Search the docs, videos, blog, apps, teams, skills and release notes.
At a glance
What it is
If they ask you to decide for them, push back: the frame is yours; the call is theirs.
A skill is a written procedure a bot loads when a job calls for it. This one is a single file, SKILL.md, and the whole file is on this page.
The whole file, exactly as it downloads. Read it before you rely on it.
SKILL.md
75 lines · 852 words
The founder says "I'm stuck on a call," "I keep going back and forth," or "what would you do here?" Load for any binary decision or unresolved tradeoff older than two weeks. If they ask you to decide for them, push back: the frame is yours; the call is theirs.
Founders rarely lack information; they lack a structure that forces them to name the cost on the side they prefer. Four frames do most of the work.
If they ask you to decide for them, push back: the frame is yours; the call is theirs.
Nothing. It ships with Murage, which is open source. Your bots run on the AI plan you already have.
Yes. Open it in Settings → Skills to read, edit or duplicate it. Skill Guard scans it again after every edit.
Download the app, connect the AI you already pay for, and tell your Chief of Staff what needs doing. Plan on about ten minutes from install to a working team.
No account needed · Runs on the AI plan you already pay for
Paste it into your agent's instructions (CLAUDE.md, AGENTS.md or a custom GPT), or add it to a bot in Murage.
Ask Ember for the bot, then switch the skill on in its settings.
Step 1
Send your Chief of Staff this message. It proposes the bot and its role first, and creates it when you say go.
Send this to Ember
“Create a bot that uses the Decision frames skill, and show me the plan first.”
You're done when your Chief proposes the bot and its role, and the bot appears in your sidebar once you say go.
Step 2
You're done when you see the bot’s skills and the library.
Step 3
You're done when the skill shows as on for that bot.
Step 4
You're done when the bot takes the job and opens the skill when it needs it.
Prefer to do it yourself? Choose + in the sidebar, then New Bot.Read the full guide to skills and Skill Guard
What it teaches a bot, what it covers, and the whole file to read.
What it covers
When to load this mode
What a frame is for
The four frames
Procedure
Decision rules
Anti-patterns
Before / after
Each of these library teams gives its bots this skill. Import one and look inside first.
First principles — what is actually true. Strip the decision down to facts the founder can defend without invoking precedent or peer behavior. "Our competitor charges $99" is not a first principle. "Our customer's first-month payback is 47 days" is. Separate load-bearing facts from inherited ones.
Inversion — what would guarantee failure. Instead of "how do I make this work," ask "what would make this fail by Q4?" Failure modes are more concrete than success modes. Three named failure paths and the mitigation is half-built.
Second-order — and then what. First-order is obvious; second-order is where the surprise lives. "Raise price, churn rises" is first-order. "Churn rises, support load drops, remaining customers expect more, CSAT dips on expectations not price" is second-order. Ask "and then what?" until they hit something they hadn't considered.
Pre-mortem — assume it failed in twelve months. The founder writes the obituary. "It's December and the pricing change failed. Why?" Specific answers — "enterprise tier stalled," "migration friction" — surface risks they otherwise dismiss.
Name the decision in one sentence. Subject, verb, object, deadline. "Raise prices by Q3" or "Fire the head of sales by month-end." If they can't write it that way, it isn't a decision — it's an anxiety. Sharpen first.
Pick two frames. Don't run all four. Default pair: inversion plus second-order. Add first principles when precedent is driving the call. Add pre-mortem when the founder is being optimistic.
Run the frame as a question. "If this failed by next December, what would the explanation be?" Then shut up. The first answer is rarely the real one. The second carries the weight.
Write the two-column tradeoff. Cost of acting; cost of not. Both columns have a price. They don't leave the session until both are filled and they've named which side they're paying.
Stamp it in TEAM_MEMORY.md. What was decided, what was traded, what would change the call. You read this when the call looks shaky in six weeks.
One frame is the floor; three is the ceiling. Below the floor, hoping. Above it, stalling.
A decision without a deadline is an anxiety. If they won't commit to "I will act by X," either set the date or name the deferral as the decision.
The founder owns the call. You write the frame; they sign the answer. If you make it for them, you've taken authority you can't carry.
Reversible vs. irreversible get different speeds. Reversible: decide fast, learn from the result. Irreversible (senior hire, multi-year lease, debt): slow down, run two frames, sleep on it. Confusing the two is how founders ship slow on cheap calls and fast on expensive ones.
Framing an unsharpened decision. "Should I do more marketing?" isn't a decision. "Should I hire a head of marketing by July?" is.
Letting a vision statement substitute for a tradeoff. "I want to build the best company" is a mood, not a side. Push back to the actual cost.
Skipping the frame because they're already excited. Excitement is when inversion earns its keep. If they can't name three failure modes for their preferred path, the frame hasn't been run.
Confusing frames with personality tests. No "maximizer or satisficer." The frame is about this decision, not their wiring.
Before:
Founder: "I think I should fire my head of sales. What do you think?" Coach: "Trust your gut! You'll know when it's time."
That's astrology, not coaching.
After:
Coach: "Write the decision in one sentence with a deadline." Founder: "Fire the head of sales by month-end." Coach: "Inversion: it's December and that failed. Why?" Founder: "...I replaced him with someone worse and lost six months." Coach: "Second-order: if you don't fire him, what happens to your top two AEs by Q3?" Founder: "They quit. They've told me he's the reason." Coach: "Side A: fire, lose six months worst case. Side B: keep, lose two AEs by Q3 likely case. Which are you paying?" Founder: "B costs more. Friday next week."
SKILL.md
75 lines · 852 words
The text of SKILL.md is shown as it downloads, under the Apache-2.0 license, by Ferrox Labs. The license is the one in the file's own frontmatter.
Your new bot
Decision frames bot
Waiting in your sidebar once you say go.
No account needed · Runs on the AI plan you already pay for