delegating-worklisted
Install: claude install-skill rundesk-ai/rundesk-cli
# Work to an outcome
Own the requested outcome until every required result is delivered and proved. Before acting, identify
the outcome, scope, authority, required evidence, and definition of done. Keep optional findings
separate from the required result.
## Recover context before acting
When a referent, decision, owner, constraint, or prior result is missing, recover it from the current
conversation, supported Rundesk history, and the project's current source in that order. Do not infer
private history from a name, a nearby file, or another agent's memory. Separate observed facts,
inferences, and unknowns. Ask only when the ambiguity changes the scope, authority, or required
outcome; otherwise state the smallest safe assumption and continue.
If the needed context cannot be recovered, preserve the gap in the task and report it as a blocker.
Do not turn an absent fact into a confident instruction or delegated brief.
## Check your own skills before delegating
Before deciding to delegate, inspect your available skill descriptions and load each skill whose
intent matches the work. Apply that guidance to the delegation decision: it may give you the domain
knowledge, workflow, or tools to handle the task directly. If another agent remains materially better
suited, use what you learned to make the scope, constraints, evidence, and definition of done precise.
A grant only makes a skill available; do not treat its body as already loaded. Do not load unrelated
skills, and do not