Name: cloudrun-development
Rating: 68 (1 reviews)
Author: TencentCloudBase

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

83%

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

The canonical home for this skill is cloudrun-development in TencentCloudBase/CloudBase-AI-Toolkit

Quality

Content

78%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.

Highly actionable and well-sequenced content with executable examples and strong validation/feedback loops in its deploy and diagnosis workflows. Its main weakness is conciseness: several critical warnings are stated verbatim 3–4 times across sections, inflating the token budget without adding clarity.

Suggestions

De-duplicate the initEnv/uninitialized-environment, 'skip getDeployLog for image deploys', and 'do not raise InitialDelaySeconds' warnings — state each once authoritatively and cross-reference it from the other sections.

Move the full Container deploy failure SOP detail (signal tables, supervisor/s6 cases) into references/image-deploy-troubleshooting.md, keeping only the ordered docs→logs→config spine in the body.

Tighten the bilingual sections (云托管 vs HTTP 云函数, Log query SOP) — the English 'When CloudRun is a better fit' and 'How to use this skill' lists overlap with the Chinese decision list and could be merged.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete tool tables and SOPs, but it repeats the same guidance several times — the initEnv/uninitialized-environment warning, 'skip getDeployLog for image deploys', and 'do not raise InitialDelaySeconds' each appear 3–4 times across the Activation Contract, checklist, Tool routing, SOP, and Troubleshooting sections, adding padding.	3 / 5
Actionability	Fully executable: copy-paste JSON payloads for init/run/deploy/traffic with exact serverConfig fields, concrete tool actions with parameters, a five-item docs checklist, a two-log comparison table, and a Dockerfile FROM workaround — all directly actionable.	5 / 5
Workflow Clarity	Multi-step deploy and failure-diagnosis workflows are explicitly sequenced with validation checkpoints (initEnv → poll envStatus=normal → deploy → follow next_step → getProcessLog two-pull comparison) and feedback loops (fix→re-validate, docs→logs→config), matching the destructive/batch feedback-loop bar.	5 / 5
Progressive Disclosure	Good structure with a clear overview, mode-selection table, tool routing, SOP, and a Reference index linking two real one-level-deep files (references/vpc-and-database.md, references/image-deploy-troubleshooting.md); however the body is long and inlines substantial detail (full SOP, multi-row tables) that could live partly in the references, a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

87%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, trigger-rich description that names concrete capabilities, gives explicit when-clauses, and cleanly carves out its niche with a 'prefer HTTP cloud functions' boundary. Minor specificity gaps (no mention of traffic/canary or initEnv actions) keep it just short of flawless.

Suggestions

Optionally name the traffic/canary and initEnv actions so the trigger surface matches the body's full capability set.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities (Function/Container mode, long connections, multi-language, AI agent, VPC DB access, deploy-failure diagnosis) with concrete tech signals (DATABASE_URL, deploy_failed, docker.io pull loops), though a few domain actions (e.g. traffic/canary, initEnv) are not surfaced, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers what (backend development rules across Function/Container mode, deploy, diagnose) and when (two 'Use this skill when…' / 'Also use when…' clauses with concrete trigger phrases), plus a clear prefer-elsewhere boundary.	5 / 5
Trigger Term Quality	Comprehensive natural triggers including long connections, multi-language, AI agent, existing/GitHub apps, MySQL/PostgreSQL/Redis, deploy_failed, readiness/probe failed, image won't start, docker.io pull loops, plus the negative 'stateless HTTP services' routing cue.	5 / 5
Distinctiveness Conflict Risk	Clear niche (CloudBase Run container/Function-mode backend with VPC DB and deploy diagnostics) with specific error tokens and a carve-out directing stateless HTTP services to HTTP cloud functions, minimizing overlap with sibling skills.	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: config/.claude/skills/cloudrun-development/SKILL.md
Commit: 3ce25cd

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.