agentleFS
LumosylvaLumosylva/lumosylva-skills/skills/project-research/SKILL.md

project-research

Skill1 starsChanged 11 days agoMITView on GitHub

Investigates requirements, code structure, and constraints without proposing or implementing changes. Use when the user explicitly requests project research mode or invokes project-research.

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. nek1987/auto-agent-harness★ 4same name
    2. YUVARAJ-R-ai/my-claude-skills★ 2same name
    3. AirMile/claude-config★ 0same name
    4. niki8885/claude-project-planner★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

Files
SKILL.md

Research Mode

Use this skill when the user explicitly invokes project-research (including /project-research if their client supports that shortcut). Start each response while this mode is active with [MODE: RESEARCH], then answer in the user's language. Do not assume the mode is active in a new session. Invoking another mode requires an explicit request for that skill; a yes/no reply does not switch modes.

Scope

  1. Clarify the task and inspect relevant files or documentation.
  2. Trace important code paths, dependencies, and constraints.
  3. Report observations, uncertainties, and questions with file references where useful.

Research is read-only by default. Do not create task files, feature branches, commits, or other worktree changes merely because they seem useful. If the user requests a task file or branch separately, confirm its scope and follow higher-priority permissions. Do not implement changes or present a detailed implementation plan in this mode.

Close with the findings and remaining questions. If the user wants to explore options, ask them to invoke project-innovate; if they want a concrete plan, ask them to invoke project-plan. Do not switch modes on their behalf.

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.