cloudrun-development

CloudBase Run backend development rules (Function mode/Container mode). Use this skill when deploying backend services that require long connections, multi-language support, custom environments, AI agent development, or migrating existing/GitHub apps that need VPC access to MySQL/PostgreSQL/Redis. Also use when diagnosing CloudRun container deploy failures (deploy_failed, readiness/probe failed, image won't start, docker.io pull loops) or a deploy stuck behind a running deploy task. For stateless HTTP services, prefer HTTP cloud functions.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%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.

A highly actionable, well-structured operational guide with strong workflow validation and clean progressive disclosure to two real reference files. The main weakness is conciseness: the same rules are restated bilingually and across multiple sections, inflating the token budget without adding new guidance.

Suggestions

Collapse the bilingual duplication: keep one canonical statement of each decision rule (e.g. the HTTP-cloud-function-first and SDK-over-TCP-direct gates) instead of restating them in the Activation Contract, Overview, and Chinese sections.

Merge the overlapping 'Common mistakes / gotchas', 'Minimal checklist', 'Best practices', and 'Troubleshooting hints' lists into a single section — most entries repeat the same warnings (don't raise InitialDelaySeconds, don't copy client credentials, set VpcConf).

Trim the restated deployment sequence: the 'How to use this skill' step list and the 'Container deploy failure SOP' cover ground already detailed in 'Tool routing' and the SOP body; consolidate to one canonical ordered flow.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no padding explaining what CloudRun/Dockerfiles are), but the same guidance is restated across the Activation Contract, bilingual Chinese decision sections, How-to-use, Best practices, and Troubleshooting — noticeable duplication that could be tightened.	3 / 5
Actionability	Copy-paste-ready JSON command examples (deploy, init, run, imageUrl), exact tool actions and parameter names (serverConfig.VpcConf, EnvParams, CLOUDBASE_APIKEY), concrete error strings, decision tables, and a Dockerfile snippet cover the common cases.	5 / 5
Workflow Clarity	Sequenced deploy steps with explicit validation checkpoints (poll envStatus until Status=normal, two-log comparison with a 20-40s gap, 'do not raise InitialDelaySeconds until logs prove') and feedback loops (initEnv -> poll -> deploy; validate -> fix -> retry) for destructive/batch deploy operations.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references to two real bundle files (references/vpc-and-database.md, references/image-deploy-troubleshooting.md) and a Reference index; detail is appropriately offloaded rather than inlined.	5 / 5
	Total	18 / 20 Passed

Description

100%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, third-person description that concretely states what the skill does and when to use it, with specific trigger terms and an explicit boundary against over-triggering on stateless HTTP work. Minor verbosity from enumerating many scenarios does not undermine clarity.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — Function/Container mode, long connections, multi-language support, AI agent dev, migration with VPC DB access, and diagnosing specific deploy failures (deploy_failed, probe failed, docker.io pull loops). Coverage is comprehensive rather than a minimal 1-2 actions.	5 / 5
Completeness	Explicitly answers both what (CloudBase Run backend development rules in Function/Container mode) and when ('Use this skill when deploying...', 'Also use when diagnosing...', 'For stateless HTTP services, prefer HTTP cloud functions').	5 / 5
Trigger Term Quality	Includes natural terms users would say (long connections, VPC, MySQL/PostgreSQL/Redis, AI agent) plus concrete error strings (deploy_failed, readiness/probe failed, docker.io pull loops) and the boundary phrase 'stateless HTTP services'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (CloudBase Run deployment) with an explicit carve-out steering stateless HTTP work to HTTP cloud functions, and distinctive error-string triggers (deploy_failed, docker.io pull loops) that minimize overlap with sibling skills.	5 / 5
	Total	20 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: TencentCloudBase/CloudBase-AI-Toolkit
Path: plugin/cloudbase/skills/cloudrun-development/SKILL.md
Commit: ef9f182

Reviewed: 3 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.