Researcher Context Audit

D

deepseek-reasonruvnet

86

Reasoning-mode completion against DeepSeek's `deepseek-reasoner` model (R1) via /v1/chat/completions. Surfaces the model's chain-of-thought (`reasoning_content`) separately from the final answer (`content`), so callers can display or discard the CoT without re-parsing. Reads DEEPSEEK_API_KEY; degrades gracefully (exit 0 with status:degraded envelope) when unset or the API is unreachable. Ignores temperature/top_p per DeepSeek's spec for reasoner models.

G

gog-weekly-digestopenclaw

84

Read-only weekly digest across Google Calendar, Gmail, and Tasks with gog.

T

triage-ticketagentscope-ai

84

First-response playbook for an inbound customer message — classifies the ticket, restates the issue, gathers missing context, and routes the reply.

C

commit-messagezulip

84

Write a commit message following Zulip's format. Use whenever writing or rewording any commit message.

W

wepushrememberber

84

Use WePush Next to inspect push channels and jobs, prepare message and recipient drafts, run dry runs, send explicitly authorized notifications, and inspect delivery results. Use when the user asks to operate WePush, not for unrelated messaging services or editing WePush source code.

O

organizationagentscope-ai

83

Use only when you need to look up team topology, worker phase, runtime state, or identity that is NOT available from the current message context. Do not use for standard task flows — the coordinator is the message sender, and the task room is in meta.json.room_id.