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
scripts/sync_manager.py:259
scripts/sync_manager.py:249, scripts/sync_manager.py:269-274, test tests/test_sync_manager.py:590-594scripts/sync_manager.py:193-201, scripts/sync_manager.py:225-235, test tests/test_sync_manager.py:330-338scripts/sync_manager.py:202-211, scripts/sync_manager.py:239-241, test tests/test_sync_manager.py:340-352scripts/sync_manager.py:515
scripts/sync_manager.py:346-384, test tests/test_sync_manager.py:275-289scripts/sync_manager.py:387-427, test tests/test_sync_manager.py:400-413scripts/sync_manager.py:430-512, test tests/test_sync_manager.py:419-452_resolve_conflict a scripts/sync_manager.py:673-679scripts/sync_manager.py:616-632, test tests/test_sync_manager.py:455-468scripts/sync_manager.py:538-543, test tests/test_sync_manager.py:473-481scripts/sync_manager.py:558-567, test tests/test_sync_manager.py:484-503scripts/sync_manager.py:573-593, test tests/test_sync_manager.py:551-586scripts/sync_manager.py:115-124, test tests/test_sync_manager.py:604-615None.
tests/test_sync_manager.py: all passed.scripts/webapp/static/index.html:244-257, scripts/webapp/static/index.html:484-491, test tests/test_webapp.py:437-446scripts/webapp/static/index.html:480-491, test tests/test_webapp.py:449-456scripts/webapp/main.py:294-312, test tests/test_webapp.py:359-371scripts/webapp/main.py:309-311, scripts/webapp/static/index.html:496-549, test tests/test_webapp.py:372-379scripts/webapp/main.py:286-291, scripts/webapp/static/index.html:248-251, scripts/webapp/static/index.html:528-530, test tests/test_webapp.py:381-394None.
tests/test_webapp.py: all passed.SKILL.md:99-119
SKILL.md:101SKILL.md:104-115SKILL.md:118-119SKILL.md:109-111None.
All requirements from the three delta specs are implemented and verified. No semantic drift or undocumented behavior was found. The only test quirk is the pre-existing flaky test_stale_takeover_race_has_single_winner in the untouched file-locking capability, documented in .spec-verify-report.md.
.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