Light File Reading
Light0305/Light-skills
Light 多格式文件深度理解常驻技能：强大地读 Word / PDF / PPTX / Excel / CSV / 图片 / 视频 / 代码 / 压缩包，不只提取文字，而是理解结构 / 图表 / 数据 / 格式要求 / 隐含意图，产结构化"理解笔记"五面 （结构逻辑·关键内容·格式约束·视觉风格·可复用）并映射到下游技能动作（这个文件→接下来能做什么）。
Summarize documents of any size: extract with the document-converter engine, chunk to fit context, fan out to subagents, then synthesize one unified summary.
Install Doc Summarizer
$ npx skills add BlackBeltTechnology/pi-agent-dashboard --skill doc-summarizer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install BlackBeltTechnology/pi-agent-dashboard doc-summarizer --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/BlackBeltTechnology/pi-agent-dashboard.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/document-converter/.pi/skills/doc-summarizer .claude/skills/doc-summarizer && 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 "doc-summarizer" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/document-converter/.pi/skills/doc-summarizer into .claude/skills/doc-summarizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-summarizer", 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/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/document-converter/.pi/skills/doc-summarizerType 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 BlackBeltTechnology/pi-agent-dashboard --skill doc-summarizer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install BlackBeltTechnology/pi-agent-dashboard doc-summarizer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/document-converter/.pi/skills/doc-summarizer .agents/skills/doc-summarizer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "doc-summarizer" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/document-converter/.pi/skills/doc-summarizer into .agents/skills/doc-summarizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-summarizer", 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 BlackBeltTechnology/pi-agent-dashboard --skill doc-summarizer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install BlackBeltTechnology/pi-agent-dashboard doc-summarizer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/document-converter/.pi/skills/doc-summarizer .cursor/skills/doc-summarizer && 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 "doc-summarizer" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/document-converter/.pi/skills/doc-summarizer into .cursor/skills/doc-summarizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-summarizer", 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/BlackBeltTechnology/pi-agent-dashboard.git --path packages/document-converter/.pi/skills/doc-summarizer--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 BlackBeltTechnology/pi-agent-dashboard --skill doc-summarizer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install BlackBeltTechnology/pi-agent-dashboard doc-summarizer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/document-converter/.pi/skills/doc-summarizer .gemini/skills/doc-summarizer && 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 "doc-summarizer" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/document-converter/.pi/skills/doc-summarizer into .gemini/skills/doc-summarizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-summarizer", 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 BlackBeltTechnology/pi-agent-dashboard doc-summarizerInstalls 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 BlackBeltTechnology/pi-agent-dashboard --skill doc-summarizer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/document-converter/.pi/skills/doc-summarizer .github/skills/doc-summarizer && 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 "doc-summarizer" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/document-converter/.pi/skills/doc-summarizer into .github/skills/doc-summarizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-summarizer", 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 BlackBeltTechnology/pi-agent-dashboard --skill doc-summarizer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install BlackBeltTechnology/pi-agent-dashboard doc-summarizer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/document-converter/.pi/skills/doc-summarizer .opencode/skills/doc-summarizer && 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 "doc-summarizer" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/document-converter/.pi/skills/doc-summarizer into .opencode/skills/doc-summarizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doc-summarizer", 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
doc-summarizer- GitHub stars
- 315
- Token cost
- ~1.2k tokens
- SKILL.md length
- 354 words
- Files
- 1
- Skills in repo
- 66
- Repo updated
- First seen
- Licence
- MIT
At a glance
Summarize documents of any size: extract with the document-converter engine, chunk to fit context, fan out to subagents, then synthesize one unified summary.
- Works in 2 steps: Extract to Markdown via the engine → Decide direct vs. chunked
- Tasks that involve Summarization
- SKILL.md covers Prerequisites, Step 1 — Extract to Markdown…, Step 2 — Decide direct vs.… and Step 3a — Direct summarization…, plus 4 more sections
- Calls npm
What it does
Doc Summarizer is an agent skill from BlackBeltTechnology/pi-agent-dashboard. Summarize documents of any size: extract with the document-converter engine, chunk to fit context, fan out to subagents, then synthesize one unified summary. Handles PDF, DOCX, PPTX, XLSX, HTML, CSV, TXT, MD. Triggers: "summarize this document", "what's in this PDF", "give me a summary of these files", "extract key points from", "condense this document", "TL;DR of this file".
Its SKILL.md is about 1.2k 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, covering Summarization, Word documents and PowerPoint presentations. It works with Microsoft Excel, Microsoft PowerPoint, Microsoft Word and Docker. The repository describes itself as: Real-time web dashboard for pi coding-agent sessions. Multi-session view, live chat mirroring, integrated terminal, diff viewer, pi-flows execution, and mobile-first remote… The licence is MIT.
When your agent uses it
- Tasks that involve Summarization
- Tasks that involve Word documents
- Tasks that involve PowerPoint presentations
Example prompts
- “summarize this document”
- “s in this PDF”
- “give me a summary of these files”
- “/doc-summarizer”
Requirements
- Python 3
- Docker
Workflow steps
2 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 86e8e4d. 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
Shell commands in SKILL.md call:
npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
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
Doc Summarizer loads about 1.2k tokens when it runs. Until then it costs about 98 tokens; SKILL.md has 354 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 BlackBeltTechnology/pi-agent-dashboard at commit 86e8e4d, republished under its MIT licence (© BlackBeltTechnology). 354 words, ~1,158 tokens.
Download SKILL.mdSave it as
.claude/skills/doc-summarizer/SKILL.md (or your agent's skills folder).- name
- doc-summarizer
- description
- Summarize documents of any size: extract with the document-converter engine, chunk to fit context, fan out to subagents, then synthesize one unified summary. Handles PDF, DOCX, PPTX, XLSX, HTML, CSV, TXT, MD. Triggers: "summarize this document", "what's in this PDF", "give me a summary of these files", "extract key points from", "condense this document", "TL;DR of this file".
Document Summarizer
Summarize documents of any size. Extraction goes through the document-converter
engine facade (dc.convertToMarkdown) — the same Docker-quarantined engine the
document-converter skill uses. There are NO host-side extractor scripts here;
the facade is the only extraction surface. Chunking and synthesis are agent work.
Prerequisites
- The
document-converterpackage built and runnable: Docker available, image built (cd packages/document-converter && npm run build:image). See thedocument-converterSKILL for the full facade contract. - Nothing else. No
pdftotext/pandoc/Python on the host — the engine owns all format handling inside Docker.
Step 1 — Extract to Markdown via the engine
Call the facade; never invoke Python, docling, or pdftotext directly.
import { createDocumentConverter } from "@blackbelt-technology/pi-dashboard-document-converter";
const dc = createDocumentConverter({
image: "pi-doc-engine:0.1.0",
stagingDir: "/abs/staging",
mounts: ["/docs"], // files outside cwd need a root (mounts or workspaceRoot), else PATH_NOT_ALLOWED
});
const { output } = await dc.convertToMarkdown("<file_path>"); // digital PDF/DOCX/…
// scanned PDF: pass OCR explicitly
await dc.convertToMarkdown("<file_path>", { ocr: { mode: "force", lang: ["english"] } });The result is a provenance-stamped .md in stagingDir. Read that file to get
the document text. On failure the call rejects with DocConverterError
(.code, .stderr) — surface UNSUPPORTED_FORMAT, PATH_NOT_ALLOWED, OCR_LANG_UNSUPPORTED,
INGEST_FAILED, DOCKER_UNAVAILABLE rather than retrying blindly.
Step 2 — Decide direct vs. chunked
Measure the extracted Markdown:
- < ~8,000 words (~10k tokens): summarize directly in the current context (Step 3a).
- >= ~8,000 words: chunk and fan out (Step 3b).
Step 3a — Direct summarization (small documents)
Read the extracted .md and produce a summary using the output format
below: title/subject, key points, entities, document type, language.
Show full SKILL.md (189 more words)Show less
Step 3b — Chunked summarization (large documents)
Chunk. Split the extracted Markdown into context-friendly pieces (~3,000–4,000 tokens each). Prefer natural boundaries — headings, sections, page markers in the engine output — over blind character cuts. No script needed; split with judgment.
Fan out. For each chunk launch a subagent (
Agenttool,subagent_type: "general-purpose"), up to ~3–4 concurrent:Summarize this text chunk (chunk {i}/{total} of document '{filename}'). Extract: key points, entities (people/orgs/dates/amounts), topics, and any conclusions or action items. Output as structured markdown. Text: {chunk_text}Merge. Collect chunk summaries, deduplicate entities and key points, and produce one unified summary in the output format. If the merged result is still > ~8,000 words, run one more summarization pass on it.
Batch summarization
For a directory or glob: extract each file via dc.convertToMarkdown (run a few
in parallel), then apply the single-document workflow per file. Emit a table:
| # | File | Type | Language | Words | Key Topics | Summary |
|---|------|------|----------|-------|------------|---------|
| 1 | invoice.pdf | Invoice | EN | 450 | AcmeCorp, 2024Q4 | Quarterly invoice… |Summary output format
## Summary: {document_name}
**Type**: {document_type}
**Language**: {language}
**Word Count**: {word_count}
**Date**: {detected_date or file_modified_date}
### Key Points
- Point 1
- Point 2
### Entities
- **People**: …
- **Organizations**: …
- **Dates**: …
- **Amounts**: …
### Brief Summary
{2-3 paragraph narrative summary}Special cases
- Scanned PDF, no text: the engine returns little/empty text on
mode: auto. Re-run withocr: { mode: "force", lang: [...] }(canonical language names). - Encrypted / unsupported / empty: surface the
DocConverterError.codeand.stderr; report metadata only. - Mixed-language: report the primary language, note others present.
© BlackBeltTechnology, 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 packages/document-converter/.pi/skills/doc-summarizer of BlackBeltTechnology/pi-agent-dashboard.
Open the folder on GitHubat commit 86e8e4d
Compare with similar skills
Doc Summarizer 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 |
|---|---|---|---|---|---|---|
| Doc Summarizer this skillBlackBeltTechnology/pi-agent-dashboard | 315 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Light File ReadingLight0305/Light-skills | 640 | — | ~4.1k | Automated safety check: Pass | MIT | |
| Heavy File Ingestion Claude CodeNateBJones-Projects/OB1 | 4.7k | — | ~614 | Automated safety check: Pass | Custom licence | |
| Heavy File Ingestion Claude DesktopNateBJones-Projects/OB1 | 4.7k | — | ~547 | Automated safety check: Pass | Custom licence | |
| Document Converterwentorai/Research-Claw | 858 | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| Compdf Conversion CLILeoYeAI/openclaw-master-skills | 2.2k | — | ~5.9k | Automated safety check: Pass | Proprietary |
Similar skills
Heavy File Ingestion Claude Code
NateBJones-Projects/OB1
Use in Claude Code when a user asks to read, analyze, summarize, or extract from a heavyweight file such as PDF, DOCX, PPTX, XLSX, CSV, or TSV.
Heavy File Ingestion Claude Desktop
NateBJones-Projects/OB1
Use in Claude Desktop when a user asks to read, analyze, summarize, or extract from a heavyweight file such as PDF, DOCX, PPTX, XLSX, CSV, or TSV.
Document Converter
wentorai/Research-Claw
Convert Office documents (PPTX, DOCX, XLSX, PDF, HTML, CSV, JSON, XML, images) to Markdown using Microsoft MarkItDown.
Compdf Conversion CLI
LeoYeAI/openclaw-master-skills
MUST use for ANY PDF or image format conversion task — converting PDF and images (JPG/JPEG/PNG/BMP/TIFF/TIF/WEBP/JPEG2000) to 10 formats (Word, Excel, PPT, HTML, Image, TXT, JSON, Markdown, RTF…
To Markdown
Mathews-Tom/armory
Convert any file or URL to clean Markdown: PDF, DOCX, XLSX, PPTX, HTML, images (OCR), audio, CSV, YouTube.
More from BlackBeltTechnology/pi-agent-dashboard
All 66 skills in this repoBrowser
BlackBeltTechnology/pi-agent-dashboard
Browser automation via the agent-browser CLI. An agent skill from BlackBeltTechnology/pi-agent-dashboard.
CI Troubleshoot
BlackBeltTechnology/pi-agent-dashboard
Diagnose failed GitHub Actions runs for pi-agent-dashboard: the 11-file workflow taxonomy, affected-test selection, the release pipeline, known failure modes, and how to read gh run logs and…
Debug Dashboard
BlackBeltTechnology/pi-agent-dashboard
Diagnose problems in the running pi-agent-dashboard system: server.log, /api/health, bridge WebSocket connectivity, vitest triage, known-issue FAQ entries.
Implement
BlackBeltTechnology/pi-agent-dashboard
Disciplined implementation in pi-agent-dashboard: the rebuild matrix (extension→reload, server→restart, client→build+restart, openspec-apply→full rebuild) plus the project's code discipline rules.
Pi Dashboard
BlackBeltTechnology/pi-agent-dashboard
Monitor and control the pi-dashboard server. An agent skill from BlackBeltTechnology/pi-agent-dashboard.
Session To Guideline
BlackBeltTechnology/pi-agent-dashboard
Turn a pi session into a Markdown "how-we-did-it" collaboration guideline: reads the session's JSONL transcript and synthesizes a reusable playbook of which prompts worked, what had to be steered…
Related
Categories
Questions about Doc Summarizer
What does Doc Summarizer do?
Summarize documents of any size: extract with the document-converter engine, chunk to fit context, fan out to subagents, then synthesize one unified summary. Doc Summarizer is an agent skill from BlackBeltTechnology/pi-agent-dashboard. Summarize documents of any size: extract with the document-converter engine, chunk to fit context, fan out to subagents, then synthesize one unified summary.
When should I use Doc Summarizer?
Doc Summarizer fits situations like: tasks that involve Summarization; tasks that involve Word documents; tasks that involve PowerPoint presentations.
How do I install Doc Summarizer in Claude Code?
Run `npx skills add BlackBeltTechnology/pi-agent-dashboard --skill doc-summarizer -a claude-code`. Or copy the skill folder (packages/document-converter/.pi/skills/doc-summarizer in BlackBeltTechnology/pi-agent-dashboard) into .claude/skills/doc-summarizer in your project. Claude Code loads it when a task matches its description.
How do I install Doc Summarizer in Codex?
Run `npx skills add BlackBeltTechnology/pi-agent-dashboard --skill doc-summarizer -a codex`. Or copy the skill folder (packages/document-converter/.pi/skills/doc-summarizer in BlackBeltTechnology/pi-agent-dashboard) into .agents/skills/doc-summarizer in your project. Codex loads it when a task matches its description.
Can I use Doc Summarizer 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 BlackBeltTechnology/pi-agent-dashboard --skill doc-summarizer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/doc-summarizer, .gemini/skills/doc-summarizer, .github/skills/doc-summarizer and .opencode/skills/doc-summarizer in your project.
What does Doc Summarizer need to run?
Going by SKILL.md and its folder, Doc Summarizer needs the command-line tools its instructions call (npm). Our summary lists: Python 3; Docker.
Does Doc Summarizer access the network?
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Doc Summarizer 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 Doc Summarizer use?
Doc Summarizer 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 Doc Summarizer use?
About 1.2k tokens (SKILL.md is roughly 4.6k 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 Doc Summarizer?
Skills that share tags, products or a category with Doc Summarizer: Light File Reading (Light0305/Light-skills, 640 stars), Heavy File Ingestion Claude Code (NateBJones-Projects/OB1, 4.7k stars), Heavy File Ingestion Claude Desktop (NateBJones-Projects/OB1, 4.7k stars) and Document Converter (wentorai/Research-Claw, 858 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Doc Summarizer?
BlackBeltTechnology (a GitHub organization) maintains it in BlackBeltTechnology/pi-agent-dashboard, which has 315 GitHub stars. The repository holds 66 skills in this directory. The repository was last updated on October 8, 2026.
Source: BlackBeltTechnology/pi-agent-dashboard on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.