본문으로 건너뛰기
cccskills
무료GitHub에 공개

ai-agent-tool-routing

Document the tools an AI agent may call, including input rules, caller permissions, execution limits, and retry conditions. Produce a tool register and verification plan for reviewing registrations or MCP routing designs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Use when designing or reviewing an AI agent tool registry or MCP router: document parameter schemas, caller authorization, execution limits, replay-safe retries and verification evidence.

설치 방법 보기

이럴 때 유용합니다

  • Defining which tools an agent may call
  • Reviewing a proposed tool registration
  • Documenting timeout and retry rules
  • Tracking test evidence and unresolved gaps

포함된 파일(1)

  • SKILL.md5.8 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

AI Agent Tool Routing Register

When to Use

  • Define which tools an agent may call, their parameter schemas and runtime limits.
  • Review a proposed tool registration before connecting it to an agent runtime.
  • Document timeout, retry and authorization contracts for an existing router.

Scope and prerequisites

This skill produces a register and a verification plan. A register does not implement a router or establish that a tool is safe. Read the actual server/tool schema and the application's identity and permission model. Record observed configuration separately from proposed policy. Do not invoke registered tools, read credentials or enable a production registration merely to fill the table.

Workflow

  1. Identify a task, the calling principal/tenant, the intended tool and its read or write effect. Tool names, model output and descriptions are not authorization.
  2. Read the advertised schema and implementation boundaries. Define required fields, additional-field rejection, length/range limits and schema version. Prefer rejection to guessed or lossy coercion. Schema validation does not enforce row-level authorization, path containment or network restrictions.
  3. Describe identity propagation and server-side resource checks. Bind a request to the verified principal; never let a tool argument select an arbitrary tenant.
  4. Set measured/project-approved timeout, rate, concurrency, response-size and cost limits. Cancellation must propagate to downstream work where supported; returning a timeout alone does not prove a write did not finish.
  5. Classify retries by effect. Retry only classified transient failures within a bounded budget. A write requires a verified server-side deduplication contract and reconciliation for ambiguous completion; a random key alone is insufficient.
  6. Define adversarial and failure cases: missing/unknown arguments, wrong tenant, denied resources, unavailable tool, oversized response and late completion.
  7. Record actual test evidence and unresolved gaps. Keep status Draft until the required checks ran against the exact runtime and schema revision. A register label never grants execution permission.

Field reference

FieldTypeExample / interpretation
tool_idstring, primary keyTOOL-001; use TEXT/VARCHAR, not a SERIAL integer
canonical_namestringread_document; match the advertised tool exactly
serverstringproject-docs local MCP; identify the actual installation
invocation_modeenumsynchronous / asynchronous / scheduled
effectenumread / write; unknown effects stay unresolved
parameter_schemaobject or immutable referencerequired document_id, unknown fields rejected
authorization_policyimmutable referenceverified caller plus document ownership check
runtime_limitsobjectillustrative timeout 5000 ms, response 65536 bytes
retry_contractobjectmaximum attempts, transient classes, deduplication evidence
statusenumdraft / tested / deprecated / blocked
evidencearray of referencesexact implementation revision, case IDs and observed results

For SQL or Notion exports, retain these distinctions: textual IDs stay strings; objects/arrays need a deliberate JSON representation or related tables; dates must use actual date values. Do not treat a checklist boolean as a proved control. Escape spreadsheet formula-like text as text when exporting user-supplied fields.

Worked example

An agent needs a document summary. The proposed tool accepts only a document ID; the server obtains the caller from verified session context, not from arguments.

{
  "tool_id": "TOOL-001",
  "canonical_name": "read_document",
  "server": "project-docs",
  "effect": "read",
  "parameter_schema": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {"document_id": {"type": "string", "minLength": 1, "maxLength": 80}},
    "required": ["document_id"],
    "additionalProperties": false
  },
  "runtime_limits": {"timeout_ms": 5000, "max_response_bytes": 65536},
  "retry_contract": {"max_attempts": 2, "retry_on": ["transient_unavailable"]},
  "status": "draft",
  "evidence": []
}

These limits are illustrative requirements, not measured service capabilities. The local schema can reject an added tenant_id, but an existing document ID still requires server-side ownership authorization. Expected negative checks: missing ID rejected, extra tenant rejected, another tenant's document denied, timeout reported without fabricated content. A positive authorized read alone does not close the negative cases. Promote to tested only with recorded actual results.

Limitations

  • No RPC, blockchain, relayer or transaction-signing prerequisite applies to this generic agent-tool register; a real tool may declare separate dependencies.
  • This document supplies no production router, authentication adapter or sandbox.
  • Declared retry/idempotency/rate limits must be enforced by the actual runtime.
  • Never log sensitive arguments or full results by default. Use case IDs and redacted error categories; preserve uncertainty after an ambiguous write.

Related skills

Read mcp-builder, mcp-server-security or error-handling-patterns when their actual scope fits the integration. They do not establish correctness by association.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Assess a new or existing AI project by examining its code, goals, and constraints. Recommend skills confirmed to exist in the available registry, then outline tasks and implementation phases with dependencies, completion criteria, and checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Planning the first steps of a new AI project
  • Assessing technical issues in an existing project
  • Selecting relevant skills from an available registry
sickn33/agentic-awesome-skills4.8만2026년 10월 23일 업데이트

007

무료

Review code and infrastructure for security risks, map potential threats, and plan stronger defenses. The skill covers OWASP checks, attack and defense exercises, and incident response, with validation required for each environment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Reviewing code and infrastructure security
  • Mapping threats with STRIDE or PASTA
  • Planning stronger security settings
sickn33/agentic-awesome-skills4.8만2026년 10월 23일 업데이트

Turn a repeatable task into an Andru.ia skill with clear inputs, outputs, examples, and limits. Draft SKILL.md, check the folder structure and required validations, and prepare a pull request describing the changes for review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Creating a skill for a repeatable task
  • Improving an existing skill’s examples and limits
  • Validating skill files and preparing a pull request
sickn33/agentic-awesome-skills4.8만2026년 10월 23일 업데이트

Prepare an industry briefing once a project's sector is defined. It covers sector context, potentially applicable regulations, familiar interface patterns, technology choices, and risks, while separating verified evidence from hypotheses and questions requiring further review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Researching industry requirements before product design
  • Checking regulations for a project's jurisdiction
  • Choosing interface patterns familiar to target users
sickn33/agentic-awesome-skills4.8만2026년 10월 23일 업데이트

Create presentation drafts from text, outlines, or documents through the 2slides API. Match a reference image's style, choose themes, add AI voice narration, and export slide images or audio for review and use.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Create a presentation from text or an outline
  • Summarize a document into slides
  • Match slide styling to a reference image
sickn33/agentic-awesome-skills4.8만2026년 10월 23일 업데이트

Plan a 360-degree or peer feedback process and create empty response templates from confirmed requirements. Produces consistent CSV, SQL, JSON Schema, or Notion property mappings while keeping visibility choices and scoring configuration separate.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Plan an anonymous peer feedback process
  • Create a CSV template for feedback responses
  • Align feedback fields across SQL and JSON Schema
sickn33/agentic-awesome-skills4.8만2026년 10월 23일 업데이트

sickn33의 스킬 모두 보기

이 스킬의 문제 신고