anyone-skill

Name: anyone-skill
Author: acnlabs

40stars5forks

How to install anyone-skill?

acnlabs/openpersona/anyone-skill

$npx -y skills add acnlabs/OpenPersona --skill anyone-skill

Installs into the current project.

Summary

Distill anyone into a runnable OpenPersona skill pack — real or fictional, personal or public, living or historical. Collects chat logs, documents, and public content, extracts a 4-dimension persona, and generates a portable OpenPersona pack via skills/open-persona. Use when aske

Files · 1

View on GitHub

SKILL.md

1	# anyone.skill — Distill Anyone
2
3	> Every person is a unique decision system, an irreplicable voice, a finite set of memories.
4	> anyone-skill distills that uniqueness into a portable, evolvable OpenPersona skill pack.
5
6	anyone-skill is a distillation front-end for OpenPersona. It handles data collection, 4-dimension extraction, and evidence grading. The final output is a full OpenPersona persona pack generated via `skills/open-persona`.
7
8	Dependency chain: `anyone-skill` → `skills/open-persona` → `openpersona create`
9	Extended chain (local model): `anyone-skill` → `persona-knowledge` → `persona-model-trainer` → runnable persona model
10
11	Optional integration: When `persona-knowledge` is installed (`skills/persona-knowledge/`), anyone-skill uses it for persistent storage, semantic search, and Knowledge Graph instead of writing directly to `training/raw/`. Detection:
12
13	```bash
14	# Check at start of Phase 3 — if this directory exists, use persona-knowledge integration
15	ls skills/persona-knowledge/SKILL.md 2>/dev/null && echo "persona-knowledge detected"
16	```
17
18	When detected, data flow becomes: `source → persona-knowledge ingest → MemPalace + KG + wiki → persona-knowledge export → training/`
19
20	## Trigger phrases
21
22	- `/create-anyone`
23	- "distill X into a skill"
24	- "create a persona for X"
25	- "make a skill pack for X"
26	- "I want to talk to X as an AI"
27	- "clone X's personality"
28
29	To evolve an existing persona:
30
31	- "I have more data" / "add this to X"
32	- "that's not right" / "X wouldn't say that"
33	- `/update-anyone {slug}`
34
35	---
36
37	## Tools
38
39
40	\| Task \| Tool \|
41	\| -------------------------------------------- \| -------------------------------------------------------------------------------------- \|
42	\| Read any text / JSON / CSV / PDF / image \| `Read` (native — use for most chat exports) \|
43	\| Search public figures / fictional characters \| `WebSearch` \|
44	\| Extract SQLite databases (iMessage / WeChat) \| `Bash` → `python3 ${CLAUDE_SKILL_DIR}/scripts/preprocess.py --input <file.db>` \|
45	\| Sample oversized files (>5000 messages) \| `Bash` → `python3 ${CLAUDE_SKILL_DIR}/scripts/preprocess.py --input <file> --max 3000` \|
46	\| Write / update files \| `Write` / `Edit` \|
47	\| Version management \| `Bash` → `python3 ${CLAUDE_SKILL_DIR}/scripts/version_manager.py` \|
48	\| List existing personas \| `Bash` → `python3 ${CLAUDE_SKILL_DIR}/scripts/skill_writer.py --action list` \|
49
50
51	> Reading strategy: use `Read` directly for all text-based exports — WhatsApp `_chat.txt`, Telegram `result.json`, Slack/Discord JSON, email `.eml`, Twitter/X archive, Feishu/DingTalk export, plain text, CSV. The agent understands any readable format natively; no parser needed.
52	> Use `preprocess.py` only for: (1) binary SQLite `.db` files, (2) files too large to fit in context (auto-samples down to `--max`).
53
54	---
55
56	## Phase 0: Classify the Subject
57
58	Determine which category the subject falls into — different categories use different data strategies and ethical rules:
59
60	```
61	Who do you want to distill?
62
63	[1] Yourself — full digital self
64	[2] Someone you know — colleague, friend, family, partner, ex
65	[3] Public figure — entrepreneur, artist, athlete, politician
66	[4] Fictional character — game, anime, novel, film, series
67	[5] Historical figure — relies on documents, biographies, speeches
68	[6] Archetype — composite persona, no single real subject
69	```
70
71	---
72
73	## Phase 1: Ethics & Copyright Check
74
75	> Full rules: [references/ethics.md](references/ethics.md). Key points by category:
76
77	Someone you know — confirm personal use only; no harassment, impersonation, or deception; all data stored locally.
78
79	Public figure — use only publicly traceable sources; generated skill must include disclaimer on first run: "Based on public information. Not the real person. For reference only."
80
81	Fictional character
82
83	- Personal local use → no restrictions, direct roleplay mode
84	- Distributing to others → act

People who liked this also viewed

6 picks

Type

anyone-skill

40stars5forks

View on GitHub

How to install anyone-skill?

acnlabs/openpersona/anyone-skill

$npx -y skills add acnlabs/OpenPersona --skill anyone-skill

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# anyone.skill — Distill Anyone
2
3	> Every person is a unique decision system, an irreplicable voice, a finite set of memories.
4	> anyone-skill distills that uniqueness into a portable, evolvable OpenPersona skill pack.
5
6	anyone-skill is a distillation front-end for OpenPersona. It handles data collection, 4-dimension extraction, and evidence grading. The final output is a full OpenPersona persona pack generated via `skills/open-persona`.
7
8	Dependency chain: `anyone-skill` → `skills/open-persona` → `openpersona create`
9	Extended chain (local model): `anyone-skill` → `persona-knowledge` → `persona-model-trainer` → runnable persona model
10
11	Optional integration: When `persona-knowledge` is installed (`skills/persona-knowledge/`), anyone-skill uses it for persistent storage, semantic search, and Knowledge Graph instead of writing directly to `training/raw/`. Detection:
12
13	```bash
14	# Check at start of Phase 3 — if this directory exists, use persona-knowledge integration
15	ls skills/persona-knowledge/SKILL.md 2>/dev/null && echo "persona-knowledge detected"
16	```
17
18	When detected, data flow becomes: `source → persona-knowledge ingest → MemPalace + KG + wiki → persona-knowledge export → training/`
19
20	## Trigger phrases
21
22	- `/create-anyone`
23	- "distill X into a skill"
24	- "create a persona for X"
25	- "make a skill pack for X"
26	- "I want to talk to X as an AI"
27	- "clone X's personality"
28
29	To evolve an existing persona:
30
31	- "I have more data" / "add this to X"
32	- "that's not right" / "X wouldn't say that"
33	- `/update-anyone {slug}`
34
35	---
36
37	## Tools
38
39
40	\| Task \| Tool \|
41	\| -------------------------------------------- \| -------------------------------------------------------------------------------------- \|
42	\| Read any text / JSON / CSV / PDF / image \| `Read` (native — use for most chat exports) \|
43	\| Search public figures / fictional characters \| `WebSearch` \|
44	\| Extract SQLite databases (iMessage / WeChat) \| `Bash` → `python3 ${CLAUDE_SKILL_DIR}/scripts/preprocess.py --input <file.db>` \|
45	\| Sample oversized files (>5000 messages) \| `Bash` → `python3 ${CLAUDE_SKILL_DIR}/scripts/preprocess.py --input <file> --max 3000` \|
46	\| Write / update files \| `Write` / `Edit` \|
47	\| Version management \| `Bash` → `python3 ${CLAUDE_SKILL_DIR}/scripts/version_manager.py` \|
48	\| List existing personas \| `Bash` → `python3 ${CLAUDE_SKILL_DIR}/scripts/skill_writer.py --action list` \|
49
50
51	> Reading strategy: use `Read` directly for all text-based exports — WhatsApp `_chat.txt`, Telegram `result.json`, Slack/Discord JSON, email `.eml`, Twitter/X archive, Feishu/DingTalk export, plain text, CSV. The agent understands any readable format natively; no parser needed.
52	> Use `preprocess.py` only for: (1) binary SQLite `.db` files, (2) files too large to fit in context (auto-samples down to `--max`).
53
54	---
55
56	## Phase 0: Classify the Subject
57
58	Determine which category the subject falls into — different categories use different data strategies and ethical rules:
59
60	```
61	Who do you want to distill?
62
63	[1] Yourself — full digital self
64	[2] Someone you know — colleague, friend, family, partner, ex
65	[3] Public figure — entrepreneur, artist, athlete, politician
66	[4] Fictional character — game, anime, novel, film, series
67	[5] Historical figure — relies on documents, biographies, speeches
68	[6] Archetype — composite persona, no single real subject
69	```
70
71	---
72
73	## Phase 1: Ethics & Copyright Check
74
75	> Full rules: [references/ethics.md](references/ethics.md). Key points by category:
76
77	Someone you know — confirm personal use only; no harassment, impersonation, or deception; all data stored locally.
78
79	Public figure — use only publicly traceable sources; generated skill must include disclaimer on first run: "Based on public information. Not the real person. For reference only."
80
81	Fictional character
82
83	- Personal local use → no restrictions, direct roleplay mode
84	- Distributing to others → act

People who liked this also viewed

6 picks

Type