How do I install the Five Hard skill?

Run npx skillmds@latest add tonydzi/five-hard in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Five Hard safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Five Hard?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Five Hard free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Five Hard?

tonydzi (@tonydzi) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Five Hard by tonydzi — Agent Skill

Name: Five Hard
Author: tonydzi

Five Hard

Have the second brain ask the owner five hard questions about their own long-held beliefs and codex entries that have not been revisited, so assumptions stop fossilizing. Monthly or on demand. Triggers: "/five-hard", "challenge my beliefs", "pressure-test my views".

tonydzi 5770cad 3.6 KB Updated Sep 17, 2026

File contents

/five-hard — five hard questions

🧒 When reporting to a non-technical operator, end with a child-simple "In plain words" recap in their language.

Why: the identity layer (belief-* + concept-bible-*, ~24 notes) is "how I think". That gets dangerous once part of it is wrong and nobody has checked. Here the brain itself starts the pressure-test.

Run

python "$IMPORTS_ROOT/five_hard_pick.py" -> the 5 most stagnant notes (oldest mtime) -> $IMPORTS_ROOT/_five_hard_pick.json. Override: env FIVE_HARD_N=7.

The questions (top-model quality — identity synthesis, not grunt work)

Read each note IN FULL and give ONE hard question per note:

N. **[<stem>]** — <the owner's thesis in your own words>
   Question: <sharp, Socratic, capable of forcing a rethink>
   Why it is hard: <which counter-fact or trend could flip it>

Style: Socratic — not "you are wrong" but "what makes you sure today?"; lean on CONCRETE recent signals; epistemic-neutrality; aim at the UNTESTED edge (the "tension / nuance" section), not at the part already reflected on. "The rule still stands" is a valid answer (bible-as-prompt).

Recording the answer (long memory; backup-first: vault_backup.py)

-> $OBSIDIAN_VAULT/04-Coach/_Five-Hard/five-hard-YYYY-MM-DD.md Frontmatter: title, date, type: five-hard, source: claude-session, tags: [five-hard, coach, identity-layer]. Body: the questions + the owner's answers verbatim; if they changed position, propose a diff to the belief/bible note with supersedes: (via /intake). NO 🧒 block inside the note.

Scheduled twin

Cron five-hard-monthly: 1st of the month, 05:25 Lisbon (the briefing window, routines-run-at-night). Picker -> questions (top-model subagent) -> the fleet log chat via python $USERPROFILE/.claude/scripts/bus_ping.py --post "..." (canon: alerts go to the fleet log chat, never to Saved Messages) + "answer by voice or text, I will file it into the vault". The manual twin is this skill; the single source of truth is the picker.

[[self-bible-identity-layer]] · [[bible-as-prompt]] · [[epistemic-neutrality]] · /coach (daily) vs /five-hard (monthly). Active-brain map A-E: item B. ⚠️ Restored 2026-07-04 after the 2026-06-24 migration wipe.

Like this skill? It is one of 100 in second-brain-starter-kit: the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with npx skills add tonydzi/second-brain-starter-kit. Everything is open source and free, so take what you need.

Flagships worth a look on their own: secondop-panel (a second opinion from a panel of external models), claude-memory-tidy (stop your agent's memory from rotting), telegram-mcp-kit (your own Telegram over MCP in about 15 minutes).

Author: Anton Dziatkovskii, Palo Alto AI Research Lab. Telegram @tonydzi - WhatsApp +1 341 222 9178 - X @Tony_Stef_

Engineers: want to test-drive this setup? Message me. I hand out free starter seeds to engineers who test and report back, and custom skill requests are welcome.

---name: five-harddescription: Have the second brain ask the owner five hard questions about their own long-held beliefs and codex entries that have not been revisited, so assumptions stop fossilizing. Monthly or on demand. Triggers: "/five-hard", "challenge my beliefs", "pressure-test my views".license: MIT---# /five-hard — five hard questions> 🧒 When reporting to a non-technical operator, end with a child-simple "In plain words" recap in their language.**Why:** the identity layer (`belief-*` + `concept-bible-*`, ~24 notes) is "how I think".That gets dangerous once part of it is wrong and nobody has checked. Here the brain itself starts the pressure-test.## Run`python "$IMPORTS_ROOT/five_hard_pick.py"` -> the 5 most stagnant notes (oldest mtime)-> `$IMPORTS_ROOT/_five_hard_pick.json`. Override: env `FIVE_HARD_N=7`.## The questions (top-model quality — identity synthesis, not grunt work)Read each note IN FULL and give ONE hard question per note:```N. **[<stem>]** — <the owner's thesis in your own words> Question: <sharp, Socratic, capable of forcing a rethink> Why it is hard: <which counter-fact or trend could flip it>```Style: Socratic — not "you are wrong" but "what makes you sure today?"; lean on CONCRETE recentsignals; `epistemic-neutrality`; aim at the UNTESTED edge (the "tension / nuance" section),not at the part already reflected on. "The rule still stands" is a valid answer (`bible-as-prompt`).## Recording the answer (long memory; backup-first: vault_backup.py)-> `$OBSIDIAN_VAULT/04-Coach/_Five-Hard/five-hard-YYYY-MM-DD.md`Frontmatter: title, date, `type: five-hard`, `source: claude-session`,`tags: [five-hard, coach, identity-layer]`. Body: the questions + the owner's answers verbatim;if they changed position, propose a diff to the belief/bible note with `supersedes:` (via `/intake`). NO 🧒 block inside the note.## Scheduled twinCron `five-hard-monthly`: 1st of the month, 05:25 Lisbon (the briefing window, `routines-run-at-night`).Picker -> questions (top-model subagent) -> **the fleet log chat** via `python $USERPROFILE/.claude/scripts/bus_ping.py --post "..."`(canon: alerts go to the fleet log chat, never to Saved Messages) + "answer by voice or text, I will file it into the vault".The manual twin is this skill; the single source of truth is the picker.## Related[[self-bible-identity-layer]] · [[bible-as-prompt]] · [[epistemic-neutrality]] · /coach (daily) vs/five-hard (monthly). Active-brain map A-E: item B. ⚠️ Restored 2026-07-04 after the 2026-06-24 migration wipe.------**Like this skill?** It is one of 100 in [second-brain-starter-kit](https://github.com/tonydzi/second-brain-starter-kit): the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with `npx skills add tonydzi/second-brain-starter-kit`. Everything is open source and free, so take what you need.Flagships worth a look on their own: [secondop-panel](https://github.com/tonydzi/secondop-panel) (a second opinion from a panel of external models), [claude-memory-tidy](https://github.com/tonydzi/claude-memory-tidy) (stop your agent's memory from rotting), [telegram-mcp-kit](https://github.com/tonydzi/telegram-mcp-kit) (your own Telegram over MCP in about 15 minutes).Author: **Anton Dziatkovskii**, Palo Alto AI Research Lab. Telegram [@tonydzi](https://t.me/tonydzi) - WhatsApp [+1 341 222 9178](https://wa.me/13412229178) - X [@Tony_Stef_](https://x.com/Tony_Stef_)**Engineers: want to test-drive this setup?** Message me. I hand out free starter seeds to engineers who test and report back, and custom skill requests are welcome.

Frequently asked questions