchor rather than the comprehensive anchor 5.

4 / 5

Completeness

Both parts are explicit: a clear 'what' ('Update Grida product model presets, native adapter compatibility and the pinned public Models dependency; distinguish canonical facts from live GG offerings') and an explicit 'when' ('Use for model selection, client catalogue updates and model-discovery drift'). It sits above anchor 4's 'when could be more specific' but below anchor 5, whose trigger phrases are concrete and natural rather than technical shorthand.

4 / 5

Trigger Term Quality

The trigger phrase 'Use for model selection, client catalogue updates and model-discovery drift' includes the natural term 'model selection', but 'model-discovery drift' is insider jargon users would rarely say, and common variations/synonyms (e.g., 'adding a model', 'model pricing', 'model catalog sync') are missing — matching anchor 3, not 4.

3 / 5

Distinctiveness Conflict Risk

Domain-specific markers ('Grida product model presets', 'pinned public Models dependency', 'GG offerings') carve out a clear niche with distinct triggers and minimal conflict risk with any other skill.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

referenced_paths_exist

Referenced path issues: 3 missing, 3 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

gridaco/grida

Path

.agents/skills/ai-models/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.