본문으로 건너뛰기
cccskills
무료GitHub에 공개

agent-harness-construction

Design and refine an AI agent’s available actions, tool inputs, and result formats. Define recovery steps for errors, manage the information kept in context, and evaluate changes through completion rates, retries, and cost per successful task.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent's tool set, action space, or observation format.

affaan-m/ECC
설치 방법 보기

이럴 때 유용합니다

  • Define an AI agent’s tool set and input formats
  • Make tool results and next steps easier to interpret
  • Specify safe retries and stopping conditions
  • Evaluate completion rates, retries, and task costs

포함된 파일(1)

  • SKILL.md2.1 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Agent Harness Construction

Use this skill when you are improving how an agent plans, calls tools, recovers from errors, and converges on completion.

Core Model

Agent output quality is constrained by:

  1. Action space quality
  2. Observation quality
  3. Recovery quality
  4. Context budget quality

Action Space Design

  1. Use stable, explicit tool names.
  2. Keep inputs schema-first and narrow.
  3. Return deterministic output shapes.
  4. Avoid catch-all tools unless isolation is impossible.

Granularity Rules

  • Use micro-tools for high-risk operations (deploy, migration, permissions).
  • Use medium tools for common edit/read/search loops.
  • Use macro-tools only when round-trip overhead is the dominant cost.

Observation Design

Every tool response should include:

  • status: success|warning|error
  • summary: one-line result
  • next_actions: actionable follow-ups
  • artifacts: file paths / IDs

Error Recovery Contract

For every error path, include:

  • root cause hint
  • safe retry instruction
  • explicit stop condition

Context Budgeting

  1. Keep system prompt minimal and invariant.
  2. Move large guidance into skills loaded on demand.
  3. Prefer references to files over inlining long documents.
  4. Compact at phase boundaries, not arbitrary token thresholds.

Architecture Pattern Guidance

  • ReAct: best for exploratory tasks with uncertain path.
  • Function-calling: best for structured deterministic flows.
  • Hybrid (recommended): ReAct planning + typed tool execution.

Benchmarking

Track:

  • completion rate
  • retries per task
  • pass@1 and pass@3
  • cost per successful task

Anti-Patterns

  • Too many tools with overlapping semantics.
  • Opaque tool output with no recovery hints.
  • Error-only output without next steps.
  • Context overloading with irrelevant references.

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

accessibility

무료

Design and audit interfaces for Web, iOS, and Android using WCAG 2.2 accessibility guidance. Check screen-reader labels, keyboard navigation, contrast, and control sizes to identify barriers and guide implementation for people using assistive technology.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Adding descriptive labels to icon-only buttons
  • Reviewing keyboard navigation and modal focus
  • Checking contrast and control sizes
affaan-m/ECC28.3만2026년 10월 16일 업데이트

agent-architecture-audit

무료

Investigate unreliable AI agents across 12 layers, including instructions, memory, tool execution, and display. Use code and logs to trace failures, rank findings by severity, and produce an ordered repair plan that prioritizes code changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Investigating failures that appear only inside an agent application
  • Tracing old conversation content leaking into new sessions
  • Checking skipped or falsely claimed tool execution
affaan-m/ECC28.3만2026년 10월 16일 업데이트

agent-eval

무료

Compare coding agents on tasks from your own codebase. Define success checks, run agents in separate Git working directories, and report pass rates, available API costs, completion time, and consistency across repeated trials.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Comparing coding agents on real development tasks
  • Evaluating a new tool or model before adoption
  • Checking performance after agent updates
affaan-m/ECC28.3만2026년 10월 16일 업데이트

agent-introspection-debugging

무료

Diagnose AI agent runs that fail repeatedly, loop through tools, or lose track of the task. Capture errors and environment details, test a focused recovery action, and produce a report explaining the evidence and outcome.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Diagnosing repeated failures in an agent run
  • Investigating loops through the same tool calls
  • Reviewing output degradation as context grows
affaan-m/ECC28.3만2026년 10월 5일 업데이트

agent-introspection-debugging

무료

Diagnose failed AI agent runs by capturing errors, checking likely causes, and choosing small, reversible recovery actions. The workflow produces a structured report of the failure, recovery steps, and evidence, helping explain repeated retries or stalled progress.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Diagnosing repeated tool calls with no progress
  • Investigating quality loss as context grows
  • Checking file paths and environment mismatches
affaan-m/ECC28.3만2026년 10월 16일 업데이트

agent-payment-x402

무료

Integrate x402, an HTTP payment protocol, so agents can pay for APIs or services. Configure task and session budgets, approved recipients, and wallets with privately managed keys, using integration paths for Base, X Layer, or Solana.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Enable an agent to pay for a paid API
  • Set task and session spending limits
  • Restrict payment recipients, networks, and assets
affaan-m/ECC28.3만2026년 10월 16일 업데이트

affaan-m의 스킬 모두 보기

이 스킬의 문제 신고