CtrlK
BlogDocsLog inGet started
Tessl Logo

cloudbase-cli

CloudBase CLI (tcb, 云开发CLI, Tencent CloudBase命令行) resource management skill. This skill should be used when users need to deploy cloud functions, manage CloudRun apps, upload files to storage, query NoSQL/MySQL databases, deploy static hosting, set access permissions, or configure CORS/domains/routing via tcb commands. Also use for CI/CD pipeline scripting, batch operations, terminal-based CloudBase management, or when the user prefers CLI over SDK/MCP.

69

Quality

85%

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 cloudbase-cli in TencentCloudBase/CloudBase-AI-Toolkit

SKILL.md
Quality
Evals
Security

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured router skill body with strong workflow clarity and clean one-level-deep progressive disclosure. Weaker on conciseness (a restated checklist and a numbering slip) and actionability (executable detail lives in the reference files rather than the body).

Suggestions

Fix the duplicated "3." in Core Principles and remove or merge the Minimum self-check if it merely restates the Core Principles, to tighten the body.

Add 1-2 concrete representative tcb command examples per routing row (or a short canonical command snippet per domain) so the body is actionable without immediately loading a reference.

DimensionReasoningScore

Conciseness

Mostly lean with no concept-explanation padding, but the Minimum self-check largely restates Core Principles and Core Principles has a duplicated "3." numbering ("Verify your work" / "Dry-run before destructive actions"), indicating content that could be tightened; not score 3 because not every token earns its place.

2 / 3

Actionability

Gives some concrete commands ("tcb login", "tcb env use <envId>", "tcb <command> --help", "--dry-run") in the Quick workflow, but the bulk of executable command syntax is delegated to reference files rather than copy-paste-ready in the body; not score 1 because concrete commands are present, not score 3 because the body is not fully executable on its own.

2 / 3

Workflow Clarity

Clear sequenced Quick workflow with explicit validation ("Verify your work" → run list/detail command), a destructive-ops checkpoint (--dry-run + explicit confirmation), and an error-recovery feedback loop ("Recover from errors, don't loop"); matches the score 3 anchor and is not capped at 2 since verification steps are present.

3 / 3

Progressive Disclosure

A Routing table maps each task to a single one-level-deep reference file, all 10 referenced files exist in references/, and guidance says to load only the matching file; matches the clear-overview-with-well-signaled-references anchor.

3 / 3

Total

10

/

12

Passed

Description

100%

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, third-person description that names concrete capabilities and gives explicit when-to-use triggers with a clear CLI-vs-SDK/MCP boundary. Voice is correctly third person, so no specificity penalty applies.

DimensionReasoningScore

Specificity

Lists many concrete actions — "deploy cloud functions, manage CloudRun apps, upload files to storage, query NoSQL/MySQL databases, deploy static hosting, set access permissions, or configure CORS/domains/routing" — matching the multiple-specific-actions anchor; above score 2 which only names domain and some actions.

3 / 3

Completeness

Explicitly answers both what ("resource management skill" + concrete action list) and when ("This skill should be used when users need to... Also use for..."); not score 2 because the when-trigger is explicit rather than implied.

3 / 3

Trigger Term Quality

Natural phrasings users would say ("deploy cloud functions", "upload files to storage", "CI/CD pipeline scripting", "terminal-based") with good variation; not score 2 because coverage of common phrasings is broad rather than partial, though some product jargon (CloudRun, NoSQL/MySQL) is present.

3 / 3

Distinctiveness Conflict Risk

Clear CLI-management niche with an explicit contrast ("when the user prefers CLI over SDK/MCP") making it unlikely to trigger the wrong skill; above score 2 which still risks overlap.

3 / 3

Total

12

/

12

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.