CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cloud-api-operations

Operate Tencent Cloud control-plane resources (monitoring/alarms, CLB, CAM roles, COS, MySQL, SCF) via cloud APIs when no dedicated MCP tool covers the task. Use when a task needs control-plane operations beyond CloudBase's own tooling, or when a callCloudApi call failed and needs classifying. Also covers enterprise platform integration: wrapping CloudBase MCP into an organization-specific MCP (tool trimming, dangerous-action interception, per-user API Key distribution, audit) — use when the user mentions 企业接入 / 封装 MCP / 企业专属 MCP / 多租户凭证下发 / platform MCP wrapping. See recipes/enterprise-mcp-wrapper.md.

Quality

96%

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 a dense, operational workflow with explicit done-when checkpoints, executable commands, exact error signatures, and clean progressive disclosure into a real, verified reference bundle. Its only weakness is minor repetition in the credentials section, where the three-identity table's facts are restated in prose and bullets.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence (never explains what CLB/CAM/COS are; uses compact tables for calling paths and identities), but the credentials section states the API Key's "no channel to attach arbitrary CAM policies" in both the table and a bullet, and the refusal behavior is repeated across the table and the 'Order matters' paragraph. This matches anchor 4 (efficient with minor trimmable repetition) rather than 5, where every token would earn its place.

4 / 5

Actionability

Guidance is fully executable: copy-paste commands ("sts GetCallerIdentity (`--api-version 2018-08-13`)", "--cloudbase-api-key -e <envId>", "tcb api"), exact doc URLs, exact error strings ("action ... is invalid or not found", "resource (...) has no permission"), and concrete API actions ("ListAttachedRolePolicies + GetPolicy"). Anchor 5 — specific, ready-to-run directives cover the common cases; per the rubric's instruction-skill note, absence of code blocks is not penalized when guidance is this actionable.

5 / 5

Workflow Clarity

Four clearly sequenced steps (discover API → choose path → check credentials → follow recipe), each closed by an explicit "**Done when**" validation checkpoint, with feedback loops for error recovery (classify-and-recover via the error table, one-click CAM grant link then retry). Anchor 5; validation checkpoints are explicit, so the missing-validation cap for risky operations does not apply.

5 / 5

Progressive Disclosure

The body is a true overview that pushes detail into one-level-deep, well-signaled references with section anchors ("./references/calling-methods.md §1", "§2 item 4", "§3", "./references/service-versions.md", recipes index "./references/recipes/README.md"), and every referenced file exists in the bundle. Anchor 5 — recipes are listed directly in the body with one-line descriptions, so navigation never requires chasing nested pointers.

5 / 5

Total

19

/

20

Passed

Description

100%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 exemplary: it states concrete capabilities with named products, gives explicit bilingual 'Use when' triggers including the exact failure scenario (callCloudApi errors), and sharply bounds its niche against dedicated MCP tooling. Dense but not padded — every clause carries trigger or capability information.

DimensionReasoningScore

Specificity

Quotes like "Operate Tencent Cloud control-plane resources (monitoring/alarms, CLB, CAM roles, COS, MySQL, SCF)", "classifying" failed callCloudApi errors, and "tool trimming, dangerous-action interception, per-user API Key distribution, audit" list multiple concrete actions spanning operations, error recovery, and enterprise integration. This matches the anchor 5 (comprehensive concrete actions) rather than 4, since no meaningful capability area is left vague.

5 / 5

Completeness

The "what" is explicit ("Operate Tencent Cloud control-plane resources ... via cloud APIs") and the "when" appears as two concrete 'Use when' clauses ("Use when a task needs control-plane operations beyond CloudBase's own tooling, or when a callCloudApi call failed and needs classifying"). Clearly anchor 5 — both questions are answered with concrete trigger phrases, not anchor 4 where the 'when' would be less explicit.

5 / 5

Trigger Term Quality

Natural user phrases include "callCloudApi call failed", "CLB", "CAM", "SCF", and a deliberate synonym cluster "企业接入 / 封装 MCP / 企业专属 MCP / 多租户凭证下发 / platform MCP wrapping". This matches anchor 5 (comprehensive coverage including synonyms in both languages); anchor 4 would require natural terms to be noticeably missing, which the bilingual synonym set precludes.

5 / 5

Distinctiveness Conflict Risk

The niche is explicitly bounded against sibling skills ("when no dedicated MCP tool covers the task", "beyond CloudBase's own tooling") and enterprise triggers are highly specific. Anchor 5 (clear niche, minimal conflict risk); anchor 4 would require overlap with closely related skills, but the scoping clauses actively prevent that.

5 / 5

Total

20

/

20

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.

Validation — 15 / 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

Path

connectors/cloudbase-intl/skills/references/cloud-api-operations/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.