Name: cloud-functions
Rating: 64 (1 reviews)
Author: TencentCloudBase

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

76%

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

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

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.

Highly actionable content with executable skeletons and specific MCP contracts, clear sequencing, and a sound reference structure. The main weaknesses are repeated guidance across multiple sections (token cost) and broken links to missing routing files (references.md, checklist.md).

Suggestions

Consolidate the repeated Custom-Image-vs-CloudRun and port-9000/scf_bootstrap guidance into one authoritative section and cross-reference it, instead of restating it in 'Common mistakes', 'Writing mode', and the decision table.

Add the missing './references.md' and 'checklist.md' files (or repoint those links to the existing references/ files and a real checklist) so navigation links resolve.

Dimension	Reasoning	Score
Conciseness	Assumes Claude's competence (no basic concept explanations) and uses tight tables/code, but the same guidance is repeated across 'Common mistakes', 'Writing mode at a glance', 'Quick decision table', and 'Function types comparison' (e.g. port 9000, scf_bootstrap, Custom Image vs CloudRun stated multiple times), so it could be tightened.	3 / 5
Actionability	Provides copy-paste-ready Event and HTTP Function skeletons, concrete scf_bootstrap/package.json examples, and specific MCP action calls with exact parameters (e.g. manageFunctions(action="createFunction"), layerName="…_{envId}") covering the common cases.	5 / 5
Workflow Clarity	The 'How to use this skill' section is a clearly sequenced 5-step workflow with an Activation Contract and Minimal checklist, and it mandates validation gates (Change Safety Protocol, Deployment Gate) before destructive/deploy/batch actions; the validation detail itself lives in referenced protocol files rather than inline, leaving minor checkpoint gaps.	4 / 5
Progressive Disclosure	SKILL.md is an overview pointing to six real one-level-deep reference files listed in a Reference index and signaled inline, but the body also repeatedly references './references.md' and 'checklist.md' which are absent from the bundle — broken navigation links that prevent a top score.	4 / 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 specific, well-bounded description that states concrete capabilities and a clear use-when clause with an anti-trigger. The 'when' guidance could be sharpened with more concrete user-facing trigger phrases to reach the top anchor.

Suggestions

Expand the 'when' clause with concrete trigger phrases users actually say (e.g. 'Use when the user asks to deploy an HTTP endpoint, debug function logs, or set up an SCF trigger').

Add common synonyms/extensions (e.g. 'serverless functions', 'SCF') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (CloudBase function runtime) and three concrete actions — 'building, deploying, and debugging' — for two named function types, with only minor coverage gaps (e.g. inspecting/operating is implied rather than enumerated).	4 / 5
Completeness	Explicitly answers both what ('guide for building, deploying, and debugging... Event Functions or HTTP Functions') and when ('should be used when users need application runtime code on CloudBase'), but the 'when' is a single abstract condition rather than a list of concrete trigger phrases.	4 / 5
Trigger Term Quality	Includes natural terms a user would say ('Event Functions', 'HTTP Functions', 'application runtime code', 'CloudBase') plus a clear anti-trigger ('not when merely calling CloudBase official platform APIs'), but omits common synonyms like 'serverless' or 'SCF'.	4 / 5
Distinctiveness Conflict Risk	Clear niche (CloudBase application runtime functions) with an explicit negative boundary against official platform API clients, making overlap with sibling skills unlikely.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Commit: f07c33c

Reviewed: 4 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.