ambition
Skill5 starsChanged 7 days agoMITView on GitHub
Rewrite a task so it is done to a field-leading standard through one lens (depth, altitude, range), then lint the rewrite for raw material, instruments, a refutable assumption and an outside judge. Use for 'be ambitious', 'make this deeper', 'what would an expert do'.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- cicorias/skillstheir own version, first seen Nov 8, 2026
- neysofu/skillstheir own version, first seen Nov 1, 2026
- Wang-Cankun/cankun-skillstheir own version, first seen Nov 1, 2026
- vaayne/agent-kittheir own version, first seen Nov 1, 2026
- Nickanbe/ambitiontheir own version, first seen Oct 25, 2026
- erikmackinnon/skillstheir own version, first seen Oct 25, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- wanderingspirit03/ambition-skill★ 109same name
- vaayne/agent-kit★ 54same name
- MontySinger/ambition★ 4same name
- Wang-Cankun/cankun-skills★ 2same name
- cicorias/skills★ 1same name
- erikmackinnon/skills★ 1same name
- neysofu/skills★ 0same name
- Nickanbe/ambition★ 0same name
- samhvw8/ambition-skill★ 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.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 33
Write the rewrite in the user's voice with one labeled line per slot (Field:, Raw:, Instruments:, Assumption:, Judge:, Pass:, Fail:, plus …
“Common” is measured: kept by at least 6 in 10 of the 9 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
Ambition: Same Goal, Higher Bar
Outcome Contract
- Outcome: one rewritten prompt the user can copy, held to the standard a field-leading expert would use.
- Done when:
scripts/lint-prompt.sh --lens <lens>exits 0 on the rewrite. - Authorization: rewrite only. Run the task, or lock it as a plan for a new session, only when the user says so.
Lens
Resolve from a leading subcommand, else the request.
| Lens | Use when | Read |
depth (default) | Do this task really well | references/depth.md |
altitude | The task is one step toward an outcome the user named | references/altitude.md |
range | The work needs fields beyond the obvious one | references/range.md |
Depth keeps the goal and scope; drop any suggestion that makes the job bigger rather than better. Altitude and range may widen it, so state the widening in one line and let the user choose.
Steps
- Take the task after the subcommand, else the most recent request; none → ask for it in one line and stop. An existing feature (path, PR, plan) is a valid target: its code, tests and history are
Raw:, and its current tests are the floor theJudge:must keep green. - Name the field, then fill each slot from the lens reference with the actual thing, not the category. Unknown → say so; never invent a source or tool.
- Write the rewrite in the user's voice with one labeled line per slot (
Field:,Raw:,Instruments:,Assumption:,Judge:,Pass:,Fail:, plus the lens extras). - Pipe it to
scripts/lint-prompt.sh --lens <lens>. Eachfail:line names a slot to make concrete; fix and re-run untilok. A pass proves the slots are filled, not that they are right.
Output
The field, one line per expert move, then the rewrite in a single fenced block and the lint result. Offer in one line to run it now or lock it as a plan for a new session; on yes, route through mono's ambition playbook.
Defer to: think (whether the task is worth doing), brainstorm (scope and plan).
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.