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) or a deploy stuck behind a running deploy task. For stateless HTTP services, prefer HTTP cloud functions.

72

Quality

90%

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 strong validation feedback loops, undermined mainly by heavy cross-section repetition and bilingual duplication that inflates the token budget. Progressive disclosure is good but would benefit from pushing more SOP detail into the existing reference files.

Suggestions

De-duplicate the PORT/app.listen(), credential-gate, and VpcConf guidance so each appears in one canonical place; link from the other sections instead of restating.

Move the full Container deploy failure SOP / log-query SOP / deploy-task SOP detail into references/image-deploy-troubleshooting.md and keep only the decision flowchart inline in SKILL.md.

Fix the references/http-function-credentials.md link to its real sibling-skill path (../cloud-functions/references/http-function-credentials.md) to avoid a dead local reference, or note explicitly that it lives in a sibling skill.

DimensionReasoningScore

Conciseness

The body is genuinely operational (non-obvious error codes, API quirks) rather than explaining known concepts, but it repeats the same guidance across Common mistakes, dedicated decision-gate sections, How-to-use, Best practices, and Troubleshooting — e.g. the PORT/app.listen() rule, the credential gate, and the VpcConf gotcha each appear 4–5 times, and bilingual duplication doubles tokens.

3 / 5

Actionability

Provides copy-paste-ready JSON tool calls with exact action/parameter names, exact env-var names (CLOUDBASE_APIKEY), a concrete docker tag/push/CCR sequence, and a Dockerfile FROM example — covering init, run, deploy (source and imageUrl), VPC, and log retrieval.

5 / 5

Workflow Clarity

Sequences are explicit with validation checkpoints and feedback loops: a numbered deploy sequence (initEnv → poll envStatus → deploy), the Container deploy failure SOP (docs → getProcessLog two-pull comparison → decision table → only-then-config), and the Deploy-task SOP with a taskStatus decision table; destructive delete requires confirmation + force.

5 / 5

Progressive Disclosure

Good structure with a Reference index and clearly signaled one-level-deep references to the two existing reference files; however substantial SOP detail (deploy-failure SOP, log-query SOP, deploy-task SOP, decision gates) is inlined in SKILL.md rather than split out, and references/http-function-credentials.md is referenced as a local path but only exists under a sibling skill (../cloud-functions/references/).

4 / 5

Total

17

/

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, specific description that answers what and when with concrete trigger terms and explicit routing guidance to avoid conflicts with sibling skills. No padding or over-claims.

DimensionReasoningScore

Specificity

Names the domain (CloudBase Run Function/Container mode) and lists multiple concrete actions — deploying long-connection/multi-language/AI-agent services, migrating apps with VPC access to MySQL/PostgreSQL/Redis, and diagnosing deploy_failed/probe/image-start/docker.io-pull failures — giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (CloudBase Run backend development rules for Function/Container mode) and 'when' via two 'Use this skill when…/Also use when…' trigger clauses plus a routing hint for the stateless case.

5 / 5

Trigger Term Quality

Covers natural user phrasings including synonyms ('stateless HTTP services' / 'HTTP cloud functions', 'migrating existing/GitHub apps') and concrete error signals a debugging user would actually say ('deploy_failed', 'readiness/probe failed', 'image won't start', 'docker.io pull loops').

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (CloudBase Run) and actively routes the overlapping case away ('For stateless HTTP services, prefer HTTP cloud functions'), minimizing wrong-skill triggering against sibling function/agent skills.

5 / 5

Total

20

/

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.