CtrlK
BlogDocsLog inGet started
Tessl Logo

cloudbase-sites-runtime

Use when the user wants to develop, run, preview, save, deploy, or roll back a CloudBase Web app in this conversation as a Lovable/Codex-Sites-like vibe- coding session — i.e. any request that maps to "spin up a React+Vite project, see it live in the browser, iterate, save versions, deploy". Activate ONLY for browser-rendered Web projects based on the CloudBase official React (or Vue) + Vite template. Do NOT activate for: WeChat/Alipay mini-program, React Native / Flutter / Electron, pure cloud functions / CloudRun backends, or Next.js / Nuxt / Astro / Remix / SvelteKit (those frameworks are explicitly out of scope).

72

Quality

88%

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

77%

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

The body is highly actionable with well-sequenced, validated workflows, but it is verbose with some redundant restatement and is monolithic rather than progressively disclosed into reference files. Weak spots are conciseness and progressive disclosure.

Suggestions

Collapse the 'Hard rules' section into the earlier sections it restates (preview-URL, dev-server ownership, two-stage deploy) to remove redundancy and tighten conciseness.

Move the error-code and state-files tables into reference files (e.g. references/error-codes.md, references/state-files.md) and link to them one level deep so the main SKILL.md stays a lean overview.

Trim explanatory asides such as 'Inspired by Codex Sites' saved version model' that do not change what Claude should do.

DimensionReasoningScore

Conciseness

Mostly high-signal operational detail Claude would not know (CLI verbs, flags, error codes, port ranges), but it is padded by a redundant 'Hard rules' section that restates earlier guidance and prose like 'Inspired by Codex Sites' saved version model'. Not a 3 because the repetition and explanatory asides could be trimmed; not a 1 because the bulk is genuinely novel technical content rather than concepts Claude already knows.

2 / 3

Actionability

Provides fully executable, copy-paste-ready guidance: exact CLI subcommands with flags, JSON-parsing rules, an error-code recovery table, state-file paths, and parameterized MCP tool calls. Not below 3 because instructions are concrete and complete rather than pseudocode.

3 / 3

Workflow Clarity

Multi-step flows are explicitly sequenced with validation checkpoints — the numbered 'walked into the conversation' routine, the Save→Deploy→Record→Rollback stages, and pre-flight recovery ('if manageApps fails with no envId... call envQuery... retry'). Not below 3 because error feedback loops (surface logPath, re-validate) are present for the risky deploy/rollback operations.

3 / 3

Progressive Disclosure

Well-organized with clear section headers, but it is a monolithic ~300-line file with the error-code table, state-files table, and all CLI detail inline — content that could be split into one-level-deep reference files. Not a 3 because no bundle/reference files exist and detail that should be separate is inline; not a 1 because sections are clearly labeled and navigable rather than an undifferentiated wall.

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.

The description is specific, trigger-rich, complete, and highly distinctive, with explicit positive and negative activation criteria in third-person voice. It is a strong description with no significant gaps.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "develop, run, preview, save, deploy, or roll back" and "spin up a React+Vite project, see it live in the browser, iterate, save versions, deploy" — matching the score-3 anchor that lists several specific actions.

3 / 3

Completeness

Explicitly answers both what (orchestrate CloudBase Web app develop/preview/save/deploy/rollback) and when ("Use when the user wants..." plus "Activate ONLY for..."). Not below 3 because the 'when' is explicit, not merely implied.

3 / 3

Trigger Term Quality

Natural user-facing terms are well covered ("build me a website", "preview", "deploy", "save", "roll back", "landing page"), which a user would realistically say; not merely technical jargon. Not below 3 because coverage of common phrasings is broad rather than partial.

3 / 3

Distinctiveness Conflict Risk

Clear niche (CloudBase React/Vue + Vite Web apps) with explicit exclusions (mini-program, RN/Flutter/Electron, cloud functions/CloudRun, Next/Nuxt/Astro/Remix/SvelteKit), making wrong-skill triggering unlikely. Not below 3 because the negative scope sharply separates it from adjacent skills.

3 / 3

Total

12

/

12

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
TencentCloudBase/CloudBase-AI-Toolkit
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.