CtrlK
BlogDocsLog inGet started
Tessl Logo

managed-model-endpoints

Register a model service in the managed family — a local model server container the daemon starts/stops on demand, or a remote upstream model API (https). Read the runbook, allocate a port (local only), compose idempotent start/stop scripts (local only), register once. Load when the user wants a model service available for inference, or when list_compute shows managed endpoints.

69

Quality

84%

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.

An excellent, highly actionable skill body with executable code, explicit validation feedback loops, and clear sequencing. The only minor gap is progressive disclosure, where some inlined reference-style content could be split into bundle files.

Suggestions

Consider extracting the full bash start script and/or the translation rules into a references/ file (e.g. START_SCRIPT.md) to keep SKILL.md a leaner overview pointing one level deep.

Tighten the cache-ownership derivation prose slightly; the docker inspect/chown logic is valuable but the surrounding explanation is the densest prose in the file.

DimensionReasoningScore

Conciseness

Dense and information-rich, assuming Claude's competence with no padding about basics; a few explanatory asides on cache ownership could be trimmed but most every line earns its place in a fragile domain.

4 / 5

Actionability

Fully executable guidance: a complete register() call with all parameters and a full bash start script with real docker commands, plus concrete translation rules covering the common cases.

5 / 5

Workflow Clarity

Clear sequence (free_port -> register -> compose start -> handle failures) with explicit validation checkpoints (port-mismatch guard, runtime-binding retry, FAILED sticky recovery) and feedback loops for a risky lifecycle operation.

5 / 5

Progressive Disclosure

Single self-contained SKILL.md with no bundle files and clear section headers; well-organized, though the long inline bash script and translation rules could plausibly live in a reference file, leaving minor organization gaps.

4 / 5

Total

18

/

20

Passed

Description

80%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, specific description that answers both what and when with concrete triggers and a distinct niche. The main weakness is trigger-term breadth, which is somewhat technical and could add more natural user phrasings.

Suggestions

Add one or two natural-sounding trigger phrases a user would actually say (e.g. 'serve a local model', 'add a model endpoint') alongside the technical 'list_compute shows managed endpoints' trigger.

Enumerate the registration actions slightly more granularly (e.g. separate 'compose the start script' from 'compose the stop script') to push specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Read the runbook, allocate a port, compose idempotent start/stop scripts, register once') but bundles the script composition into one phrase rather than enumerating each, leaving minor coverage gaps.

4 / 5

Completeness

Clearly states both what ('Register a model service in the managed family') and when ('Load when the user wants a model service available for inference, or when list_compute shows managed endpoints') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes some relevant natural triggers ('wants a model service available for inference', 'list_compute shows managed endpoints') but leans technical and misses common synonyms a user would naturally say.

3 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (daemon-owned managed model endpoints, register-once) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
UnicomAI/wanwu
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.