// Push all local environments to the Prime Intellect Environments Hub. Use when environments are out of sync and need to be published.
Search the web via the Exa API. Accepts up to 10 queries in parallel. Returns titles, URLs, and highlighted snippets from each result.
Search Google via the Serper API. Accepts up to 10 queries in parallel. Returns titles, URLs, snippets, and knowledge-graph data.
Replace a unique string in a file. old_str must appear exactly once in the file.
Diagnose and repair-or-remove broken tasks under environments/general_agent/tasks. Use after `general-agent validate` reports [FAIL] entries (post-synthesis, after a refactor, or on a periodic sweep).
Synthesize a new general-agent task family from a seed task, evolving through difficulty tiers with empirical pass-rate gating. Use when asked to create new tasks or grow the task set.
Fetch a webpage via Exa and return an LLM-generated summary. Accepts an optional query that steers what the summary focuses on.
| name | env-sync-push |
| description | Push all local environments to the Prime Intellect Environments Hub. Use when environments are out of sync and need to be published. |
bash skills/env-sync-push/push.sh
The script pushes every environments/*/ directory to the hub in parallel (5 at a time). Environments whose content hash already exists are skipped automatically — only actually changed environments get published.
PRIME_API_KEY must be set or configured with prime config set-api-key.prime config set-team-id <team-id> before pushing. In CI, read the ID from PRIME_TEAM_ID.prime CLI must be installed (uv tool install prime).For each environment, prime env push -p environments/<dir> is called. The hub computes a content hash of the environment package:
The script only reports updated and failed environments. Skipped (unchanged) environments are counted but not listed, keeping the output focused on what actually changed.
/env-sync-check and seeing out-of-sync environments.