be-ambitious
Skill657 starsChanged 27 days agoMITView on GitHub
Turn a task or prompt into a deeper version of itself, not a bigger one. Before rewriting, say what a top professional in the field would do that the user isn't asking for, the rawest source material they would start from, the specific methods and tools they would use, and what (other than the user or the model) would show the result is right. Then rewrite the prompt to ask for exactly that. USE WHEN: /be-ambitious, "be ambitious", "make this prompt deeper", "what would an expert do here", "raise the bar on this task", "rewrite my prompt like a pro would ask it". NOT FOR: expanding scope, adding features, or general prompt polishing for tone or length.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- sandover/agent-skillstheir own version, first seen Nov 8, 2026
- cill-i-am/skillsword for word, first seen Nov 1, 2026
- pengelbrecht/skillsword for word, first seen Nov 1, 2026
- ganeshiyer316/claude-skillstheir own version, first seen Oct 25, 2026
- robonuggets/be-ambitioustheir own version, first seen Oct 20, 2026
Other versions5 projects use a version of this.
Word for word · 2
- cill-i-am/skills★ 1100% same
- pengelbrecht/skills★ 1100% same
Edited · 0
None found.
Wrote their own version · 3
- robonuggets/be-ambitious★ 72same name
- sandover/agent-skills★ 4same name
- ganeshiyer316/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- codex-dynamic-workflowsSkill
- codex-relaySkill
- explain-thisSkill
- modsmithSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 34
Keep the user's goal and scope.
- Distinctive: line 61
If you don't know something in the field well enough to answer, say so rather than inventing a source or tool.
- Distinctive: line 71
Stop after the rewrite. Offer in one line to run it now.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Be ambitious
Adapted from a prompt shared by Felix Rieseberg (Anthropic):
I want a deeper version of this task, not a bigger one. Before rewriting it: (1) say what a top professional in this field would do here that I'm not asking for; (2) name the rawest material they would start from instead of what has already been digested for me; (3) name the specific methods and tools they would use; (4) say what, other than you or me, would show the result is right. Then rewrite my prompt to ask for exactly that.
Input
The task is whatever follows /be-ambitious. If nothing follows, use the
user's most recent request in this conversation. If there is none, ask for the
task in one line and stop.
Deeper, not bigger
Keep the user's goal and scope. Depth means a higher standard for the same outcome: better sources, sharper methods, real verification. Do not add deliverables, features, or side quests. If a suggestion would make the job larger rather than better, drop it.
Steps
Name the field first (e.g. "investigative journalism", "SRE incident response", "clinical pharmacology"), then answer the four questions for that field. Be concrete: name the actual thing, not the category.
- What a top professional would do that wasn't asked for. The two or three moves that separate expert work from competent work here, such as stating the decision the work serves, checking base rates, reproducing before fixing, or writing the counter-argument.
- The rawest material. The primary sources they would start from instead of summaries: the dataset, not the chart; the filing, not the article; the logs and the code, not the bug report; the paper's methods section, not the abstract. Say where it lives if you know.
- Specific methods and tools. Named techniques, instruments, libraries, commands, or frameworks, and why each fits this task.
- What, other than the user or the model, would show it is right. An external check: a test suite or benchmark, a reproduction, ground-truth data, a known answer to compare against, a measurement, a domain expert or reviewer, a real user's behavior. Say what result would count as a pass and what would count as a failure.
If you don't know something in the field well enough to answer, say so rather than inventing a source or tool.
Rewrite
Then write the rewritten prompt in a single fenced block the user can copy. It should ask for exactly what the four answers describe: start from the raw material, use the named methods, and end with the external check and its pass criterion. Keep it about as long as it needs to be, and in the user's voice.
Stop after the rewrite. Offer in one line to run it now; don't start the task unless the user says so.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.