CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cloud-functions

CloudBase function runtime guide for building, deploying, and debugging your own Event Functions or HTTP Functions. This skill should be used when users need application runtime code on CloudBase, not when they are merely calling CloudBase official platform APIs.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is cloud-functions in TencentCloudBase/CloudBase-AI-Toolkit

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 and workflow-safe, with rare platform knowledge and explicit validation gates, but it is longer than needed due to duplicated polling and CORS/credential guidance, and its progressive-disclosure structure is undermined by links to files (references.md, checklist.md, tooling-fallback.md) that are not shipped in the bundle.

Suggestions

Ship or remove the dead links: `references.md` (the routing hub referenced four times), `checklist.md`, and `tooling-fallback.md` are absent from the bundle, so the primary navigation and pre-deployment checklist paths dead-end.

Deduplicate the image-deployment polling workflow: it is stated in full both as a gotcha bullet and in the "MCP image deployment with polling" section; keep one canonical version and cross-reference it.

Trim the thrice-repeated CORS and HTTP-function-credential explanations into the already-linked references (http-functions.md, http-function-credentials.md) and state the rule once in the body.

DimensionReasoningScore

Conciseness

Mostly high-value platform-specific knowledge Claude would not know (error-code diagnoses, gateway/CORS semantics, credential channels), but the image-deployment polling workflow appears twice nearly verbatim (the gotcha bullet and the "MCP image deployment with polling" section), and CORS and credential guidance is each repeated three or more times. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened'; not 2 because there is no basic-concept padding.

3 / 5

Actionability

Fully executable guidance throughout: copy-paste-ready Event and HTTP Function skeletons (complete server code, scf_bootstrap, package.json), exact MCP calls with action names and parameters, concrete error codes (401 MISSING_CREDENTIALS, InvalidParameter.Cls, CLOUD_REGISTRY_CREDENTIAL_MISSING) paired with diagnosis steps, and specific naming formats like `{layerName}_{当前envId}`. Matches the 'copy-paste ready; covers common cases' anchor.

5 / 5

Workflow Clarity

Clear sequencing (Activation Contract -> decision table -> 5-step "How to use this skill" -> tool map) with explicit validation checkpoints (Change Safety Protocol, Deployment Gate, poll getFunctionDeployStatus to a terminal status, verify listFunctionLogs after role binding) and error-recovery feedback loops (expired status -> getFunctionDetail, credential failure -> env-block guidance). Matches the top anchor including feedback loops for a deployment workflow.

5 / 5

Progressive Disclosure

The seven references/ files are real, substantive, one level deep, contextually linked, and indexed at the bottom — but the body's primary routing hub `./references.md` (referenced four times, including in the Minimal checklist), `checklist.md`, and `tooling-fallback.md` are all linked yet absent from the bundle, breaking the main navigation path. This sits between 'minor organization gaps' (4) and clearly broken reference signaling (3); the dead routing-hub links pull it to 3.

3 / 5

Total

16

/

20

Passed

Description

78%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 description that explicitly covers what the skill does and when to use it, with a valuable negative boundary clause. The main improvement opportunity is making the when-trigger more concrete (e.g., mentioning cloud functions, serverless, or SCF) and broadening action coverage slightly.

DimensionReasoningScore

Specificity

Names the domain ("CloudBase function runtime") with three concrete actions ("building, deploying, and debugging") applied to specific artifacts ("Event Functions or HTTP Functions"), matching the 'several specific actions; minor gaps' anchor. Not 5 because three verbs is narrower coverage than the comprehensive multi-action examples; not 3 because it goes beyond naming 1-2 actions.

4 / 5

Completeness

Explicitly answers both what ("guide for building, deploying, and debugging your own Event Functions or HTTP Functions") and when ("This skill should be used when users need application runtime code on CloudBase"). Not 5 because the when-clause uses the abstract phrase "application runtime code" rather than concrete mention-triggers; not 3 because the when guidance is explicit, not merely implied.

4 / 5

Trigger Term Quality

Includes natural phrases users would say such as "Event Functions", "HTTP Functions", "deploying", and "CloudBase", giving good keyword coverage. Not 5 because common synonyms like "serverless", "SCF", or plain "cloud function" are absent; not 3 because coverage extends well beyond a single generic keyword.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (authoring your own function runtime code on CloudBase) and adds an explicit negative boundary ("not when they are merely calling CloudBase official platform APIs") that prevents overlap with API-client skills. Minimal conflict risk.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 2 missing

Warning

Total

14

/

16

Passed

Repository

TencentCloudBase/CloudBase-AI-Toolkit

Path

connectors/cloudbase-intl/skills/references/cloud-functions/SKILL.md

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.