New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Human Distill

by HybridAIOne in HybridAIOne/hybridclaw

Distill a real person into a hireable coworker agent from their source material — chat exports, emails, meeting transcripts, documents, interviews, and live mirroring.

MITAuto-check passed

Install Human Distill

skills CLI
$ npx skills add HybridAIOne/hybridclaw --skill human-distill -a claude-code

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

GitHub CLI
$ gh skill install HybridAIOne/hybridclaw human-distill --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/HybridAIOne/hybridclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/human-distill .claude/skills/human-distill && 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
human-distill
GitHub stars
159
Token cost
~1.9k tokens
SKILL.md length
813 words
Files
5 (incl. references)
Skills in repo
72
Repo updated
First seen
Licence
MIT

At a glance

Distill a real person into a hireable coworker agent from their source material — chat exports, emails, meeting transcripts, documents, interviews, and live mirroring.

  • Works in 4 steps: Consent first. Distilling a real, named… → Evidence or nothing. Every claim in… → Never impersonate. The coworker mirrors… → …
  • The operator wants to clone a colleague
  • SKILL.md covers Hard rules, Pipeline, Intake modalities and Incremental updates and…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Human Distill is an agent skill from HybridAIOne/hybridclaw. Distill a real person into a hireable coworker agent from their source material — chat exports, emails, meeting transcripts, documents, interviews, and live mirroring. Use when the operator wants to clone a colleague, build a coworker from someone's writing, onboard a digital twin, or asks to 'distill', 'clone', or 'mirror' a person. Consent-gated for real humans.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/extraction-contract.md`, `references/interview-protocol.md` and `references/mirroring.md`).

The repository describes itself as: Enterprise-ready self-hosted AI assistant runtime with sandboxed execution, secure credentials, approvals, and memory. The licence is MIT.

When your agent uses it

  • The operator wants to clone a colleague
  • Build a coworker from someones writing
  • Onboard a digital twin
  • Asks to distill

Example prompts

  • “s writing, onboard a digital twin, or asks to”
  • “mirror”
  • “/human-distill”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Consent first. Distilling a real, named human requires a recorded
  2. Evidence or nothing. Every claim in extraction.json must cite real
  3. Never impersonate. The coworker mirrors the subject's judgment, not
  4. Privacy. Third-party PII is masked at ingest. If you see unmasked

What it can do on your machine

Read from SKILL.md and the folder at commit a65023b. 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

Human Distill loads about 1.9k tokens when it runs, and up to ~4.7k if it reads all its reference files. Until then it costs about 95 tokens; SKILL.md has 813 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.7k

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 HybridAIOne/hybridclaw at commit a65023b, republished under its MIT licence (© HybridAIOne). 813 words, ~1,851 tokens.

Download SKILL.mdSave it as .claude/skills/human-distill/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
human-distill
description
Distill a real person into a hireable coworker agent from their source material — chat exports, emails, meeting transcripts, documents, interviews, and live mirroring. Use when the operator wants to clone a colleague, build a coworker from someone's writing, onboard a digital twin, or asks to 'distill', 'clone', or 'mirror' a person. Consent-gated for real humans.
user-invocable
true

Human Distillation

Turn a person's source material into a working coworker agent: a persona written into the agent identity files (IDENTITY.md, SOUL.md, USER.md, CV.md) and a work-module skill (skills/<alias>-playbook/) that carries their workflows, preferences, and judgment. Every generated claim cites the corpus documents it came from; nothing is invented beyond the source.

The deterministic engine is the hybridclaw coworker CLI from the distill plugin. If hybridclaw coworker prints the general usage instead, the plugin is not installed: ask the operator to run hybridclaw plugin install distill rather than installing it yourself. Your judgment enters the pipeline through exactly one artefact: extraction.json. You never edit the persona files directly — the engine renders them from validated claims so every line stays cited, versioned, and reversible.

Hard rules

  1. Consent first. Distilling a real, named human requires a recorded consent artefact. Never run coworker consent record on your own initiative or invent a consent statement — the operator must provide the statement and run (or explicitly dictate) the command. If a run is blocked, relay the remediation message and stop.
  2. Evidence or nothing. Every claim in extraction.json must cite real corpus document ids from the analysis packet. If you cannot support a claim, leave it out or put the question in openQuestions. The engine flags and drops uncited claims — do not try to route around it.
  3. Never impersonate. The coworker mirrors the subject's judgment, not their identity. Do not sign as the subject or present generated output as written by them.
  4. Privacy. Third-party PII is masked at ingest. If you see unmasked third-party contact details anywhere in generated output, stop and run hybridclaw coworker eval --alias <alias> to surface it.

Pipeline

hybridclaw coworker distill --alias <alias> --name "<display name>" \
  [--role "<role>"] [--match-alias <name|email>]... --source <path> [...]

Stages run in order, each resumable: ingest → analyse → build → merge → correct. The run record lives at runtime/distill/<run-id>/run.json in the coworker's agent workspace, with a human-readable REPORT.md beside it.

  1. Intake. Ask the operator: who is being distilled (display name, role, relationship), which aliases/emails identify their authorship (--match-alias, critical for chat exports), whether they are a real person (default) or fictional (--fictional), and what source material exists.
  2. Consent. For a real person, confirm consent is recorded (hybridclaw coworker consent show --alias <alias>). If not, give the operator the exact consent record command to run and wait.
  3. Ingest + analyse. Run coworker distill with the sources. The engine masks third-party PII, weights quality (authored long-form > chat one-liners), holds out a slice for eval, and writes an analysis packet.
  4. Extract. Read analysis/PACKET.md in the run directory and write analysis/extraction.json following references/extraction-contract.md and the six-dimension model in references/six-dimensions.md.
  5. Merge. Resume the run (coworker distill --alias <alias> --resume <run-id>). The engine validates citations, merges claims, writes the persona files and the work-module skill as versioned edits, and opens review items for any conflict you declared. Report flagged claims and open reviews to the operator verbatim from REPORT.md.
  6. Verify. Run hybridclaw coworker eval --alias <alias>. A leakage failure must be reported and fixed before the coworker is used.
Show full SKILL.md (317 more words)Show less

Intake modalities

Use every channel of evidence the operator can provide; they compound:

ModalityHow
Chat exportsSlack export dirs/JSON, generic chat JSONL — --kind auto detects them
Email.mbox archives
Meetings ("listening")Speaker-labelled transcripts (Name: text lines)
Writing samplesMarkdown / text docs, decision records, posts
Questionnairehybridclaw coworker interview --alias <alias> [--audience subject|colleague] --out <file> generates a gap-driven interview targeting the dimensions with least evidence; the answered file is ingested with --kind interview (highest weight)
MirroringLive draft-compare-diff sessions per references/mirroring.md; differences become corrections

After each merge, check openQuestions and dimension coverage in the packet; offer the operator a fresh interview round for the weakest dimensions.

Incremental updates and corrections

  • New material later: same coworker distill command — only the delta is re-analysed; standing conclusions are never overwritten. Contradictions you declare via conflictsWith become review items the operator resolves with coworker review resolve.
  • When the operator corrects the coworker's behaviour in conversation ("she'd never open with a greeting"), persist it immediately: hybridclaw coworker correct --alias <alias> --note "<correction>". It becomes a maximum-weight corpus document and is promoted into the persona on the next run. Then continue with the corrected behaviour in the current session.

Operating boundaries

  • Green: reading sources/corpus/status/reports, generating questionnaires, writing extraction.json, coworker status|eval|interview|review list.
  • Amber (confirm with the operator first): coworker distill runs and resumes (they write workspace files, reversibly), coworker correct, coworker review resolve, coworker export.
  • Red (never): recording or fabricating consent, coworker forget (operator-only), editing generated persona/skill files by hand, distilling someone the operator has not named.

Container note

If hybridclaw is not on PATH (sandboxed container session), do the file-contract half yourself — read PACKET.md, write extraction.json — and hand the operator the exact distill --resume command to run locally.

Deeper material

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

Files

SKILL.md and 4 other files (references) in skills/human-distill of HybridAIOne/hybridclaw.

  • SKILL.md
  • references/extraction-contract.md
  • references/interview-protocol.md
  • references/mirroring.md
  • references/six-dimensions.md

Open the folder on GitHubat commit a65023b

Compare with similar skills

Human Distill 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.

Human Distill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Human Distill this skillHybridAIOne/hybridclaw159—~1.9kAutomated safety check: PassMIT
Paperclip Distillpaperclipai/paperclip100k—~2.8kAutomated safety check: PassMIT
Setup Coworkasgeirtj/system_prompts_leaks69k—~3kAutomated safety check: PassCC0-1.0
Rules Distillationaffaan-m/ECC277k2 repos~2.3kAutomated safety check: PassMIT
Taste Distillationaffaan-m/ECC277k—~2.3kAutomated safety check: PassMIT
Rules Distillaffaan-m/ECC276k—~1.5kAutomated safety check: PassMIT

Similar skills

  • Paperclip Distill

    paperclipai/paperclip

    A skill your agent uses when an operation issue is a Paperclip cursor-window, distill, or backfill.

    100k GitHub stars~2.8k tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Setup Cowork

    asgeirtj/system_prompts_leaks

    Guided Cowork setup — install a matching plugin, try a skill, connect tools.

    69k GitHub stars~3k tokensUpdated yesterday
    Auto-check passed

  • Rules Distillation

    affaan-m/ECC

    Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.

    277k GitHub starsUsed in 2 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • Taste Distillation

    affaan-m/ECC

    Measure a set of reference videos into a reusable style pack - colour grade as a 3D LUT, cut rhythm as a shot-length distribution, hero stills, screen-blend overlay plates, and a text spec for a…

    277k GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • Rules Distill

    affaan-m/ECC

    スキルをスキャンしてドメイン横断的な原則を抽出し、ルールに蒸留する——既存のルールファイルへの追記、修正、または新規作成

    276k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

  • Rules Distill

    affaan-m/ECC

    扫描技能以提取跨领域原则并将其提炼为规则——追加、修订或创建新的规则文件

    276k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed

More from HybridAIOne/hybridclaw

All 72 skills in this repo

  • Hermes3000 Writing

    HybridAIOne/hybridclaw

    Use Hermes3000 to plan, draft, revise, save, check consistency, and export long-form manuscripts through the Hermes3000 AI writing portal API.

    159 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Manim Video

    HybridAIOne/hybridclaw

    Plan, script, render, and stitch Manim Community Edition videos in Python.

    159 GitHub stars~4.7k tokensUpdated today
    Auto-check: notes

  • Skill Creator

    HybridAIOne/hybridclaw

    Create and update SKILL.md-based skills with strong trigger metadata, lean docs, and reliable init, validate, package, and publish workflows.

    159 GitHub stars~2k tokensUpdated today
    Auto-check passed

  • XLSX

    HybridAIOne/hybridclaw

    Create, edit, inspect, and analyze .xlsx spreadsheets and Excel workbooks.

    159 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Excalidraw

    HybridAIOne/hybridclaw

    Create and revise editable .excalidraw diagrams as Excalidraw JSON for architecture diagrams, flowcharts, sequence diagrams, concept maps, and other hand-drawn explainers.

    159 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Google Ads

    HybridAIOne/hybridclaw

    Manage Google Ads accounts with safe GAQL reporting, campaign planning, guarded mutations, and gateway-proxied REST API calls.

    159 GitHub stars~4k tokensUpdated today
    Auto-check passed

Questions about Human Distill

What does Human Distill do?

Distill a real person into a hireable coworker agent from their source material — chat exports, emails, meeting transcripts, documents, interviews, and live mirroring. Human Distill is an agent skill from HybridAIOne/hybridclaw. Distill a real person into a hireable coworker agent from their source material — chat exports, emails, meeting transcripts, documents, interviews, and live mirroring.

When should I use Human Distill?

Human Distill fits situations like: the operator wants to clone a colleague; build a coworker from someones writing; onboard a digital twin; asks to distill.

How do I install Human Distill in Claude Code?

Run `npx skills add HybridAIOne/hybridclaw --skill human-distill -a claude-code`. Or copy the skill folder (skills/human-distill in HybridAIOne/hybridclaw) into .claude/skills/human-distill in your project. Claude Code loads it when a task matches its description.

How do I install Human Distill in Codex?

Run `npx skills add HybridAIOne/hybridclaw --skill human-distill -a codex`. Or copy the skill folder (skills/human-distill in HybridAIOne/hybridclaw) into .agents/skills/human-distill in your project. Codex loads it when a task matches its description.

Can I use Human Distill 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 HybridAIOne/hybridclaw --skill human-distill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/human-distill, .gemini/skills/human-distill, .github/skills/human-distill and .opencode/skills/human-distill in your project.

What does Human Distill need to run?

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

Does Human Distill 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 Human Distill 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 Human Distill use?

Human Distill 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 Human Distill use?

About 1.9k tokens (SKILL.md is roughly 7.4k 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 2.9k tokens, read only when the agent opens those files.

What are the alternatives to Human Distill?

Skills that share tags, products or a category with Human Distill: Paperclip Distill (paperclipai/paperclip, 100k stars), Setup Cowork (asgeirtj/system_prompts_leaks, 69k stars), Rules Distillation (affaan-m/ECC, 277k stars) and Taste Distillation (affaan-m/ECC, 277k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Human Distill?

HybridAIOne (a GitHub organization) maintains it in HybridAIOne/hybridclaw, which has 159 GitHub stars. The repository holds 72 skills in this directory. The repository was last updated on October 10, 2026.

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