research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
- License 许可
- MIT
- 所属仓库
- sanurb/.dotfiles
- 最近更新
- 2026-11-12
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- research
- description
- Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
02 资源文件 1
- 参考文档agents/openai.yaml94 B
03 SKILL.md 正文
Spin up exactly one background agent to do the research, so you keep working while it reads.
Recursion guard
Before spawning, check RESEARCH_SUBAGENT:
- If
RESEARCH_SUBAGENT=1, this pane is already the delegated researcher. Do not spawn any agent or pane. Perform the research and write the report directly. - Otherwise, create one background pane with
herdr pane split ... --env RESEARCH_SUBAGENT=1, and explicitly tell that agent not to delegate or spawn subagents.
Never create a second research agent as a retry. If the delegated agent stalls or fails, stop/close it and complete the research in the original pane.
The background agent's job:
- Investigate the question against primary sources — official docs, source code, specs, first-party APIs — not a secondary write-up of them. Follow every claim back to the source that owns it.
- Write the findings to a single Markdown file, citing each claim's source.
- Save it where the repo already keeps such notes; match the existing convention, and if there is none, put it somewhere sensible and say where.
04 同仓库更多 Skills
writing-great-skills
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
write-discoverable-code
Rules for writing code that coding agents (and humans) can find and understand through plain-text search. Apply whenever writing or renaming code: functions, types, constants, files, error messages, doc comments. Grounded in measurement: agents navigate by plain-text search, not by AST or language server, so every identifier is a search query and every search miss costs wasted reads.
wrangler
Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
workers-best-practices
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
web-perf
Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.
wayfinder
Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.