Agent skill

Save Research

by meain in meain/dotfiles

Summarize and save research findings from the current conversation into a well-structured markdown document.

MITAuto-check passedDevOps & Cloud

Install Save Research

skills CLI
$ npx skills add meain/dotfiles --skill save-research -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install meain/dotfiles save-research --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/meain/dotfiles.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agents/.agents/skills/save-research .claude/skills/save-research && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
save-research
GitHub stars
285
Token cost
~1.6k tokens
SKILL.md length
693 words
Files
1
Skills in repo
36
Repo updated
First seen
Licence
MIT

At a glance

Summarize and save research findings from the current conversation into a well-structured markdown document.

  • Works in 5 steps: Gather Findings → Determine Output Location → Determine the Filename → …
  • Tasks that involve Markdown
  • SKILL.md covers When to Use, Instructions and Guidelines
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Save Research is an agent skill from meain/dotfiles. Summarize and save research findings from the current conversation into a well-structured markdown document. Triggers: /save-research, "save this research", "write up findings", "document what we found", "save these notes"

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering Markdown. The repository describes itself as: If there is a shell, there is a way! The licence is MIT.

When your agent uses it

  • Tasks that involve Markdown

Example prompts

  • “save this research”
  • “write up findings”
  • “document what we found”
  • “/save-research”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Gather Findings
  2. Determine Output Location
  3. Determine the Filename
  4. Write the Document
  5. Verify

What it can do on your machine

Read from SKILL.md and the folder at commit f469fb6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Save Research loads about 1.6k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 693 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from meain/dotfiles at commit f469fb6, republished under its MIT licence (© meain). 693 words, ~1,614 tokens.

Download SKILL.mdSave it as .claude/skills/save-research/SKILL.md (or your agent's skills folder).
name
save-research
description
Summarize and save research findings from the current conversation into a well-structured markdown document. Triggers: /save-research, "save this research", "write up findings", "document what we found", "save these notes"

/save-research -- Save Research Findings to Markdown

Collect, organize, and write all research findings from the current conversation into a structured markdown document for future reference.

When to Use

Use this skill when:

  • You have been researching a topic and want to preserve the findings
  • The conversation contains useful information worth saving as a reference
  • You want to build up a knowledge base over time

Instructions

Phase 1: Gather Findings
  1. Review the entire conversation history to identify all research findings, insights, code examples, links, decisions, and key takeaways.
  2. Group related findings into logical sections.
  3. Note any open questions or areas that need further research.
Phase 2: Determine Output Location

Ask the user or infer from context:

  • Project-specific research (related to the current codebase or project): Save to .mdocs/<category>/ in the project root (see Phase 2b for categories). Create the directory if it does not exist.
  • Generic / cross-project research (general knowledge, tools, techniques): Save to /Users/meain/dev/mdocs/<category>/ using the same category system as project-specific research (see Phase 2b). Create the directory if it does not exist.

If it is unclear whether the research is project-specific or generic, ask the user.

Phase 2b: Determine the Category

Project-specific documents must be placed in a category subdirectory under .mdocs/. Pick the best-fit category based on the document's purpose:

CategoryWhen to use
planStep-by-step plans for executing a task across repos/systems (has ordered steps, timelines, or rollout tiers)
guideProactive how-to instructions — "I want to do X" (testing guides, operational procedures, style guides)
runbookReactive incident response — "something broke, now what?" (triage steps, remediation, rollback procedures)
designForward-looking proposals and architecture decisions (options analysis, solution designs, feature specs)
referenceExplanations of how something already works (system behavior, patterns, tool docs, configuration references)
investigationAnalysis of bugs, performance issues, code quality, or root causes (debugging findings, violation reports, post-mortems)
taskTracking documents for specific tickets or work items (task checklists, ticket context, status tracking)

If a document spans multiple categories, pick the primary purpose:

  • A design doc that includes investigation context → design
  • A guide that was born from an investigation → guide
  • A plan driven by a specific ticket → plan (not task)

If genuinely unsure, ask the user.

Phase 3: Determine the Filename
  1. Derive a descriptive, kebab-case filename from the research topic.
    • Example: .mdocs/reference/go-generics.md, .mdocs/design/react-server-components-patterns.md
  2. For project-specific research, the full path is: .mdocs/<category>/<filename>.md
  3. If a file with the same name already exists, ask the user whether to:
    • Append to the existing file
    • Overwrite it
    • Use a different name
Show full SKILL.md (277 more words)Show less
Phase 4: Write the Document

Use the following structure for the markdown file. The title, date, tags, and status should be in YAML front matter metadata rather than in the document body. This keeps the # (h1) heading level available for use within the document content itself.

markdown
---
title: <Title of Research Topic>
date: YYYY-MM-DD
tags: [tag1, tag2, tag3]
status: complete | in-progress | needs-review
claude-session-id: ${CLAUDE_SESSION_ID}  # or pi-session-id: <ask user> when under pi agent
---

## Summary

A 2-4 sentence high-level summary of what was researched and the key conclusions.

## Findings

### <Subtopic 1>

- Key points as bullet lists
- Include code snippets in fenced blocks where relevant

### <Subtopic 2>

...

## Key Takeaways

- Numbered or bulleted list of the most important conclusions

## Code Examples

Include any significant code snippets or commands discovered during research.
Only include this section if there are meaningful code examples.

## References

- Links to documentation, articles, or other resources consulted
- Only include this section if there are references to list

## Open Questions

- Anything unresolved or worth investigating further
- Only include this section if there are open questions

Writing guidelines:

  • Always include a session ID in the YAML front matter so the source conversation can be traced back later. If ${CLAUDE_SESSION_ID} is available (Claude Code), use claude-session-id: as the key. Otherwise, when running under pi agent (check PI_CODING_AGENT=true env var), ask the user to provide the session ID and use pi-session-id: as the key. The user can run /session in pi to look up the current session ID.
  • Be concise but thorough -- these are reference documents, not prose
  • Prefer bullet points over paragraphs
  • Include concrete code examples where applicable
  • Use proper markdown formatting (headings, code fences, links)
  • Add tags that would help with future search and discovery
  • Use today's date for the Date field
Phase 5: Verify
  1. Read back the written file to confirm it was saved correctly.
  2. Report the full file path to the user.
  3. Provide a brief summary of what was captured (number of sections, key topics).

Guidelines

  • NEVER fabricate information that was not discussed in the conversation
  • NEVER omit significant findings from the conversation
  • If the conversation covered multiple unrelated topics, ask the user if they want separate files or one combined document
  • Preserve technical accuracy -- do not paraphrase code or commands incorrectly
  • Keep the document self-contained so it is useful without the original conversation context
  • Omit sections from the template that have no content (e.g., skip "Open Questions" if there are none)

© meain, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in agents/.agents/skills/save-research of meain/dotfiles.

Open the folder on GitHubat commit f469fb6

Compare with similar skills

Save Research next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Save Research compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Save Research this skillmeain/dotfiles285—~1.6kAutomated safety check: PassMIT
Docs Learn Site Structurenetdata/netdata81k—~1.7kAutomated safety check: PassGPL-3.0
Run Uatoocx/tfplan2md174—~1.2kAutomated safety check: PassMIT
Generate Demo Artifactsoocx/tfplan2md174—~798Automated safety check: PassMIT
Update Test Snapshotsoocx/tfplan2md174—~734Automated safety check: PassMIT
Triageflowershow/flowershow1.1k—~1.9kAutomated safety check: PassAGPL-3.0

Similar skills

  • Change, review or troubleshoot Learn publication, docs/.map mapping, page URLs, redirects, sidebars, MDX and ingest/CI behavior.

    81k GitHub stars~1.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Run Uat

    oocx/tfplan2md

    Run User Acceptance Testing by creating a PR with rendered markdown on GitHub or Azure DevOps.

    174 GitHub stars~1.2k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Generate the comprehensive demo markdown artifacts from the current codebase.

    174 GitHub stars~798 tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Update Test Snapshots

    oocx/tfplan2md

    Regenerate test snapshot files after intentional markdown output changes.

    174 GitHub stars~734 tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Triage

    flowershow/flowershow

    Automatically triage a newly opened GitHub issue — categorise it, verify the claim, and apply the right category and state so a maintainer or agent can pick it up.

    1.1k GitHub stars~1.9k tokensUpdated 2 days ago
    DevOps & CloudAuto-check passed
  • Okf

    scaccogatto/okf-skills

    Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read.

    408 GitHub stars~2.1k tokensUpdated 10 days ago
    DevOps & CloudAuto-check: notes

More from meain/dotfiles

All 36 skills in this repo
  • Recall

    meain/dotfiles

    Search past Claude Code and Codex sessions. An agent skill from meain/dotfiles.

    285 GitHub starsUsed in 1 repo~684 tokens
    Auto-check passed
  • Grill With Docs

    meain/dotfiles

    Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise.

    285 GitHub starsUsed in 21 repos~875 tokens
    Auto-check passed
  • Backlog

    meain/dotfiles

    Daily backlog management — full planning review OR add a single entry from a URL.

    285 GitHub stars~3k tokensUpdated 1 mo ago
    Auto-check passed
  • Concern Review

    meain/dotfiles

    Generate an interactive local HTML review page for a large PR or diff, grouping the changed files by logical concern (not just by file) so a reviewer can go through one theme at a time instead of a…

    285 GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed
  • My Weekly Report

    meain/dotfiles

    Generate a concise weekly status update in team format. An agent skill from meain/dotfiles.

    285 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Web Search

    meain/dotfiles

    Search the web using lynx and DuckDuckGo. An agent skill from meain/dotfiles.

    285 GitHub stars~830 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Save Research

What does Save Research do?

Summarize and save research findings from the current conversation into a well-structured markdown document. Save Research is an agent skill from meain/dotfiles. Summarize and save research findings from the current conversation into a well-structured markdown document.

When should I use Save Research?

Save Research fits situations like: tasks that involve Markdown.

How do I install Save Research in Claude Code?

Run `npx skills add meain/dotfiles --skill save-research -a claude-code`. Or copy the skill folder (agents/.agents/skills/save-research in meain/dotfiles) into .claude/skills/save-research in your project. Claude Code loads it when a task matches its description.

How do I install Save Research in Codex?

Run `npx skills add meain/dotfiles --skill save-research -a codex`. Or copy the skill folder (agents/.agents/skills/save-research in meain/dotfiles) into .agents/skills/save-research in your project. Codex loads it when a task matches its description.

Can I use Save Research in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add meain/dotfiles --skill save-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/save-research, .gemini/skills/save-research, .github/skills/save-research and .opencode/skills/save-research in your project.

What does Save Research need to run?

SKILL.md names no scripts, command-line tools or credentials: Save Research is instructions for the agent only.

Does Save Research access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Save Research safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Save Research use?

Save Research is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Save Research use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Save Research?

Skills that share tags, products or a category with Save Research: Docs Learn Site Structure (netdata/netdata, 81k stars), Run Uat (oocx/tfplan2md, 174 stars), Generate Demo Artifacts (oocx/tfplan2md, 174 stars) and Update Test Snapshots (oocx/tfplan2md, 174 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Save Research?

meain (a GitHub user) maintains it in meain/dotfiles, which has 285 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on September 5, 2026.

Source: meain/dotfiles on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.