uncloud

Use when managing an Uncloud cluster — deploying services, configuring Caddy ingress, adding static proxy routes for non-cluster devices, publishing ports, scaling, inspecting logs, or managing machines and volumes with the `uc` CLI.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, highly actionable CLI reference with executable commands and well-organized sections, but it is a monolithic single-file document with no progressive disclosure to bundle files and lacks explicit validation checkpoints around its destructive rm/deploy operations.

Suggestions

Add explicit validation/verification steps before destructive and batch operations — e.g. recommend `uc service inspect`/`uc machine ls` confirmation before `uc service rm`/`uc machine rm`, and a post-deploy health check after `uc deploy --recreate`.

Split the full CLI command tables and the Compose File Extensions reference into a separate references/ file (e.g. CLI-REFERENCE.md) and link to it from SKILL.md, keeping the overview and core workflows inline for one-level-deep progressive disclosure.

Add a brief feedback loop for the external-device routing recipe (what to check if the block is missing from `uc caddy config`, referencing the existing 'Caddy admin socket unreachable' common mistake).

Dimension	Reasoning	Score
Conciseness	The body is dense reference material — command tables, flags, and executable snippets — with no padding explaining concepts Claude already knows; the only prose ('How It Works', 'Core Concepts') covers Uncloud-specific details like the WireGuard mesh and 10.210.0.0/16 overlay. Not a 2 because every section earns its place rather than including unnecessary explanation.	3 / 3
Actionability	Provides copy-paste-ready `uc` commands, flag references, full compose extension examples (`x-ports`, `x-caddy`, `x-machines`), and a complete external-device routing recipe. Not a 2 because the guidance is fully executable rather than pseudocode or abstract description.	3 / 3
Workflow Clarity	The external-device routing workflow is clearly numbered with a verify step (`uc caddy config`), but destructive operations (`uc machine rm`, `uc service rm`, `uc volume rm`) and batch deploys lack explicit pre-validation checkpoints or feedback loops, which the rubric caps at 2. Not a 3 because there is no validation gate before destructive/batch actions; not a 1 because sequences are present and one workflow does include verification.	2 / 3
Progressive Disclosure	The body is a well-sectioned ~337-line monolithic CLI reference with no bundle files and no external references, fitting the 2-anchor's 'content that should be separate is inline' (e.g. the full command tables and compose-extension reference could live in separate files). Not a 3 because there are no one-level-deep references to split the material; not a 1 because internal sectioning is clear rather than a wall of text.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 with an explicit 'Use when' trigger and a comprehensive list of concrete capabilities tied to the `uc` CLI. It uses third-person/trigger voice and avoids fluff, conflicting with nothing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'deploying services, configuring Caddy ingress, adding static proxy routes for non-cluster devices, publishing ports, scaling, inspecting logs, or managing machines and volumes' — tied to the `uc` CLI, matching the 3-anchor's 'lists multiple specific concrete actions'. It is not a 2 because the action set is comprehensive and specific rather than naming only a domain and a few actions.	3 / 3
Completeness	Explicit 'Use when managing an Uncloud cluster ...' trigger answers 'when', and the enumerated actions with `uc` CLI answer 'what', matching the 3-anchor that requires both an explicit trigger and a clear capability statement. Not a 2 because the 'when' is explicit, not merely implied.	3 / 3
Trigger Term Quality	Uses natural operator phrasing a user would actually say — 'managing an Uncloud cluster', 'deploying services', 'configuring Caddy ingress', 'publishing ports', 'scaling', 'inspecting logs' — with good coverage of variations. Not a 2 because it covers the common trigger terms a cluster operator would voice, not just a single keyword.	3 / 3
Distinctiveness Conflict Risk	The 'Uncloud cluster' / '`uc` CLI' / 'Caddy ingress' niche is highly specific and unlikely to fire for unrelated skills. Not a 2 because the triggers are distinct rather than overlapping with generic container or proxy skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Commit: 754b8dd

Reviewed: 4 days 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.