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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./config/.claude/skills/cloud-functions/SKILL.md

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 content is highly actionable with complete code skeletons, exact tool contracts, and strong validation/polling feedback loops for risky deployments. It is held back by substantial duplication of the polling, layer-naming, and CORS rules (plus inline version-pinned notes) and by a broken reference chain: the central routing file references.md and the pre-deployment checklist.md are referenced but missing from the bundle.

Suggestions

State the image-deployment polling workflow once (in its dedicated section) and reduce the corresponding gotcha bullet to a one-line pointer, and similarly deduplicate the layer-naming and CORS gateway rules into their single canonical locations.

Ship the missing references.md and checklist.md files (or repoint those links to existing files such as the Reference index section), since the body instructs the agent to read both before writing code or deploying.

Move version-sensitive details (e.g., "on 2.36.2 and earlier") into a clearly labeled compatibility/deprecated note in the relevant reference file instead of inline in the main body.

DimensionReasoningScore

Conciseness

The body is dense with CloudBase-specific facts Claude cannot infer (MCP action contracts, credential rules, gateway behavior), but it is noticeably repetitive: the image-deploy polling workflow appears twice in near-full form (a ~200-word gotcha bullet plus a dedicated section), layer naming appears about four times, the CORS gateway rule three times, and version-pinned details ("on 2.36.2 and earlier") sit inline rather than in a deprecated/old-patterns section. This fits the mostly-efficient-but-could-be-tightened anchor rather than the minor-trimming anchor.

3 / 5

Actionability

Guidance is fully executable and copy-paste ready: complete working hello-world skeletons for both Event and HTTP Functions (including scf_bootstrap and package.json), exact MCP tool signatures with parameters (manageFunctions(action="createFunction") etc.), a ready JSON deploy config, concrete CLS query strings, and a decision table. Specific examples cover the common cases, matching the top anchor.

5 / 5

Workflow Clarity

"How to use this skill" gives a clear numbered sequence (choose runtime model, use MCP entrances, write and deploy, doc-first fallbacks, read detailed reference) with explicit validation checkpoints: required Change Safety Protocol and Deployment Gate before changes, post-creation log verification (queryFunctions(action="listFunctionLogs")), and a polling feedback loop for deployments (poll getFunctionDeployStatus until succeeded/failed, expired means confirm via getFunctionDetail rather than report failure). This matches the clear-sequence-with-explicit-validation-and-feedback-loops anchor.

5 / 5

Progressive Disclosure

Section structure is well organized and the reference index lists seven one-level-deep files that all exist in the bundle, but the body's primary routing instructions point to files that are missing: ./references.md (referenced three times as the place to pick the detailed reference) and checklist.md (required reading before deployment) are absent from the bundle. Following the skill's own navigation chain therefore breaks immediately, which is more than the minor organization gap of the next anchor up.

3 / 5

Total

16

/

20

Passed

Description

75%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 specific, explicit about both what it does and when to use it, and actively disambiguates from the platform-API sibling skill. Its main gaps are missing common synonyms (serverless, SCF, cloud functions) in the trigger terms and an abstract when-condition that leaves residual overlap with the CloudRun skill.

Suggestions

Add natural trigger phrases users would actually say, e.g. "Use when the user mentions cloud functions, serverless functions, SCF, function logs, scf_bootstrap, or deploying an HTTP endpoint on CloudBase."

Sharpen the when-clause from the abstract "application runtime code" to concrete conditions, such as "when the user needs custom backend code that runs on CloudBase's function runtime (Event or HTTP Function) rather than a long-lived container (CloudRun) or a client calling platform APIs."

Mention the HTTP gateway/API-endpoint use case in the capability list, since browser-facing endpoints are a primary reason users reach for this skill.

DimensionReasoningScore

Specificity

"building, deploying, and debugging your own Event Functions or HTTP Functions" names the domain plus three concrete actions across two artifact types, matching the several-specific-actions anchor. Not 3 (more than 1-2 actions) and not 5 (adjacent actions like trigger, log, or gateway configuration are absent, so coverage is not comprehensive).

4 / 5

Completeness

A clear "what" (build/deploy/debug Event and HTTP Functions) is paired with an explicit trigger clause ("This skill should be used when users need application runtime code on CloudBase") plus a negative boundary, so it is not capped at 3. Not 5 because the when-condition "application runtime code" is abstract rather than the concrete trigger phrases the top anchor requires (e.g., "when the user mentions function logs or scf_bootstrap").

4 / 5

Trigger Term Quality

Natural terms users would say are present ("deploy", "debug", "CloudBase", "Event Functions", "HTTP Functions"), giving good keyword coverage. Not 5 because common synonyms like "serverless", "SCF", or the generic phrase "cloud functions" are missing, which a user would plausibly say when needing this skill.

4 / 5

Distinctiveness Conflict Risk

Naming the exact function types and explicitly excluding "merely calling CloudBase official platform APIs" carves a clear niche against the platform-API skill. Not 5 because the positive trigger "application runtime code on CloudBase" still overlaps the closely related CloudRun container-service skill, which the negative clause does not disambiguate.

4 / 5

Total

16

/

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

config/.claude/skills/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.