agentleFS
eugenezhangco-speceugenezhangco-spec/athena/.claude/skills/research/SKILL.md

research

Skill0 starsChanged 7 months agoMITView on GitHub

Save research findings, articles, and learnings to the user's Notion Research database with key takeaways. Use when the user says "save this research", "add to research", "log this finding", "research note", or after a deep-research session when findings should be persisted.

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

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After a deep-research session, when findings should be persisted

    line 12
  2. Distinctive:

    If not present, ask the user to set it up or suggest running the onboard skill.

    line 25
  3. Distinctive:

    Write concise Key Takeaways (2–5 bullet points, plain language, actionable where possible).

    line 44
  4. Very specific:

    Create the entry via mcp__notion__notion-create-pages.

    line 47
  5. Distinctive:

    If the research has detailed findings beyond the takeaways, add them as page body content.

    line 48
  6. Distinctive:

    After a deep-research session, proactively suggest saving the findings here.

    line 54
  7. Very specific:

    If the research connects to a current goal or project (from personal/goals.md), mention that connection.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 170 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

Skill: Research

When to Use

  • User shares research findings, an article summary, or key learnings
  • User says "save this research", "add to research", "log this finding", "research note"
  • After a deep-research session, when findings should be persisted
  • User discovers something relevant to their business, industry, or goals

Prerequisites

Writes to a Notion database. The user must have configured in personal/notion-databases.md:

research_database_id: <user's Notion database ID>
research_data_source: collection://<data source id>
research_parent_page: <parent page id>

If not present, ask the user to set it up or suggest running the onboard skill.

Expected Notion Schema

PropertyTypeOptions
TopictitleClear research topic
CategoryselectBusiness, AI, Marketing, Finance, Industry (user can customize)
Source URLurlOptional — where the info came from
Key TakeawaystextThe essential findings, 2–5 bullet points
DatedateAuto-set to today
StatusselectUnread, Read, Applied

Adapt to user's actual property names if they differ.

Steps

  1. Identify the research topic from the user's message or session context.
  2. Determine the best Category fit.
  3. Write concise Key Takeaways (2–5 bullet points, plain language, actionable where possible).
  4. Capture Source URL if provided.
  5. Set Date to today. Set Status to "Read" if the user has already reviewed the content, "Unread" if saving for later.
  6. Create the entry via mcp__notion__notion-create-pages.
  7. If the research has detailed findings beyond the takeaways, add them as page body content.
  8. Confirm back with topic and category.

Rules

  • Key Takeaways should be specific and actionable, not generic summaries.
  • After a deep-research session, proactively suggest saving the findings here.
  • If the research connects to a current goal or project (from personal/goals.md), mention that connection.
  • Yellow tier when proactively suggesting. Green tier when user explicitly asks.
  • One entry per distinct research topic. Don't combine unrelated findings.

Output Format

Saved to Research:
- [Topic] ([Category]) — [X] takeaways captured

One line per entry.

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.