Facilitates asking questions to teammates and managing self-reflection within the Egregore system.

Install

mkdir -p .claude/skills/ask-egregore-labs && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17482" && unzip -o skill.zip -d .claude/skills/ask-egregore-labs && rm skill.zip

Installs to .claude/skills/ask-egregore-labs

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Ask an asynchronous Egregore question to a teammate when the user invokes /ask or $ask, or help the current user formulate inward reflection questions.
151 chars✓ has a “when” trigger
Beginner

Key capabilities

  • Resolve the current author from state or git config
  • Load people from memory files
  • Draft concrete questions for a target teammate
  • Send questions to a target teammate
  • Generate questions for user self-reflection

How it works

The skill resolves the target teammate, drafts questions, and sends them asynchronously, or generates questions for the user's self-reflection if no target is specified.

Inputs & outputs

You give it
User's request to ask a teammate a question or for self-reflection
You get back
Sent questions to a teammate or a set of questions for user reflection

When to use ask

  • Ask teammate a question
  • Track project inquiries
  • Self-reflection

About this skill

Egregore Ask

Native Codex Egregore skill. Use this when the user wants to ask a teammate a question, run a topic by someone, or inspect pending questions for themselves.

Flow

  1. Run bin/agent.sh sync.
  2. Resolve the current author from .egregore-state.json, then git config.
  3. Load people from memory/people/*.md. Match target names against filename, name:, github:, and heading text, case-insensitively. Strip leading @.
  4. If the user named a target, draft one to four concrete questions. In connected mode, optionally gather context with bin/graph.sh queries, but suppress raw JSON and continue from memory files if graph access fails.
  5. Preview the exact questions and target. Use structured Codex question tooling when available; otherwise render:
Send these questions?
1. Send as-is
2. Edit
Other:
  1. For each approved question, run:
bin/agent.sh ask --from "$AUTHOR" --to "$TARGET" --topic "$TOPIC" --question "$QUESTION"

Add harvest flags only when this ask is part of a harvest: --harvest-id, --harvest-session-id, --turn, --question-intent, and --context-mode.

  1. In connected mode, notify best-effort with:
bash bin/notify.sh send "$TARGET" "$AUTHOR has a question about \"$TOPIC\". Ask for \$activity to answer."
  1. Report the created memory/knowledge/questions/... path.

Inward Mode

If no target matches, do not create a question file. Generate a small set of questions for the user to answer in-session, grounded in current conversation and memory context. Offer to save the result as a reflection only after the user answers.

Rules

  • Person-targeted asks are asynchronous: store, optionally notify, then stop.
  • Local mode is filesystem-only; skip graph and notification calls.
  • Do not use Claude Code commands.

When not to use it

  • When the user wants to use Claude Code commands
  • When the user wants to use graph or notification calls in local mode
  • When the user wants to ask a question that is not asynchronous

Limitations

  • Does not use Claude Code commands
  • Person-targeted asks are asynchronous
  • Local mode is filesystem-only

How it compares

This skill focuses on asynchronous question asking and self-reflection, providing structured question drafting and delivery, unlike direct conversational queries.

Compared to similar skills

ask side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
ask (this skill)01moReviewBeginner
team-collaboration-standup-notes13moNo flagsIntermediate
然而 / conversation / 风一样的坑爹哥04moNo flagsBeginner
internal-comms83moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry