Engage: rewrite a rough prompt into a strong, more ambitious one, then carry it out.
Adapted from be-ambitious (MIT, RoboNuggets), after Felix Rieseberg's article on ambition for humans with models.
The prompt: the words typed after the command
Empty → the prompt is the user's message just before this command (what they wrote
before typing it). Nothing there either → ask for the prompt in one line and stop.
First decide what you were handed. A prompt to improve (a rewrite is asked for, or
it is meant for another agent or tool) → stop after the rewrite. A task to do →
carry it out. Cannot tell → stop after the rewrite.
- Aim higher — better, not bigger. Find the goal beyond the goal: the outcome
this task serves. Pick the ambition types that fit (usually one or two); skip a
type that does not fit. Ambition raises the outcome, the standard or the
perspectives — never the deliverables, features or side quests.
- Altitude — the task serves an outcome: climb the ladder (do this task →
remove the whole class of it → keep it from coming back, naming the setup
that needs), and work the highest rung you can finish and check with the
access you have.
- Depth — the task should be done really well: start from the rawest
material, not what was digested for you; use the field's best methods and
instruments, not its vocabulary; set a specific hard target and treat it
as reasonable.
- Range — the result must land with people, or the obvious field is stuck:
name the verbs under the nouns, bring in the fields they call for, each
doing its real job with its own tools (a subagent each, where available) —
never role-play. A narrow fix with one right answer takes Depth only.
- Rewrite it. Keep every requirement, name, path, number and constraint exactly,
and the user's intent. Make the goal and the goal beyond it explicit; add what
"done" means, the scope (what not to touch), the context the repo already gives
(read the files and conventions it names - never guess them) and the output
expected. List the data, tools and access the plan needs, each marked have or
missing (and what a missing one would unlock); never invent a source, tool or
result. End with the outside judge: a test, benchmark, reproduction,
measurement or other check that is not you, and what counts as a pass. Settle
an ambiguity by its most likely reading; never invent a requirement. A gap
that would change the result and that the repo cannot settle → ask that one
question first.
- Show it. At most three short lines first: the goal beyond the goal; the
types picked and skipped; what is missing. Then the rewrite once, under
**Engaged prompt:**, as a quote block. No other commentary.
- Do it. Treat the engaged prompt as the user's request, in this same turn,
with every rule of this session still in force (skills, CLAUDE.md / AGENTS.md /
GEMINI.md, permissions). Start at the rung you picked. For the work itself, ask
first only when that rung replaces what the user asked for instead of raising
it, spends money, or cannot be undone; otherwise no stop for approval. Report
honestly against the judge: a missed hard target with real numbers is a result;
a faked pass is not.
1---2name: engage-picard3description: Improve the prompt written before (or after) this command with AI - aim at the goal beyond the goal - then carry it out4metadata:5 source: https://skillmd.com/skills/bodish-coder/engage-picard6---78Engage: rewrite a rough prompt into a strong, more ambitious one, then carry it out.9Adapted from be-ambitious (MIT, RoboNuggets), after Felix Rieseberg's article on ambition for humans with models.1011The prompt: the words typed after the command12Empty → the prompt is the user's message just before this command (what they wrote13before typing it). Nothing there either → ask for the prompt in one line and stop.1415First decide what you were handed. A prompt to improve (a rewrite is asked for, or16it is meant for another agent or tool) → stop after the rewrite. A task to do →17carry it out. Cannot tell → stop after the rewrite.18191. **Aim higher — better, not bigger.** Find the goal beyond the goal: the outcome20 this task serves. Pick the ambition types that fit (usually one or two); skip a21 type that does not fit. Ambition raises the outcome, the standard or the22 perspectives — never the deliverables, features or side quests.23 - **Altitude** — the task serves an outcome: climb the ladder (do this task →24 remove the whole class of it → keep it from coming back, naming the setup25 that needs), and work the highest rung you can finish and check with the26 access you have.27 - **Depth** — the task should be done really well: start from the rawest28 material, not what was digested for you; use the field's best methods and29 instruments, not its vocabulary; set a specific hard target and treat it30 as reasonable.31 - **Range** — the result must land with people, or the obvious field is stuck:32 name the verbs under the nouns, bring in the fields they call for, each33 doing its real job with its own tools (a subagent each, where available) —34 never role-play. A narrow fix with one right answer takes Depth only.352. **Rewrite it.** Keep every requirement, name, path, number and constraint exactly,36 and the user's intent. Make the goal and the goal beyond it explicit; add what37 "done" means, the scope (what not to touch), the context the repo already gives38 (read the files and conventions it names - never guess them) and the output39 expected. List the data, tools and access the plan needs, each marked have or40 missing (and what a missing one would unlock); never invent a source, tool or41 result. End with the outside judge: a test, benchmark, reproduction,42 measurement or other check that is not you, and what counts as a pass. Settle43 an ambiguity by its most likely reading; never invent a requirement. A gap44 that would change the result and that the repo cannot settle → ask that one45 question first.463. **Show it.** At most three short lines first: the goal beyond the goal; the47 types picked and skipped; what is missing. Then the rewrite once, under48 `**Engaged prompt:**`, as a quote block. No other commentary.494. **Do it.** Treat the engaged prompt as the user's request, in this same turn,50 with every rule of this session still in force (skills, CLAUDE.md / AGENTS.md /51 GEMINI.md, permissions). Start at the rung you picked. For the work itself, ask52 first only when that rung replaces what the user asked for instead of raising53 it, spends money, or cannot be undone; otherwise no stop for approval. Report54 honestly against the judge: a missed hard target with real numbers is a result;55 a faked pass is not.