self-message
Self-Message
You can send yourself a continuation message to start a fresh agentic loop within the same session. This resets your reasoning frame while preserving full conversation context.
This is NOT a subagent. It's a new turn for YOU — same session, same context, new frame.
How It Works
- Send your self-message using the bundled script
- Finish your turn normally (stop responding)
- A Stop hook intercepts your stop, reads the message, deletes it
- The hook returns
{"decision": "block", "reason": "<your message>"} - You receive the message as context and start a new agentic loop
bash ${CLAUDE_SKILL_DIR}/scripts/self-message.sh "Reassess: the recursive approach hit a dead end. Try iterative with memoization instead."
More from alberduris/skills
x-twitter
Interact with X (Twitter) API v2. Post tweets, search, engage, moderate, and analyze — all from your AI agent. Full 36-command skill for Twitter/X automation.
107second-opinion
Consult peer LLM for alternative perspectives when you need second opinion, peer review, or fresh take on technical decisions; useful for validating approaches or exploring alternative solutions
11langfuse-traces
Query Langfuse traces for debugging LLM calls, analyzing token usage, and investigating workflow executions. Use when debugging AI/LLM behavior, checking trace data, or analyzing observability metrics.
11newspaper-explainer
Generate self-contained HTML broadsheet newspapers to explain any subject worth reporting — project status, reviews, dispatches, reports, or anything else.
11telegram-notify
Send notifications via Telegram. Use when the user asks to notify, alert, message, or ping — or when a long-running task completes and the user previously asked to be notified. Can also schedule messages for later delivery.
4beehiiv
Manage your Beehiiv newsletter — list and read posts, create drafts from Markdown/HTML files. 6-command skill for Beehiiv newsletter automation.
1