Markdown Article Formatter
JimLiu/baoyu-skills
Reformats plain text or Markdown articles with frontmatter, a title, a summary, headings, bold, lists and code blocks, and saves a separate formatted copy.
Summarize a document, meeting transcript, or email — pick a style that matches what the content actually is, and fold long input forward in sections instead of losing the back half.
Install Summarize
$ npx skills add amd/gaia --skill summarize -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install amd/gaia summarize --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/amd/gaia.git skills-src && mkdir -p .claude/skills && cp -r skills-src/hub/skills/summarize .claude/skills/summarize && rm -rf skills-srcUse ~/.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/
Install the "summarize" agent skill from https://github.com/amd/gaia/tree/main/hub/skills/summarize into .claude/skills/summarize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "summarize", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/amd/gaia/tree/main/hub/skills/summarizeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add amd/gaia --skill summarize -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install amd/gaia summarize --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/amd/gaia.git skills-src && mkdir -p .agents/skills && cp -r skills-src/hub/skills/summarize .agents/skills/summarize && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "summarize" agent skill from https://github.com/amd/gaia/tree/main/hub/skills/summarize into .agents/skills/summarize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "summarize", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add amd/gaia --skill summarize -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install amd/gaia summarize --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/amd/gaia.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/hub/skills/summarize .cursor/skills/summarize && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "summarize" agent skill from https://github.com/amd/gaia/tree/main/hub/skills/summarize into .cursor/skills/summarize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "summarize", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/amd/gaia.git --path hub/skills/summarize--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add amd/gaia --skill summarize -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install amd/gaia summarize --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/amd/gaia.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/hub/skills/summarize .gemini/skills/summarize && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "summarize" agent skill from https://github.com/amd/gaia/tree/main/hub/skills/summarize into .gemini/skills/summarize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "summarize", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install amd/gaia summarizeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add amd/gaia --skill summarize -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/amd/gaia.git skills-src && mkdir -p .github/skills && cp -r skills-src/hub/skills/summarize .github/skills/summarize && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "summarize" agent skill from https://github.com/amd/gaia/tree/main/hub/skills/summarize into .github/skills/summarize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "summarize", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add amd/gaia --skill summarize -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install amd/gaia summarize --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/amd/gaia.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/hub/skills/summarize .opencode/skills/summarize && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "summarize" agent skill from https://github.com/amd/gaia/tree/main/hub/skills/summarize into .opencode/skills/summarize/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "summarize", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
summarize- GitHub stars
- 1.6k
- Token cost
- ~1.5k tokens
- SKILL.md length
- 781 words
- Files
- 1
- Skills in repo
- 44
- Repo updated
- First seen
- Licence
- MIT
At a glance
Summarize a document, meeting transcript, or email — pick a style that matches what the content actually is, and fold long input forward in sections instead of losing the back half.
- Works in 4 steps: Identify what you're summarizing before… → Get the full text. For an indexed… → Decide if it fits in one pass. If the… → …
- The user pastes
- SKILL.md covers Procedure, Styles, Folding a long document… and Fork this
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Summarize is an agent skill from amd/gaia. Summarize a document, meeting transcript, or email — pick a style that matches what the content actually is, and fold long input forward in sections instead of losing the back half. Use when the user pastes or points at a transcript, email, PDF, or long document and asks for a summary, action items, or key decisions.
Its SKILL.md is about 1.5k 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 Documents & Office. The repository describes itself as: Build AI agents for your PC. The licence is MIT.
When your agent uses it
- The user pastes
- Points at a transcript
- Long document and asks for a summary
Example prompts
- “/summarize”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Identify what you're summarizing before you pick a style. Read the
- Get the full text. For an indexed document, index_document it first
- Decide if it fits in one pass. If the content is short enough for you
- Write to the style, not a generic summary. Match the length and
What it can do on your machine
Read from SKILL.md and the folder at commit 6c3bb5c. 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.
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
Summarize loads about 1.5k tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 781 words of instructions outside code blocks.
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 amd/gaia at commit 6c3bb5c, republished under its MIT licence (© amd). 781 words, ~1,495 tokens.
Download SKILL.mdSave it as
.claude/skills/summarize/SKILL.md (or your agent's skills folder).- name
- summarize
- description
- Summarize a document, meeting transcript, or email — pick a style that matches what the content actually is, and fold long input forward in sections instead of losing the back half. Use when the user pastes or points at a transcript, email, PDF, or long document and asks for a summary, action items, or key decisions.
- license
- MIT
- version
- 1.0.0
Summarize
A summary that drops the back half of a long document is worse than no summary — it looks complete and isn't. Everything here exists to stop that: pick the right style for what the content is, and never lose earlier material when the input is too long to read in one pass.
Procedure
Identify what you're summarizing before you pick a style. Read the first portion and classify it:
- Transcript — speaker labels, timestamps, back-and-forth dialogue.
- Email —
From:/To:/Subject:headers, a greeting/sign-off, one author's voice. - Document / PDF / business content — reports, decks, specs; prose without dialogue structure. When it's genuinely ambiguous, say which you picked and why in one clause rather than silently guessing — the style below changes with it.
Get the full text. For an indexed document,
index_documentit first if it isn't already (list_indexed_documentsto check), then either callsummarize_document(file_path, summary_type)ordump_documentfirst if you need the raw extracted text. For pasted text or a plain text file,read_fileis enough.summary_typeaccepts onlybrief,detailed, orbullets— anything else comes back as an error, not a summary. The named styles below are how you shape the output: pick the closest of those three, then write to the style the user actually asked for. For "what were the action items", that meansdetailed(so nothing is dropped) and then writing the list yourself from the text.Decide if it fits in one pass. If the content is short enough for you to read and reason over directly, write the summary yourself using the style instructions below — don't reach for the section-by-section tool path for a two-page memo. For anything long, use
summarize_document(which already sections and folds internally) or the manual fold-forward procedure below when the tool isn't available for the content you have.Write to the style, not a generic summary. Match the length and structure rules exactly — a "brief" that runs to eight sentences failed the request even if every sentence is accurate.
Styles
Transcripts and emails — conversational, outcome-focused:
Only brief, detailed and bullets are real summary_type values; the
rest name a shape you write yourself.
| Style | What to produce |
|---|---|
| brief / executive | 2–3 sentences on the key outcomes and decisions. |
| detailed | Full paragraph coverage of every major topic and outcome. |
| participants | Simple list of who was involved, with role/title if known. |
| action_items | Simple list of what was assigned, and to whom if stated. |
| key_decisions | Simple list of concrete decisions and outcomes — not discussion. |
| topics_discussed | Simple list of the subjects covered. |
Documents, PDFs, and business content — numbers before narrative:
| Style | What to produce |
|---|---|
brief | At most 3 sentences, no bullets, only the 2–3 essential takeaways. No filler ("Overall", "In summary"). |
detailed | 250+ words. Extract every number, percentage, dollar amount, date, and metric. Name competitors, partners, customers, technologies. Full paragraphs, no bullets. |
bullets | At most 3 bullets total, each under 20 words, one idea per bullet. |
| executive | At most 5 sentences. Priority order: (1) quantitative metrics, (2) financial data, (3) strategic outcomes, (4) competitive differentiators. Always keep the specific numbers. Board-ready tone, no bullets. |
The rule underneath the table: for business documents, a metric always
outranks the marketing language around it. "Revenue grew 40% YoY to $12M" is
the sentence that survives a brief; "the company is scaling rapidly" is not.
Show full SKILL.md (235 more words)Show less
Folding a long document forward (map-reduce)
summarize_document already does this internally when it's available — call
it and you're done. Reach for the manual version only when you're working
from pasted text or a file too large to read in one pass and the tool isn't
an option:
- Split the text into ordered chunks, breaking on paragraph boundaries where possible rather than mid-sentence.
- Summarize the first chunk normally, in the target style.
- For every chunk after that, summarize it against the running summary: given the summary so far and the new chunk, output only the facts in the new chunk that are not already captured — no restating, no rephrasing what came before, no transition filler like "Additionally". This is the whole point of folding forward instead of summarizing each chunk in isolation: isolated per-chunk summaries repeat themselves and drift from the style once concatenated; folding keeps one coherent summary that only grows by what's actually new.
- Append each chunk's new-facts output to the running summary in order. The final running summary is the answer — do not re-summarize it again at the end, that just re-introduces the drift step 3 was avoiding.
Fork this
Swap the document table's priority order for a different domain (legal: obligations and deadlines before financial terms; incident review: root cause and impact before remediation steps) and the same fold-forward procedure carries a completely different kind of long input.
© amd, 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 hub/skills/summarize of amd/gaia.
Open the folder on GitHubat commit 6c3bb5c
Compare with similar skills
Summarize 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Summarize this skillamd/gaia | 1.6k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Markdown Article FormatterJimLiu/baoyu-skills | 26k | 6 repos | ~3.5k | Automated safety check: Pass | MIT | |
| MarkitdownImCa0/just-laws | 781 | 14 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Obsidian MarkdownAtmosphere/atmosphere | 3.8k | 20 repos | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| DOCXrvdbreemen/OTGW-firmware | 207 | 33 repos | ~4.3k | Automated safety check: Pass | Proprietary | |
| Gzh Designisjiamu/gzh-design-skill | 3.9k | 1 repos | ~2.2k | Automated safety check: Pass | AGPL-3.0 |
Similar skills
Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
Obsidian Markdown
Atmosphere/atmosphere
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax.
DOCX
rvdbreemen/OTGW-firmware
A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx files).
Gzh Design
isjiamu/gzh-design-skill
微信公众号文章排版引擎，将 Markdown 转换为可直接粘贴到公众号编辑器的 HTML。主题风格从 references/theme-index.md 注册的自定义主题库中选取，自动章节编号、关键词下划线标记、引言卡片、目录导航、代码块、图片/GIF、作者签名。支持 Markdown / Word(.docx) / PDF / 纯文本输入（非 Markdown…
Word Document Reader and Writer
HKUDS/DeepTutor
Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.
More from amd/gaia
All 44 skills in this repoGAIA Agent Eval Scorecard
amd/gaia
Adds a release eval scorecard to a GAIA hub agent by writing a harness adapter, running a real eval, and wiring the result into the agent's README and release gate.
GAIA Sidecar Agent Release
amd/gaia
Walks through releasing a GAIA sidecar agent as a frozen binary plus npm client through the tag-triggered Agent Hub CI pipeline, with a human gate before publishing.
Analyzing Claude Code Sessions
amd/gaia
Mines local Claude Code session transcripts with a deterministic Python pipeline to show what the agent is actually used for, how often it fails and what it costs.
GAIA Agent Benchmarking
amd/gaia
Benchmarks AMD's GAIA agent against Claude Code and across models on quality, honesty, steps, tokens, time and real cost, using gaia eval tasks.
Verified Coding Workflow
amd/gaia
Guides safe code changes by finding the right file with grep or semantic search, reading before editing, reproducing bugs first, and proving a fix with a real test run.
GAIA Agent Builder
amd/gaia
Walks through scaffolding, writing and testing a new GAIA agent as a Python class with the SDK, from the base Agent subclass to registered tool methods.
Related
Categories
Questions about Summarize
What does Summarize do?
Summarize a document, meeting transcript, or email — pick a style that matches what the content actually is, and fold long input forward in sections instead of losing the back half. Summarize is an agent skill from amd/gaia. Summarize a document, meeting transcript, or email — pick a style that matches what the content actually is, and fold long input forward in sections instead of losing the back half.
When should I use Summarize?
Summarize fits situations like: the user pastes; points at a transcript; long document and asks for a summary.
How do I install Summarize in Claude Code?
Run `npx skills add amd/gaia --skill summarize -a claude-code`. Or copy the skill folder (hub/skills/summarize in amd/gaia) into .claude/skills/summarize in your project. Claude Code loads it when a task matches its description.
How do I install Summarize in Codex?
Run `npx skills add amd/gaia --skill summarize -a codex`. Or copy the skill folder (hub/skills/summarize in amd/gaia) into .agents/skills/summarize in your project. Codex loads it when a task matches its description.
Can I use Summarize 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 amd/gaia --skill summarize -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/summarize, .gemini/skills/summarize, .github/skills/summarize and .opencode/skills/summarize in your project.
What does Summarize need to run?
SKILL.md names no scripts, command-line tools or credentials: Summarize is instructions for the agent only.
Does Summarize 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 Summarize 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 Summarize use?
Summarize is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Summarize use?
About 1.5k tokens (SKILL.md is roughly 6k 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 Summarize?
Skills that share tags, products or a category with Summarize: Markdown Article Formatter (JimLiu/baoyu-skills, 26k stars), Markitdown (ImCa0/just-laws, 781 stars), Obsidian Markdown (Atmosphere/atmosphere, 3.8k stars) and DOCX (rvdbreemen/OTGW-firmware, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Summarize?
amd (a GitHub organization) maintains it in amd/gaia, which has 1,580 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on October 6, 2026.
Source: amd/gaia on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.