Agent skill

Tech Distiller

by yaofeino1 in yaofeino1/tech-distiller

Collects technical documents from URLs, files, wikis or APIs, filters them by role or technical direction, and writes a structured report on architecture, algorithms and design decisions.

No licenceAuto-check passedKnowledge Management

Install Tech Distiller

skills CLI
$ npx skills add yaofeino1/tech-distiller --skill tech-distiller -a claude-code

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

GitHub CLI
$ gh skill install yaofeino1/tech-distiller tech-distiller --agent claude-code

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

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

Facts

Skill name
tech-distiller
GitHub stars
144
Token cost
~1.2k tokens
SKILL.md length
458 words
Files
6 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

Collects technical documents from URLs, files, wikis or APIs, filters them by role or technical direction, and writes a structured report on architecture, algorithms and design decisions.

  • Works in 5 steps: Gather Inputs → Fetch & Filter Documents → Extract Technical Signals → …
  • Summarizing a team's internal technical docs into one report
  • SKILL.md covers Workflow, Evolution — 报告进化机制 and Notes
  • Runs Python scripts from its folder

What it does

The agent asks only for what is missing: the document sources, the technical direction or role to focus on, the output format (Markdown by default, or Word or PowerPoint), the depth (overview or detailed) and the target audience. It fetches each source with web fetch or file reads, or with an installed skill for a knowledge base, then filters the content using references/filtering-guide.md.

Filtering keeps paragraphs that match at least two direction-specific signals and drops off-topic material such as HR or legal text. If fewer than 3 relevant documents turn up, the agent warns you and offers to broaden the scope, and sources above 50k tokens are chunked and summarized in passes. Extracted signals include architecture, core algorithms, interfaces, performance and scale, design decisions, tech stack and open problems.

The report is rendered with scripts/render_report.py or written directly, with empty sections left out, and Word or PowerPoint output is handed to the docx or pptx skill. An existing report can later be evolved by feeding new documents into it.

When your agent uses it

  • Summarizing a team's internal technical docs into one report
  • Producing a role-specific report such as backend, ML or data platform
  • Updating an earlier technical report with new documents
  • Writing onboarding material that captures architecture and design decisions

Example prompts

  • “Distill the docs in ./wiki-export into a backend architecture report in Markdown.”
  • “Generate a detailed report for the recommendation direction from these three design docs, as a PowerPoint.”
  • “Update our existing data platform report with the new design docs I added.”

Requirements

  • Network access to fetch URL sources
  • Access or credentials for any internal wiki or API sources
  • Python with the packages in requirements.txt for scripts/render_report.py

Workflow steps

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

  1. Gather Inputs
  2. Fetch & Filter Documents
  3. Extract Technical Signals
  4. Generate Report
  5. Deliver Output

What it can do on your machine

Read from SKILL.md and the folder at commit 035fe2c. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    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

Tech Distiller loads about 1.2k tokens when it runs, and up to ~1.9k if it reads all its reference files. Until then it costs about 169 tokens; SKILL.md has 458 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~169
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.9k

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); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 458 words (~1,155 tokens).

name
tech-distiller

Read the full SKILL.md on GitHub

Files

SKILL.md and 5 other files (scripts, references) in the repository root of yaofeino1/tech-distiller.

  • SKILL.md
  • .gitignore
  • README.md
  • references/filtering-guide.md
  • requirements.txt
  • scripts/render_report.py

Open the folder on GitHubat commit 035fe2c

Compare with similar skills

Tech Distiller 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.

Tech Distiller compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tech Distiller this skillyaofeino1/tech-distiller144—~1.2kAutomated safety check: PassNone
Mineru Document Exploreropendatalab/MinerU-Document-Explorer638—~6.2kAutomated safety check: NotesMIT
Doc SummarizerBlackBeltTechnology/pi-agent-dashboard315—~1.2kAutomated safety check: PassMIT
Offensive ReportingSnailSploit/Claude-Red7.4k—~3.7kAutomated safety check: PassMIT
Documentsmagnus919/agent-skills115—~2.3kAutomated safety check: PassMIT
Document Generationautomateyournetwork/netclaw676—~1.9kAutomated safety check: PassApache-2.0

Similar skills

  • Mineru Document Explorer

    opendatalab/MinerU-Document-Explorer

    MinerU Document Explorer — Agent-native knowledge engine. An agent skill from opendatalab/MinerU-Document-Explorer.

    638 GitHub stars~6.2k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check: notes
  • Doc Summarizer

    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.

    315 GitHub stars~1.2k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Offensive Reporting

    SnailSploit/Claude-Red

    Penetration test and red team report writing methodology. An agent skill from SnailSploit/Claude-Red.

    7.4k GitHub stars~3.7k tokensUpdated 20 days ago
    SecurityAuto-check passed
  • Documents

    magnus919/agent-skills

    Generate, inspect, validate, and fix PDF, Word (.docx), Excel (.xlsx), and PowerPoint (.pptx) documents: turn structured content into render-ready artifacts, verify structural and output quality…

    115 GitHub stars~2.3k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Document Generation

    automateyournetwork/netclaw

    Generate Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) documents and fill existing PDF forms, from real NetClaw data, with per-element provenance and no fabrication.

    676 GitHub stars~1.9k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Knowledge Ingest

    evolution-foundation/evo-nexus

    Upload a file (PDF, DOCX, PPTX, XLSX, HTML, EPUB, image) or URL to the Knowledge base.

    545 GitHub stars~922 tokensUpdated 4 mo ago
    Documents & OfficeAuto-check passed

Questions about Tech Distiller

What does Tech Distiller do?

Collects technical documents from URLs, files, wikis or APIs, filters them by role or technical direction, and writes a structured report on architecture, algorithms and design decisions. The agent asks only for what is missing: the document sources, the technical direction or role to focus on, the output format (Markdown by default, or Word or PowerPoint), the depth (overview or detailed) and the target audience.md.

When should I use Tech Distiller?

Tech Distiller fits situations like: summarizing a team's internal technical docs into one report; producing a role-specific report such as backend, ML or data platform; updating an earlier technical report with new documents; writing onboarding material that captures architecture and design decisions.

How do I install Tech Distiller in Claude Code?

Run `npx skills add yaofeino1/tech-distiller --skill tech-distiller -a claude-code`. Or copy the skill folder (the yaofeino1/tech-distiller repository) into .claude/skills/tech-distiller in your project. Claude Code loads it when a task matches its description.

How do I install Tech Distiller in Codex?

Run `npx skills add yaofeino1/tech-distiller --skill tech-distiller -a codex`. Or copy the skill folder (the yaofeino1/tech-distiller repository) into .agents/skills/tech-distiller in your project. Codex loads it when a task matches its description.

Can I use Tech Distiller 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 yaofeino1/tech-distiller --skill tech-distiller -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tech-distiller, .gemini/skills/tech-distiller, .github/skills/tech-distiller and .opencode/skills/tech-distiller in your project.

What does Tech Distiller need to run?

Going by SKILL.md and its folder, Tech Distiller needs Python for the scripts in its folder. Our summary lists: Network access to fetch URL sources; Access or credentials for any internal wiki or API sources; Python with the packages in requirements.txt for scripts/render_report.py.

Does Tech Distiller 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 Tech Distiller 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Tech Distiller use?

No licence was found for Tech Distiller or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Tech Distiller 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. Its references folder adds about 779 tokens, read only when the agent opens those files.

What are the alternatives to Tech Distiller?

Skills that share tags, products or a category with Tech Distiller: Mineru Document Explorer (opendatalab/MinerU-Document-Explorer, 638 stars), Doc Summarizer (BlackBeltTechnology/pi-agent-dashboard, 315 stars), Offensive Reporting (SnailSploit/Claude-Red, 7.4k stars) and Documents (magnus919/agent-skills, 115 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tech Distiller?

yaofeino1 (a GitHub user) maintains it in yaofeino1/tech-distiller, which has 144 GitHub stars. The repository was last updated on April 6, 2026.

Source: yaofeino1/tech-distiller on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.