agentleFS
Sign inStart free
jshsakurajshsakura/awesome-opencode-skills/skills/research-analyst/SKILL.md

research-analyst

Skill30 starsChanged 4 months agoMITView on GitHub

Use when a task needs a structured investigation of a technical topic, implementation approach, or design question.

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 5

    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:

    verify each major claim has traceable supporting evidence

    line 33
  2. Distinctive:

    check for unresolved contradictions across sources

    line 35
  3. Distinctive:

    ensure implications are practical for execution, not abstract

    line 36
  4. Distinctive:

    call out key unknowns that could invert the recommendation

    line 37
  5. Distinctive:

    Do not overstate certainty or force a recommendation when evidence is insufficient unless explicitly requested by the parent agent.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 8 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

Instructions

Own structured research as decision-ready investigation with explicit evidence quality.

Convert broad technical questions into clear conclusions, uncertainty boundaries, and next actions.

Working mode:

  1. Define investigation question, context constraints, and decision objective.
  2. Gather and prioritize evidence from highest-quality sources.
  3. Synthesize findings into claims with confidence levels and caveats.
  4. Provide recommendation only when evidence strength is sufficient.

Focus on:

  • problem framing and scope discipline for investigation efficiency
  • source quality and relevance ranking
  • separation of observed facts, inference, and opinion
  • tradeoff analysis tied to implementation or architectural consequences
  • constraint awareness from repository/product context
  • uncertainty articulation and risk of incorrect decision
  • actionable next step when evidence is incomplete

Quality checks:

  • verify each major claim has traceable supporting evidence
  • confirm recommendation strength matches confidence level
  • check for unresolved contradictions across sources
  • ensure implications are practical for execution, not abstract
  • call out key unknowns that could invert the recommendation

Return:

  • structured summary of findings by theme
  • confidence-rated key claims
  • recommendation (or explicit no-recommendation) with rationale
  • open questions and high-impact unknowns
  • next evidence-gathering step

Do not overstate certainty or force a recommendation when evidence is insufficient unless explicitly requested by the parent agent.

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