agentleFS
Sign inStart free
anxndsgnanxndsgn/skills/research/SKILL.md

research

Skill1 starsChanged 51 days agoApache-2.0View on GitHub

Investigate a question with cited evidence, going wherever the answer is observable first-hand — market landscape, community sentiment, a specific code repository, or anything else external. Use when the user asks to research, look into, or validate something about a market, competitors, what people are saying, or an external repo.

189 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • truongtv22Skill

    Problem-Solving Techniques

    Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), scale uncertainty (scale game), and dispatch when stuck. Techniques derived from Microsoft Amplifier project patterns adapted for immediate application.

    Also in 5 projects that use this

  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 43 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • +5 more from Lambenthan
  • +1 more from skyllwt

The file

Create a free account to mount
Files
SKILL.md

/research <question or target> → find where the answer is observable → gather in parallel → report with sources

The deliverable is a short report the user can act on. Its value is entirely in being trustworthy: every claim links to its source, evidence is kept separate from your inference, and findings carry dates — a complaint from 2019 may be long fixed, a competitor from memory may be dead. What you couldn't find is a finding too; report it instead of papering over it.

Where to look

One question decides the whole approach: where would this answer leave a first-hand trace? Go there, as close to the primary source as access allows. There is no fixed menu of research types — a market question leaves traces in what people pay for and switch to; a sentiment question in people's own words where they actually talk (site: queries reach forums and reviews well); a question about a codebase in the code itself, which you can shallow-clone into the scratchpad and read.

Whatever the trace, the same rule applies: secondary accounts — an article about the market, a README describing its own code, a post summarizing what users think — are leads, not evidence. Follow them down to the behavior, the verbatim words, or the artifact they describe before citing anything. And weigh patterns over volume: the same complaint recurring across independent voices is signal; one loud post is not.

Fan out independent angles as parallel sub-agents when the question has more than one, so a slow angle doesn't serialize the rest.

Report

## Research: <question>

**Answer:** <the one-paragraph takeaway>

## Findings
<ranked by how much each changes the user's decision; every claim sourced>

## Still unknown
<what the evidence couldn't settle, and how it could be settled>

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free