cloudbase-platform

CloudBase platform overview and routing guide. This skill should be used when users need high-level capability selection, platform concepts, console navigation, or cross-platform best practices before choosing a more specific implementation skill.

Quality

80%

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 ./plugin/cloudbase/skills/cloudbase-platform/SKILL.md

Quality

Content

76%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 with concrete tool calls, URL patterns, and validation checkpoints, and it uses one-level-deep protocol references well. It loses conciseness points for restating platform concepts and duplicating the domain-management table, and a few destructive paths could enumerate validation more explicitly.

Suggestions

Consolidate the domain-management guidance — the security-domain vs custom-domain distinction appears in three places (gotchas, table, key indicators); keep one authoritative table and cross-reference it.

Trim concept restatements Claude already knows (e.g. basic explanations of static hosting vs cloud storage) to leaner pointers.

For destructive/batch operations (delete custom domain, deleteRoles, disableRoute), enumerate explicit pre-check and validate-after steps rather than prose cautions to push workflow_clarity to 5.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly task-oriented, but it repeatedly re-states platform concepts Claude already knows and restates the same domain-management table across three sections, so it is 'mostly efficient' with padding that could be tightened rather than lean.	3 / 5
Actionability	Provides fully executable, copy-paste-ready guidance throughout — concrete MCP tool calls with exact parameters (manageEnv, manageGateway, queryPermissions), real URL patterns, and worked examples like the cloud-storage public-URL construction — covering the common cases.	5 / 5
Workflow Clarity	Multi-step flows are sequenced with explicit checkpoints and feedback loops (e.g. permission-change retry guidance, the Recording Operation Results validate-then-write steps, env-alias resolution before URL construction); a few destructive/batch paths lean on prose rather than enumerated validation, leaving minor gaps.	4 / 5
Progressive Disclosure	Structure is good: SKILL.md is an overview with a clearly signaled reference index pointing to three one-level-deep protocol files (verified present in references/protocols/), and routing links to sibling skills; some reference-heavy console/API material is inlined rather than split out, leaving minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

83%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 cleanly answers both 'what' and 'when' with concrete, third-person, trigger-oriented language and is well-distinguished from sibling implementation skills. Its main limitation is that the 'actions' are curatorial/routing verbs rather than the concrete transform actions the specificity anchor rewards.

Suggestions

Lead with one or two concrete platform actions (e.g. 'Routes CloudBase tasks to the correct implementation skill and explains console entry points') to lift specificity toward the top anchor.

Add a few common user synonyms (e.g. 'Tencent CloudBase', 'TCB') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (CloudBase platform overview/routing) and several concrete actions — 'high-level capability selection', 'platform concepts', 'console navigation', 'cross-platform best practices' — though the actions are advisory/curatorial rather than the data-transform verbs the rubric rewards, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly states both what it does ('CloudBase platform overview and routing guide') and when to use it ('should be used when users need high-level capability selection, platform concepts, console navigation, or cross-platform best practices before choosing a more specific implementation skill'), satisfying the top anchor for both what and when.	5 / 5
Trigger Term Quality	Includes natural user phrasing like 'which CloudBase capability, service, or tool to use', 'console navigation', 'cross-platform best practices', and capability names (hosting, storage, authentication, cloud functions, database); a few common synonyms are absent but coverage is good.	4 / 5
Distinctiveness Conflict Risk	The 'before choosing a more specific implementation skill' framing carves a clear routing/overview niche distinct from the sibling implementation skills, with only minor overlap risk against those specialized skills.	4 / 5
	Total	17 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (504 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 7 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: TencentCloudBase/CloudBase-AI-Toolkit
Path: plugin/cloudbase/skills/cloudbase-platform/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.