CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is highly actionable with copy-paste-ready tool calls, well-sequenced deploy/diagnose workflows, and proper validation gating for destructive and batch operations. Its main weakness is conciseness: the initEnv/envStatus and deploy-gating guidance is repeated across multiple sections, and some reference-grade detail is inlined rather than pushed into the existing reference files.

Suggestions

Consolidate the initEnv/envStatus initialization guidance (currently restated in the activation contract, minimal checklist, deployment sequence, and troubleshooting hints) into one authoritative location and cross-reference it to remove repetition.

Move the full log-query SOP, readiness-probe mechanics tables, and five-item docs checklist into references/image-deploy-troubleshooting.md, leaving SKILL.md with the decision rules and a pointer, to tighten conciseness and sharpen progressive disclosure.

Promote remaining implicit validations (e.g., post-deploy DB-connectivity check) into explicit numbered checkpoints with failure-recovery feedback loops so every workflow branch has an enforced validate-then-proceed gate.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence (no padding about what a container or VPC is), but several pieces of guidance are restated across sections — initEnv/envStatus instructions recur in the activation contract, checklist, deployment sequence, and troubleshooting — which could be tightened into a single canonical location.

3 / 5

Actionability

Fully executable guidance throughout: concrete JSON tool-call payloads (deploy, getProcessLog), a complete docker pull/tag/push sequence, full serverConfig examples with VpcConf, and a five-item docs checklist mapped to specific serverConfig fields.

5 / 5

Workflow Clarity

Clear multi-step sequences with explicit validation checkpoints — 'Confirm the environment has CloudRun initialized before the first deploy', the docs → getProcessLog → config SOP ordering, the two-log 20-40s comparison, and delete requiring force:true confirmation. A 5 is withheld because some validation is described as a recommended step rather than an enforced, sequenced checkpoint with explicit error-recovery feedback loops in every branch.

4 / 5

Progressive Disclosure

SKILL.md serves as a structured overview pointing to two real, one-level-deep reference files (references/vpc-and-database.md and references/image-deploy-troubleshooting.md, both present and clearly signaled in the Reference index). It stops just short of a 5 because the body still inlines substantial reference-grade detail (full log-query SOP, probe mechanics, five-item tables) that could live entirely in the reference files.

4 / 5

Total

16

/

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.

The description is well-targeted: third-person voice, explicit what-and-when guidance, concrete trigger phrases including diagnostic error strings, and a clear boundary against HTTP cloud functions. Its only weakness is mild reliance on platform jargon and slightly abstract actions rather than a fully exhaustive action list.

DimensionReasoningScore

Specificity

Names the domain (CloudBase Run backend dev) and lists several concrete actions — 'deploying backend services', 'migrating existing/GitHub apps', 'diagnosing CloudRun container deploy failures' — but the actions stay slightly high-level rather than enumerating every operation, so it sits just below the comprehensive 5.

4 / 5

Completeness

Explicitly answers both 'what' (CloudBase Run backend development rules, Function/Container mode) and 'when' via two concrete 'Use this skill when'/'Also use when' clauses with concrete trigger phrases, plus a boundary directive ('For stateless HTTP services, prefer HTTP cloud functions').

5 / 5

Trigger Term Quality

Strong, natural trigger coverage ('long connections', 'multi-language support', 'AI agent development', 'VPC access to MySQL/PostgreSQL/Redis', 'deploy_failed', 'readiness/probe failed', 'docker.io pull loops'), but it leans on platform-specific jargon and omits a few common synonyms, so it is not a full 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche (CloudBase Run deployment and deploy-failure diagnosis) with distinct triggers and an explicit anti-trigger steering stateless HTTP work to a different skill, giving minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

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.