human-distill
Distill a real person into a hireable coworker agent from their source material — chat exports, emails, meeting transcripts, documents, interviews, and live…
Skill by HybridAIOne
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hybridaione-human-distill
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/human-distill
What's inside
- Skill 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.
- License
- MIT
- Instructions
- 124 lines in SKILL.md · view on GitHub
Files (5)
- SKILL.md
- extraction-contract.md · references/
- interview-protocol.md · references/
- mirroring.md · references/
- six-dimensions.md · references/
SKILL.md (first lines)
# 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](references/extraction-contract.md)
and the six-dimension model in
[references/six-dimensions.md](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.
## Intake modalities
Use every channel of evidence the operator can provide; they compound:
| Modality | How |
|---|---|
| Chat exports | Slack export dirs/JSON, generic chat JSONL — `--kind auto` detects them |
| Email | `.mbox` archives |
| Meetings ("listening") | Speaker-labelled transcripts (`Name: text` lines) |
| Writing samples | Markdown / text docs, decision records, posts |
| Questionnaire | `hybridclaw 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) |
| Mirroring | Live draft-compare-diff sessions per [references/mirroring.md](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
- [references/six-dimensions.md](references/six-dimensions.md) — the persona model and what evidence each dimension needsFrom HybridAIOne/hybridclaw, MIT.
More from HybridAIOne/hybridclaw
- 0.720score
langfuse
HybridAIOne
Use Langfuse for LLM observability and evaluation and look up Langfuse documentation.
SkillAFreshness: A★ 159Claude Code +9 - 0.720score
datalion
HybridAIOne
Use for DataLion workflows such as listing, reading, creating, or editing projects, inspecting data sources, importing Excel or CSV data, working with reports…
SkillAFreshness: A★ 159Claude Code +9 - 0.720score
manim-video
HybridAIOne
Plan, script, render, and stitch Manim Community Edition videos in Python.
SkillAFreshness: A★ 159Claude Code +9 - 0.720score
hermes3000-writing
HybridAIOne
Use Hermes3000 to plan, draft, revise, save, check consistency, and export long-form manuscripts through the Hermes3000 AI writing portal API.
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
meme-generation
HybridAIOne
Generate meme images from curated classic templates, dynamic imgflip templates, or a custom image.
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
ga4
HybridAIOne
Run production Google Analytics 4 Data API reports with gateway-injected bearer auth, safe request review, traffic source, landing-page, time-series, revenue…
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
excalidraw
HybridAIOne
Create and revise editable `.excalidraw` diagrams as Excalidraw JSON for architecture diagrams, flowcharts, sequence diagrams, concept maps, and other…
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
agentic-tpm
HybridAIOne
Coordinate cross-functional project delivery by tracking commitments, dependencies, decisions, and risks; maintain project context and prepare bounded…
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
distil-pii-redactor
HybridAIOne
Redact, anonymize, sanitize, or remove PII locally with Distil-PII and llama.cpp; keep personal data and secret values out of model context, logs, and chat.
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
diagram
HybridAIOne
Create, validate, update, and render diagram-as-code artifacts with Mermaid-first schema awareness plus PlantUML, Graphviz DOT, and Excalidraw JSON adapters.
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
google-ads
HybridAIOne
Manage Google Ads accounts with safe GAQL reporting, campaign planning, guarded mutations, and gateway-proxied REST API calls.
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
hetzner-cloud
HybridAIOne
Read and operate Hetzner Cloud servers, server types, locations, networks, volumes, snapshots, and cost estimates through gateway-proxied API requests.
SkillAFreshness: A★ 159Claude Code +9
Signals
- Stars
- 159
- Forks
- 17
- Open issues
- 323
- Last commit (this folder)
- Oct 8, 2026 (19 days ago)
- Last release
- Oct 24, 2026 (3 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/HybridAIOne/hybridclaw
- Website
- www.hybridclaw.io/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from HybridAIOne
- 0.720score
datalion
HybridAIOne
Use for DataLion workflows such as listing, reading, creating, or editing projects, inspecting data sources, importing Excel or CSV data, working with reports…
SkillAFreshness: A★ 159Claude Code +9 - 0.720score
hermes3000-writing
HybridAIOne
Use Hermes3000 to plan, draft, revise, save, check consistency, and export long-form manuscripts through the Hermes3000 AI writing portal API.
SkillAFreshness: A★ 159Claude Code +9 - 0.720score
langfuse
HybridAIOne
Use Langfuse for LLM observability and evaluation and look up Langfuse documentation.
SkillAFreshness: A★ 159Claude Code +9 - 0.720score
manim-video
HybridAIOne
Plan, script, render, and stitch Manim Community Edition videos in Python.
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
meme-generation
HybridAIOne
Generate meme images from curated classic templates, dynamic imgflip templates, or a custom image.
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
agentic-tpm
HybridAIOne
Coordinate cross-functional project delivery by tracking commitments, dependencies, decisions, and risks; maintain project context and prepare bounded…
SkillAFreshness: A★ 159Claude Code +9
Cite this page
human-distill skill. Agent Mart. https://agentmart.dev/skills/hybridaione-human-distill (last updated 2026-10-24)