High Token Mode
Lomnus-ai/TokenBurner
Forces heavy internal computation (thinking tokens) before each response.
Agent skill
by harryvondiesel-web in harryvondiesel-web/5-persona-advisory-board
Run a 5 Persona Advisory Board review, board review, strategic decision stress-test, offer critique, risk check, or pricing/timing/positioning decision review.
$ npx skills add harryvondiesel-web/5-persona-advisory-board --skill 5-persona-advisory-board -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install harryvondiesel-web/5-persona-advisory-board 5-persona-advisory-board --agent claude-codeProject 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/
Install the "5-persona-advisory-board" agent skill from https://github.com/harryvondiesel-web/5-persona-advisory-board/tree/main into .claude/skills/5-persona-advisory-board/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "5-persona-advisory-board", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add harryvondiesel-web/5-persona-advisory-board --skill 5-persona-advisory-board -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install harryvondiesel-web/5-persona-advisory-board 5-persona-advisory-board --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "5-persona-advisory-board" agent skill from https://github.com/harryvondiesel-web/5-persona-advisory-board/tree/main into .agents/skills/5-persona-advisory-board/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "5-persona-advisory-board", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add harryvondiesel-web/5-persona-advisory-board --skill 5-persona-advisory-board -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install harryvondiesel-web/5-persona-advisory-board 5-persona-advisory-board --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "5-persona-advisory-board" agent skill from https://github.com/harryvondiesel-web/5-persona-advisory-board/tree/main into .cursor/skills/5-persona-advisory-board/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "5-persona-advisory-board", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add harryvondiesel-web/5-persona-advisory-board --skill 5-persona-advisory-board -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install harryvondiesel-web/5-persona-advisory-board 5-persona-advisory-board --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "5-persona-advisory-board" agent skill from https://github.com/harryvondiesel-web/5-persona-advisory-board/tree/main into .gemini/skills/5-persona-advisory-board/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "5-persona-advisory-board", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install harryvondiesel-web/5-persona-advisory-board 5-persona-advisory-boardInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add harryvondiesel-web/5-persona-advisory-board --skill 5-persona-advisory-board -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "5-persona-advisory-board" agent skill from https://github.com/harryvondiesel-web/5-persona-advisory-board/tree/main into .github/skills/5-persona-advisory-board/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "5-persona-advisory-board", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add harryvondiesel-web/5-persona-advisory-board --skill 5-persona-advisory-board -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install harryvondiesel-web/5-persona-advisory-board 5-persona-advisory-board --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "5-persona-advisory-board" agent skill from https://github.com/harryvondiesel-web/5-persona-advisory-board/tree/main into .opencode/skills/5-persona-advisory-board/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "5-persona-advisory-board", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
5-persona-advisory-boardRun a 5 Persona Advisory Board review, board review, strategic decision stress-test, offer critique, risk check, or pricing/timing/positioning decision review.
5 Persona Advisory Board is an agent skill from harryvondiesel-web/5-persona-advisory-board. Run a 5 Persona Advisory Board review, board review, strategic decision stress-test, offer critique, risk check, or pricing/timing/positioning decision review.
Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 20 other files, including assets (for example `.github/ISSUE_TEMPLATE/bug_report.md`, `.github/ISSUE_TEMPLATE/compatibility_report.md` and `.github/ISSUE_TEMPLATE/feature_request.md`).
It sits in Testing & QA, covering Load testing and Positioning and messaging. The repository describes itself as: A reusable AI skill for stress-testing high-leverage decisions through five strategic lenses. The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit ed1216c. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
5 Persona Advisory Board loads about 2.8k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 1,622 words of instructions outside code blocks.
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.
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.
The full file from harryvondiesel-web/5-persona-advisory-board at commit ed1216c, republished under its MIT licence (© harryvondiesel-web). 1,622 words, ~2,831 tokens.
.claude/skills/5-persona-advisory-board/SKILL.md (or your agent's skills folder). This skill also uses 15 other files; get the full folder from GitHub.Interview first. Stress-test with five strategic lenses. Decide with clarity.
Version: 0.2.1 License: MIT
Use this skill when the user wants to stress-test an important decision before acting.
The 5 Persona Advisory Board is not celebrity roleplay and does not impersonate real people. It is a structured decision process that uses five interpretive strategic lenses to expose blind spots, disagreement, assumptions, risks, and one practical next action.
This skill is for the 20% decisions that drive 80% of the outcome: strategy, risk, offers, product, growth, timing, positioning, and long-term direction.
Use it when the decision is important enough that a shallow answer would be dangerous. Do not use it for ordinary lookup, basic summarization, or simple task execution.
CRIT = Context, Role, Interview, Task.
Do not give final advice too early. First collect enough context to make the board useful.
When the user asks for:
route into CRIT first.
If context is missing, ask 1-3 focused interview questions before running the board. Do not run the five lenses or final decision brief until the interview is answered, unless the user explicitly asks to skip the interview. If the user skips, state assumptions clearly before giving advice.
If the environment cannot ask follow-up questions, such as a headless run, scheduled task, or non-interactive API pipeline, state the missing context and assumptions explicitly, then run the board.
When the user gives a decision with enough context, briefly summarize the CRIT context and then run the board. Do not ask filler questions just to follow the format.
Use these five lenses by default unless the user changes them.
Focus: simplicity, focus, product clarity, taste, story, and memorability.
Key question:
Is this clear, focused, and worth building?
Boundaries:
Focus: long-term value, incentives, risk, durability, capital discipline, and margin of safety.
Key question:
Is this durable, rational, and worth the risk?
Boundaries:
Focus: customer obsession, scale, systems, experimentation, mechanisms, and operating leverage.
Key question:
Does this create long-term customer value and scale?
Boundaries:
Focus: offer strength, value, demand, pricing, execution, and sales friction.
Key question:
Is the offer strong enough to win now?
Boundaries:
Focus: long-term alignment, personal values, likely regrets, freedom, identity, and the person the user wants to become.
Key question:
Will I be proud I made this decision?
Boundaries:
Before running the board, gather or summarize:
If this information is missing, interview the user first.
Ask up to three questions. Choose only the most important ones.
Useful questions:
Use this format:
One sentence.
Brief summary of the situation, facts, stage, and assumptions.
For each lens, label the view clearly:
Where the lenses agree, where they disagree, and what each lens may be over-weighting.
The likely long-term alignment issue or regret risk.
This project is not affiliated with, endorsed by, or connected to Steve Jobs' estate, Warren Buffett, Jeff Bezos, Alex Hormozi, or any related company. The advisor personas are interpretive reasoning frameworks inspired by publicly available principles and ideas.
Use the 5 Persona Advisory Board.
Decision: [decision]
Context: [context]
Current plan: [plan]
Evidence: [evidence]
Constraints: [constraints]
Time horizon: [time horizon]
If context is missing, interview me first using CRIT. Then run the Product Clarity, Risk and Capital, Scale and Systems, Offer Strength, and Future Self lenses. Force disagreement, then give the final decision brief and next action.
Start with one fixed-price audit package or keep writing custom proposals for every client.
The founder has limited time, no sales team, and needs cash quickly. Custom proposals create unpaid scoping and slow sales cycles. A fixed audit could make the offer easier to buy, but delivery scope and pricing risk are still unproven.
Product Clarity Lens:
Risk and Capital Lens:
Scale and Systems Lens:
Offer Strength Lens:
Future Self Lens:
The lenses mostly agree on audit-first. The disagreement is scope and pricing discipline: Offer Strength wants a clean, easy yes; Risk and Capital warns that fixed price is dangerous without protected scope; Scale and Systems warns that the package only works if delivery is truly repeatable.
The bigger regret is probably not "I started too simple." The bigger regret is building a custom-only practice where every sale creates a new job.
© harryvondiesel-web, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 15 other files (assets) in the repository root of harryvondiesel-web/5-persona-advisory-board.
Open the folder on GitHubat commit ed1216c
5 Persona Advisory Board 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| 5 Persona Advisory Board this skillharryvondiesel-web/5-persona-advisory-board | 133 | — | ~2.8k | Automated safety check: Pass | MIT | |
| High Token ModeLomnus-ai/TokenBurner | 173 | — | ~9.1k | Automated safety check: Pass | MIT | |
| Benchmark Reportagentic-community/mcp-gateway-registry | 968 | — | ~590 | Automated safety check: Pass | Apache-2.0 | |
| Review The WorkAIDevGTM/gtm-cofounder | 310 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Writing Livekit Scenarioslivekit-examples/agent-starter-python | 264 | 1 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Go Testingcxuu/golang-skills | 173 | 1 repos | ~1.3k | Automated safety check: Pass | Apache-2.0 |
Lomnus-ai/TokenBurner
Forces heavy internal computation (thinking tokens) before each response.
agentic-community/mcp-gateway-registry
Generate a benchmark report from stress test results (registration, API performance, search concurrency).
AIDevGTM/gtm-cofounder
Before showing the user any substantive GTM deliverable (positioning, value prop, homepage, launch post, pricing, sales script, the brief or roadmap), stress-test it against the standard as an…
livekit-examples/agent-starter-python
Creates and maintains the scenarios a LiveKit agent simulation runs, and wires the agent to consume them.
cxuu/golang-skills
A skill your agent uses when writing, reviewing, or improving Go test code — including table-driven tests, subtests, parallel tests, test helpers, test doubles, and assertions with cmp.Diff.
grp06/goalcraft
Turn a rough draft, vague ambition, or messy task brief into a powerful Codex /goal objective for persistent, evidence-checked work.
Run a 5 Persona Advisory Board review, board review, strategic decision stress-test, offer critique, risk check, or pricing/timing/positioning decision review. 5 Persona Advisory Board is an agent skill from harryvondiesel-web/5-persona-advisory-board. Run a 5 Persona Advisory Board review, board review, strategic decision stress-test, offer critique, risk check, or pricing/timing/positioning decision review.
5 Persona Advisory Board fits situations like: tasks that involve Load testing; tasks that involve Positioning and messaging.
Run `npx skills add harryvondiesel-web/5-persona-advisory-board --skill 5-persona-advisory-board -a claude-code`. Or copy the skill folder (the harryvondiesel-web/5-persona-advisory-board repository) into .claude/skills/5-persona-advisory-board in your project. Claude Code loads it when a task matches its description.
Run `npx skills add harryvondiesel-web/5-persona-advisory-board --skill 5-persona-advisory-board -a codex`. Or copy the skill folder (the harryvondiesel-web/5-persona-advisory-board repository) into .agents/skills/5-persona-advisory-board in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add harryvondiesel-web/5-persona-advisory-board --skill 5-persona-advisory-board -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/5-persona-advisory-board, .gemini/skills/5-persona-advisory-board, .github/skills/5-persona-advisory-board and .opencode/skills/5-persona-advisory-board in your project.
SKILL.md names no scripts, command-line tools or credentials: 5 Persona Advisory Board is instructions for the agent only.
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.
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.
5 Persona Advisory Board is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with 5 Persona Advisory Board: High Token Mode (Lomnus-ai/TokenBurner, 173 stars), Benchmark Report (agentic-community/mcp-gateway-registry, 968 stars), Review The Work (AIDevGTM/gtm-cofounder, 310 stars) and Writing Livekit Scenarios (livekit-examples/agent-starter-python, 264 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
harryvondiesel-web (a GitHub user) maintains it in harryvondiesel-web/5-persona-advisory-board, which has 133 GitHub stars. The repository was last updated on October 7, 2026.
Source: harryvondiesel-web/5-persona-advisory-board on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.