context-audit

Hold the CEO seat: keep the goal and the decisions, hand every hands-on step to agents, and report the outcome.

Build or query the agent observability ledger obs.db, and roll its distilled rules into per-project digests.

Pick the scene team from the user's teams directory, compose its roles, and coordinate their work through completion.

Archive plan artifacts, distill this session into ccobs, correct a rule that proved wrong, then improve, merge, or retire existing skills before registering…

Watch running Herdr agents for a subscription rate-limit wall and either wake them after reset or hand the task to another agent.

Write and track a deterministic, acceptance-bearing dev plan as a mini-project.

Interview the user round by round across a design tree until every branch is settled.

Audit project architecture, domain model, and harness rules from a CTO lens.

This skill should be used to search Xiaohongshu (小红书/RED) and extract the real content of 图文 notes — via the `xhs` CLI's search, read, and comments — then…

This skill should be used to search Bilibili (B站/哔哩哔哩) and extract what videos actually say — via the `bili` CLI's search plus one-shot subtitle + AI summary…

Base skill: understand any local audio or video file by sending it to Gemini Flash-Lite (native multimodal — transcribes speech, reads on-screen text/slides…

Treat an open question — "which approach/library should we use?", "is this feasible?", "how do others solve this?" — as a tracked study that survives context…