本文へ移動
cccskills
無料GitHub で公開

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

bg-szy/TOP-SKILLS
インストール方法を見る

含まれるファイル（1）

  • SKILL.md2.0 KB

SKILL.md（原文）

インストールする前に、エージェントに与えられる指示の中身を確認できます。

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.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

ログインしてレビューを書く

同じリポジトリのスキル

概要と使いどころ

aav-vector-design-agent

無料

AI-powered adeno-associated virus (AAV) vector design for gene therapy including capsid engineering, promoter selection, and tropism optimization.

日本語の概要は準備中です。原文の説明を表示しています。

bg-szy/TOP-SKILLS62026年9月8日 更新

academic-humanizer

無料

Improve the clarity and voice of AI-assisted academic writing (papers, theses, rebuttals) and

日本語の概要は準備中です。原文の説明を表示しています。

bg-szy/TOP-SKILLS62026年9月8日 更新

academic-paper

無料

12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebuttal-audit). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, audit my rebuttal, check my response draft, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見, 評估回覆, 논문 작성, 초록 작성, 논문 수정, 논문 계획을 도와줘, 심사 의견 반영, 답변서 점검, AI 사용 고지.

日本語の概要は準備中です。原文の説明を表示しています。

bg-szy/TOP-SKILLS62026年9月8日 更新

academic-paper-composer

無料

Systematic writing framework for philosophy and interdisciplinary academic papers from optimized outline to submission-ready manuscript. Use when users want to: (1) write a paper from a detailed outline, (2) ensure quality control during writing, (3) maintain consistency across chapters, (4) prepare a submission-ready manuscript, or (5) systematically execute a planned paper. Triggered by phrases like 'write the paper from this outline,' 'compose the full manuscript,' 'execute the outline,' or when users have completed strategic planning (academic-paper-strategist skill) and are ready to write. Takes optimized outline as input; outputs complete manuscript with iterative quality checks.

日本語の概要は準備中です。原文の説明を表示しています。

bg-szy/TOP-SKILLS62026年9月8日 更新

academic-paper-reviewer

無料

Multi-perspective academic paper review with dynamic reviewer personas. Runs a 5-seat, role-separated review panel (Journal-Fit Reviewer + 3 peer-review roles + Devil's Advocate) with field-specific expertise; role separation is not a claim of independent error processes. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy, 審查論文, 論文審查, 模擬審查, 同儕審查, 幫我審這篇, 以審查人角度評估, 審查者校準, 논문 심사, 동료 심사, 모의 심사, 심사자 관점에서 평가, 심사자 보정.

日本語の概要は準備中です。原文の説明を表示しています。

bg-szy/TOP-SKILLS62026年9月8日 更新

academic-paper-strategist

無料

Systematic strategic planning framework for philosophy and interdisciplinary academic papers targeting preprint platforms (PhilArchive, arXiv, PhilSci-Archive). Use when users want to: (1) plan a paper on a specific topic, (2) identify research gaps and assess originality, (3) develop optimized paper outlines, (4) prepare for preprint submission, or (5) understand platform requirements and writing standards. Triggered by phrases like 'plan a paper on,' 'help me design a paper about,' 'identify research gaps in,' 'is this idea original,' or when users need structured research planning. The skill guides through three phases: Platform Analysis (identifying target venue and studying sample papers), Theoretical Framework (AI-driven literature search and gap identification), and Outline Optimization (structured design with reviewer-perspective self-assessment). Each phase includes quality evaluation standards and validation checkpoints.

日本語の概要は準備中です。原文の説明を表示しています。

bg-szy/TOP-SKILLS62026年9月8日 更新

bg-szy のスキルをすべて見る

このスキルの問題を報告する