How do I install the Ots Summarize skill?

Run npx skillmds@latest add spillwavesolutions/ots-summarize in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Ots Summarize skill do?

After tick-hour, read .source.jsonl, apply the host-switch filter, write summary and saliency. Edition A (host CLI) or B (API key). Does not touch the snapshot. It is listed under Research & Search on SkillMD.

Is Ots Summarize safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ots Summarize?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ots Summarize free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ots Summarize?

spillwavesolutions (@spillwavesolutions) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ots Summarize by spillwavesolutions

Name: Ots Summarize
Author: spillwavesolutions

File contents

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/ots" summarize \
  --period 2026-08-21T14 \
  --author "$SECOND_BRAIN_IDENTITY" \
  --bundle "$SECOND_BRAIN_ROOT"

The model runs inline (Edition A or B from okf/temporal/tailer.json). No hidden queue. Scheduler is the user's cron — ots print-cron prints suggested lines.

Edition A (no API key) always passes the pinned cheapest model:

Claude Code: claude -p --model claude-haiku-4-5
Codex: codex exec -m gpt-5.6-luna
Grok Build: grok --model grok-4-fast -p

Missing CLI or wrong model fails loudly. Sonnet / Sol / Terra / any non-pin fails closed. Never use the session default. No silent fallback to Edition B.

Edition B: ANTHROPIC_API_KEY → claude-haiku-4-5; OPENAI_API_KEY → gpt-5.6-luna. Same prompt and files.

Tests / air-gapped:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/ots" summarize \
  --period 2026-08-21T14 \
  --author "$SECOND_BRAIN_IDENTITY" \
  --bundle "$SECOND_BRAIN_ROOT" \
  --stub

--model-cmd is an explicit override, not Edition B.

Inspect (no model call):

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/ots" sessions list --period 2026-08-21T14 --bundle "$SECOND_BRAIN_ROOT"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/ots" sessions show --id software_engineer__local__001 --bundle "$SECOND_BRAIN_ROOT"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/ots" summarize --status --period 2026-08-21T14 --bundle "$SECOND_BRAIN_ROOT"

Filter (not stored): user prompt + final assistant; skip tool_result. Never rewrite .source.jsonl. Overnight pointers stay out of scope.

Frequently asked questions

Ots Summarize