CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

provider-model-refresh

Use the September 2026 image, video, speech and Avatar V adapters with explicit model/host contracts.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/provider-model-refresh/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 dense and lean operational reference: exact model IDs, per-host parameter rules, validation checkpoints, and paid-job recovery guidance with essentially zero padding. Its main weaknesses are that all per-provider detail lives inline in SKILL.md with no reference-file split, and no complete worked request example is provided.

DimensionReasoningScore

Conciseness

Nearly every line states a provider-specific fact Claude could not know, e.g. "fal v4 accepts at most 5,000 characters and has no speed/style control. Direct v4 accepts up to 10,000." and "LTX-2.5 supports text/image/audio generation, not retake or extend." There is no tutorializing, no explanation of known concepts, and no padding to trim, matching the lean anchor rather than the score 4 "minor over-explanation" anchor.

5 / 5

Actionability

Concrete specifics throughout: exact IDs ("gpt-image-2.5-flare", "kling-o3-standard", "eleven_v4"), parameter names ("image_path", "mask_path", "resume_job"), env requirements ("use FAL_KEY, not the official Kling credentials"), and numeric limits ("up to 14 reference images", "at most 2,000 UTF-16 code units"). Score 5 is not reached because parameters and values are never assembled into one complete worked request example covering a common case end to end.

4 / 5

Workflow Clarity

Sequenced steps and checkpoints are present: "First `list_looks` or `inspect_look`... before POST", "checked-in schemas under tools/provider_contracts validate the complete request before submission", "`dry_run=true` validates and prices the exact request without generating", and the timeout recovery loop "pass the returned `resume_job` to the same tool... check the provider dashboard before submitting again". Score 5 is not reached because the core route-validate-submit-recover flow is never laid out as a single ordered sequence; checkpoints are scattered across sections.

4 / 5

Progressive Disclosure

Section headers are clear (Routing, Image requests, Video and jobs, Speech and music, Avatar V) and the one true reference is a well-signaled link to [provider-refresh-oct23], but roughly 120 lines of per-provider contract detail are inlined in SKILL.md that would navigate better as per-provider reference files, and other pointers (AGENT_GUIDE.md, docs/provider-update-plan-2026-10-03.md, tools/provider_contracts) are prose mentions rather than clearly signaled references. This matches the score 3 anchor of structure present but content that should be separate is inline; not 4 because the bulk detail belongs at reference depth, not 2 because organization is genuinely good.

3 / 5

Total

16

/

20

Passed

Description

53%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 names a distinct, well-scoped niche but is thin as a trigger document: it says what the skill governs without listing concrete operations and gives no guidance on when to invoke it. Natural user vocabulary is only partially covered, leaning on internal jargon like "model/host contracts".

Suggestions

Add an explicit trigger clause, e.g. "Use when generating or editing images, video, speech, music, or HeyGen avatar content with the September 2026 provider models."

Include natural synonyms users would actually say — text-to-speech, voiceover, avatar video, image editing, music generation — instead of jargon like "adapters" and "model/host contracts".

Name one or two concrete operations (e.g., "route exact model IDs per host and validate requests against provider contracts") to sharpen the what.

DimensionReasoningScore

Specificity

"Use the September 2026 image, video, speech and Avatar V adapters with explicit model/host contracts" names the media-generation domain and one concrete commitment (explicit model/host contracts), but enumerates no specific operations such as routing, editing, or synthesis. It is above score 2 because the contract requirement is more concrete than a purely generic action, but below 4 because no list of concrete actions is given.

3 / 5

Completeness

The "what" is stated clearly (use the refreshed adapters with explicit model/host contracts), but there is no "Use when..." clause or equivalent trigger guidance, which the rubric caps at 3. Score 4 is not earned because the "when" is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

"image, video, speech and Avatar V" are natural domain keywords, but common user phrasings like "voice", "text-to-speech", "music", "avatar video", or "generate" are missing, and "adapters" and "model/host contracts" are internal jargon users would not say. Coverage gaps exceed the "a few natural terms missing" bar of score 4.

3 / 5

Distinctiveness Conflict Risk

"September 2026 ... Avatar V adapters" carves a clear niche with low conflict risk, but the broad "image, video, speech" terms could overlap closely related media-generation skills (such as the sibling provider-refresh-oct23 skill) and no trigger phrases distinguish it. Not 5 due to that sibling overlap; not 3 because the scope is far more specific than generic media handling.

4 / 5

Total

13

/

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: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

calesthio/OpenMontage

Path

.agents/skills/provider-model-refresh/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.