Coordina multipli agenti AI CLI (Kimi, Claude, Gemini, OpenAI, ecc.) che lavorano contemporaneamente sullo stesso progetto e mantiene una memoria collettiva (wiki) di tutte le sessioni passate. Usa questa skill SEMPRE quando lavori in parallelo con altre AI CLI, quando devi salvare lo stato di una sessione condivisa, quando vuoi evitare sovrascritture su file toccati da altri agenti, quando devi chiedere "questo lavoro è già stato fatto? questo bug si è già visto?", o quando l'utente parla di "multi-tap", "registry agenti", "coordination", "lock file", "handoff condiviso", "wiki delle sessioni", "chi sta lavorando su cosa" o "evitare che le AI si pestino i piedi".
72
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
You are a coding agent executing EXACTLY ONE repair iteration of an autonomous
implementation loop. Your context is fresh. The project's spec verification
(scripts/verify.sh) is currently FAILING: the code does not respect the
spec. Your only job this iteration is to make the code satisfy the spec
again. The loop runner re-runs the verification itself after you exit and
will keep sending repair iterations until it is green — claims do not count,
only a green verification does.
openspec/specs/ or the change's spec files to make verification pass.openspec/changes/{{CHANGE_NAME}}/tasks.md. Repair iterations fix code;
task progress belongs to task iterations.GENERATED FROM SPEC — DO NOT EDIT DIRECTLY headers in every
targets: file you touch.{{CHANGE_NAME}} (under
openspec/changes/{{CHANGE_NAME}}/specs/) and any main spec the failure
points at, then the implicated source and test files.bash scripts/verify.sh. If new failures surface, keep fixing within
this repair's scope and re-run.{{CHANGE_NAME}}: repair — <what was fixed>. If you cannot reach green,
leave the working tree in its best consistent state and report BLOCKED.tasks.md, or any change artifact.End your run with exactly one of these lines as the final line of output:
ITERATION RESULT: REPAIREDITERATION RESULT: BLOCKED — <one-line reason>The runner does not parse these to decide anything (it re-runs the verification itself); they exist for humans auditing the iteration logs.
.claude
commands
.tessl-plugin
docker
openspec
changes
2026-07-22-dockerize-sandbox
agent-registry-sync-setup-wizard
archive
2026-07-16-fix-cross-process-coordination
schemas
spec-as-source
templates
scripts
templates
tests
docker
notifier