agentleFS
sreejithramansreejithraman/SreeStack/skills/research/SKILL.md

research

Skill1 starsChanged 16 days agoMITView on GitHub

Investigate a question against primary sources and record cited findings. Use when research, documentation or API facts, or background reading are requested.

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

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When independent reading helps another owner continue useful work, use orchestration to delegate a bounded question with that path.

    line 24
  2. Distinctive:

    Use Gemini for YouTube retrieval and Grok for X posts, with the configured selections in agent routing.

    line 31
  3. Distinctive:

    Follow factual claims to primary sources: official documentation, source code, specifications, datasets, or first-party APIs.

    line 41
  4. Distinctive:

    Write one Markdown note with a direct answer, claim-level citations, unresolved gaps, and implications for the requested decision.

    line 44

“Common” is measured: kept by at least 6 in 10 of the 169 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Research

Own a question and the evidence needed to answer it. Resolve the decision and scope. Use agent routing's General research selection for investigation and synthesis.

Note storage

Choose the note path before delegating. Use the host-provided session scratch directory outside the repo when available; otherwise create a unique directory under a writable OS temp directory. Save in the project only when explicitly requested or when the task requires maintained documentation, honoring its destination.

Record the note's absolute path in task handoffs and compaction summaries. Reuse and update the same note as findings change; reread it after compaction or resume. Keep it available while the session or dependent workers need it.

When independent reading helps another owner continue useful work, use orchestration to delegate a bounded question with that path. When dispatched as the researcher, own the investigation and synthesis; assign additional children only when the brief permits it.

Source routing

Use Gemini for YouTube retrieval and Grok for X posts, with the configured selections in agent routing. Honor user overrides. Use orchestration for bounded source retrieval; when dispatching a researcher, permit these source tasks in its brief. Source retrievers work directly and return content or grounded extracts with canonical URLs, relevant dates/timestamps, retrieval method, and access gaps. Inspect the evidence before using it; a child summary alone does not prove retrieval.

Findings and acceptance

  1. Follow factual claims to primary sources: official documentation, source code, specifications, datasets, or first-party APIs. Record the revision/date and limits of the evidence; distinguish findings from inference.
  2. Write one Markdown note with a direct answer, claim-level citations, unresolved gaps, and implications for the requested decision.
  3. Inspect the note and sources before accepting it. Finish when the question is answered with the required evidence, or report exactly what remains unsupported and what would resolve it. Return the note path and conclusion.

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.