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). For stateless HTTP services, prefer HTTP cloud functions.

Quality

89%

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 skill with clear sequenced workflows, validation feedback loops, and appropriately split one-level-deep references. The main weakness is conciseness: several critical warnings are repeated many times and could be consolidated without losing effectiveness.

Suggestions

Consolidate the environment-initialization (initEnv) guidance into one authoritative location and reference it rather than restating the full rationale at ~6 different points in the body.

Centralize the 'do not raise InitialDelaySeconds' / getDeployLog-vs-getProcessLog distinction once in the SOP and link back to it instead of repeating the warning inline in the Activation Contract, checklist, tool routing, and troubleshooting sections.

Trim the duplicated OpenAccessTypes-vs-VpcConf and 'do not deploy httpbin' reminders to a single canonical statement to reduce token cost while preserving the gotcha.

Dimension	Reasoning	Score
Conciseness	The body is free of concept-padding and is task-relevant throughout, but the same critical warnings are heavily repeated — the environment-initialization requirement appears ~6 times and 'do not raise InitialDelaySeconds' ~5 times — so it could be tightened by consolidating that reinforcement.	3 / 5
Actionability	Copy-paste-ready JSON tool calls (init, run, deploy with full serverConfig, imageUrl deploy), concrete docker pull/tag/login/push commands, a five-item docs checklist, and a two-log diagnostic table give fully executable guidance across common cases.	5 / 5
Workflow Clarity	Multi-step processes are explicitly sequenced (4-step deploy sequence, Container deploy failure SOP ordering docs→logs→config) with validation checkpoints (poll envStatus until normal, two-log liveness compare) and feedback loops; destructive delete requires force:true confirmation.	5 / 5
Progressive Disclosure	SKILL.md is a well-organized overview pointing to two real one-level-deep references (references/vpc-and-database.md, references/image-deploy-troubleshooting.md) that are clearly signaled by relative path and enumerated in a closing Reference index.	5 / 5
	Total	18 / 20 Passed

Description

95%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 with explicit 'what' and 'when' clauses, rich natural trigger terms, and clear conflict-risk mitigation via negative guidance. The only minor weakness is the slightly abstract 'backend development rules' framing rather than a pure verb-driven action list.

Dimension	Reasoning	Score
Specificity	Concrete actions are listed ('deploying backend services', 'AI agent development', 'migrating existing/GitHub apps', 'diagnosing CloudRun container deploy failures'), but the lead phrase 'backend development rules' is slightly abstract, leaving a minor gap versus a fully verb-driven enumeration.	4 / 5
Completeness	It explicitly answers both 'what' (CloudBase Run backend development/deploy/diagnose rules) and 'when' via two explicit 'Use this skill when...' / 'Also use when...' clauses with concrete trigger phrases, plus negative guidance.	5 / 5
Trigger Term Quality	Comprehensive natural triggers including 'long connections', 'MySQL/PostgreSQL/Redis', 'VPC', 'deploy_failed', 'readiness/probe failed', 'image won't start', and 'docker.io pull loops' cover both user phrasings and error-code synonyms users would encounter.	5 / 5
Distinctiveness Conflict Risk	It carves a clear CloudBase Run niche with specific triggers and explicitly disambiguates ('For stateless HTTP services, prefer HTTP cloud functions'), minimizing overlap with the sibling cloud-functions skill.	5 / 5
	Total	19 / 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: f07c33c

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.