agentleFS
Sign inStart free
websublimewebsublime/mister-anderson/skills/research/SKILL.md

research

Skill3 starsChanged 7 months agoMITView on GitHub

Validate technical assumptions from the plan against real APIs, libraries, and codebase before spec creation. Dispatches Smith to produce structured research docs.

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

10 rules. 0 are common, 3 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user provides $ARGUMENTS, analyze them for:

    line 14
  2. Very specific:

    Plan must exist: Ask the user for the plan path (e.g., docs/plans/01-plan-mcp-foundation.md).

    line 20
  3. Very specific:

    PRD must exist: Ask the user for the PRD path (e.g., docs/PRD.md).

    line 21
  4. Very specific:

    No plan found. Recommend running /plan first.

    line 25
  5. Very specific:

    No PRD found. Recommend running /requirements first.

    line 29
  6. Very specific:

    Ask the user for the research topic (e.g., github-dependencies-api)

    line 35
  7. Very specific:

    If multiple research docs needed for the same phase, use distinct topics (e.g., 01-research-github-api.md, 01-research-projects-v2.md)

    line 37
  8. Very specific:

    Ensure the docs/research/ directory exists (create if needed)

    line 38
  9. Distinctive:

    Ask the user: "Are there specific APIs, libraries, or assumptions you want Smith to focus on?

    line 41
  10. Distinctive:

    Verify the research doc was created at the agreed path

    line 56

“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

Validate technical assumptions from the plan against real APIs, libraries, and codebase before writing the spec.

<on-init> If the user provides $ARGUMENTS, analyze them for: - A plan path - Specific APIs, libraries, or assumptions to focus on </on-init><on-check> 1. **Plan must exist.** Ask the user for the plan path (e.g., `docs/plans/01-plan-mcp-foundation.md`). Read to confirm. 2. **PRD must exist.** Ask the user for the PRD path (e.g., `docs/PRD.md`). Read to confirm. </on-check><on-check-fail if="plan"> No plan found. Recommend running `/plan` first. </on-check-fail><on-check-fail if="prd"> No PRD found. Recommend running `/requirements` first. </on-check-fail><on-execute> 1. **Define output location:** - Determine the phase number from the plan filename (e.g., `01` from `01-plan-*`) - Ask the user for the research topic (e.g., `github-dependencies-api`) - Suggest default path: `docs/research/{NN}-research-{topic-kebab}.md` - If multiple research docs needed for the same phase, use distinct topics (e.g., `01-research-github-api.md`, `01-research-projects-v2.md`) - Ensure the `docs/research/` directory exists (create if needed)
  1. Identify focus areas (optional):
    • Ask the user: "Are there specific APIs, libraries, or assumptions you want Smith to focus on? Or should he extract all assumptions from the plan?"

  2. Dispatch using exactly these parameters — no more, no less:

    Agent(
    subagent_type="investigator",
    prompt="Research technical feasibility for the plan at {plan_path}. PRD for context: {prd_path}. Save the research document to {research_path}. {focus_areas_or_empty}Read the plan to extract all technical assumptions and external dependencies, then validate each one against real documentation and the existing codebase."
)

    Do NOT add extra parameters unless the user explicitly requests it.

    </on-execute>
<on-complete> 1. Verify the research doc was created at the agreed path 2. Show the user Smith's report summary: how many assumptions confirmed/contradicted </on-complete><on-complete if="contradictions_found"> Present each contradiction clearly. Ask: "These contradictions need to be resolved before creating the spec. Do you want to adjust the plan first, or proceed to `/spec` with these known issues?" </on-complete><on-next> Recommend proceeding with `/spec` referencing the plan and research doc. </on-next>

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