AGENT SKILL

research

Deep research — clarify question, find primary sources, verify, deliver recommendation. Use when the answer requires checking documentation, papers, or official repos rather than guessing from memory.

License 许可
MIT
最近更新
2026-04-30
Stars
★ 1
Forks
2

01 前言 Front Matter

name
research
metadata
{ "harness-tags": "skill,research,analysis", "harness-author": "human", "harness-status": "active", "harness-related": "ask-before-assuming" }
description
Deep research — clarify question, find primary sources, verify, deliver recommendation. Use when the answer requires checking documentation, papers, or official repos rather than guessing from memory.

02 资源文件 1

03 SKILL.md 正文

Skill: Research

Process

  1. Clarify — What is the actual question? What decision does this inform?
  2. Find primary sources — Documentation, papers, official repos. Not blog summaries.
  3. Verify recency — Is this information current? Check dates.
  4. Cross-reference — Do multiple sources agree?
  5. Recommend — Deliver ONE recommendation with confidence level.

Red Flags

  • Relying on a single source
  • Information older than 6 months for fast-moving topics
  • Delivering options without a recommendation
  • Summarizing without verifying

When NOT to Use

  • When the answer is in the codebase (search first)
  • When the creator has already made a decision (don't second-guess)

04 同仓库更多 Skills

Phoenixrr2113
Phoenixrr2113/agent-harness

research

Conduct research.

资料检索与研究
★ 1
Phoenixrr2113
Phoenixrr2113/agent-harness

{{NAME=null}=null}

Briefly describe what this skill does AND when to use it. Use imperative phrasing ("Use this skill when..."). Aim for 80-500 chars. Include keywords the model can pattern-match against the user's prompt.

Skill与智能体开发
★ 1
Phoenixrr2113
Phoenixrr2113/agent-harness

working-in-a-git-repo

Operating manual for dev work: worktree discipline, build/test/lint commands, file ownership zones, commit style, and a verification checklist before reporting done. Use when starting any feature/fix work in this repo.

Skill与智能体开发
★ 1
Phoenixrr2113
Phoenixrr2113/agent-harness

test-runner

Runs the project's test suite (or a targeted subset), parses the output, and reports pass/fail with failing-test details. Use when you need to know test status; call with the test command to run, or leave blank for the project default.

测试与质量Skill与智能体开发
★ 1
Phoenixrr2113
Phoenixrr2113/agent-harness

reviewer

Reviews a diff or change set for bugs, security issues, test gaps, and style. Use when evaluating a code change, reviewing a pull request, or running a structured review pass before merge.

Skill与智能体开发
★ 1
Phoenixrr2113
Phoenixrr2113/agent-harness

fix-failing-tests

Seven-step flow for diagnosing and fixing failing tests. Use when the user asks to fix failing tests, green the suite, or says 'tests are red' — works through reproduce → read → root-cause → propose → apply → verify → commit.

测试与质量
★ 1