agentleFS
Sign inStart free
ZimoLiaoZimoLiao/scholaraio/.claude/skills/technical-report/SKILL.md

technical-report

Skill585 starsChanged 3 months agoMITView on GitHub

Use when the user wants a technical report, topic report, research briefing, structured investigation, evidence synthesis, recommendations, or final report packaging.

2 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

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a report-oriented workflow for investigation, synthesis, and recommendation.

    line 7
  2. Distinctive:

    Use this skill when the user wants:

    line 21
  3. Distinctive:

    If the user mainly wants:

    line 27
  4. Distinctive:

    Use one primary path:

    line 44
  5. Very specific:

    Use /document when the report should be turned into a formal DOCX or presentation.

    line 70
  6. Very specific:

    Use /citation-check before final delivery if the report contains generated author-year citations.

    line 71
  7. Very specific:

    Use /export if the user wants a bibliography bundle alongside the report.

    line 72

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Technical Report Workflow

Create a report-oriented workflow for investigation, synthesis, and recommendation.

Purpose

This skill handles the cases that are not quite a paper and not just raw notes:

  • technical survey reports
  • topic briefings
  • special-topic investigations
  • advisor or team-facing research reports

It does not replace the deeper analysis skills. Instead, it decides which analysis path to use and then shapes the result into a report.

When To Use

Use this skill when the user wants:

  • a technical report
  • a topic or special-subject report
  • a research briefing for a team, supervisor, or project
  • a recommendation memo grounded in literature

If the user mainly wants:

  • a literature review article: use /literature-review
  • an open-problem analysis: use /research-gap
  • a slide deck: use /document

Workflow

1. Clarify Report Goal

Identify:

  • who the report is for
  • whether the report is explanatory, comparative, or decision-support
  • whether the user wants conclusions only or also recommendations
  • whether the report is meant to stay as Markdown or become a formal DOCX/PPTX deliverable

2. Choose The Analysis Backbone

Use one primary path:

Report typeRoute
State-of-the-art / what is known/literature-review
Open questions / what is missing/research-gap
User's own project update or method summary/paper-writing

3. Build A Report Structure

Recommended default structure:

  1. Executive summary
  2. Scope and question definition
  3. Evidence base or literature coverage
  4. Comparative analysis
  5. Risks, limitations, or disagreements
  6. Recommendations / next steps
  7. References

Adjust by audience:

  • supervisor or PI: prioritize takeaways and decisions
  • technical team: prioritize trade-offs, methods, constraints
  • self-study memo: prioritize structure and evidence trail

4. Package The Deliverable

  • Use /document when the report should be turned into a formal DOCX or presentation.
  • Use /citation-check before final delivery if the report contains generated author-year citations.
  • Use /export if the user wants a bibliography bundle alongside the report.

Output Pattern

Recommended outputs inside workspace/<name>/:

  • technical-report-outline.md
  • technical-report.md
  • references.bib
  • packaged deliverable from /document if requested

Principles

  • Decision-oriented structure: reports should help someone act, not only read.
  • Separation of layers: analysis comes from existing writing/research skills; this skill organizes it into a report.
  • Audience-aware emphasis: same evidence, different structure for different readers.
  • Honest scope: packaging is currently routed through /document; do not imply a separate report generator backend.

Example

用户说："帮我写一个这个方向的技术调研报告，给组会用" → 用本 skill 先明确 audience 和结构，再转 /literature-review 或 /research-gap 形成分析主体，最后接 /document

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