メニュー
Cross-session memory via Reflexio server. Search is automatic (hook-injected before every response). Use reflexio_publish tool to flush corrections and learnings immediately. Manual search fallback via exec if hook injection is empty.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Run lint checks (ruff for Python, Biome for TS/JS), type checks (pyright for Python, tsc for TS/JS), and the standard pytest tiers (unit + e2e + tests skipped during pre-commit). Investigates failures to determine if they are application bugs or test issues, and fixes application bugs rather than weakening tests. Does not run paid-LLM real-API tests or scenario probes from the test-* command family.
Start all local services (backend, frontend, docs) with dependency checking, error diagnosis, and automatic recovery. Handles missing npm/python packages, port conflicts, and stale processes.
Sync AI coding tool instruction files (AGENTS.md, GEMINI.md, AGENTS.md) so they stay aligned. Detects which file changed and copies it to the others. Use when syncing md files, syncing instructions, updating GEMINI.md, or updating AGENTS.md.
Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or constraint; (2) user corrects the agent and confirms the fix with an explicit 'good'/'perfect' or by moving on without re-correcting for 1-2 turns; (3) at start of a user turn, to retrieve relevant facts and playbooks from past sessions.
Run a full-sweep consolidation over all .reflexio/ files — TTL sweep + n-way cluster merge. Use when the user asks to 'clean up reflexio', 'consolidate memory', 'deduplicate playbooks', or suspects drift across sessions.
Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or constraint; (2) user corrects the agent and confirms the fix with an explicit 'good'/'perfect' or by moving on without re-correcting for 1-2 turns; (3) at start of a user turn, to retrieve relevant facts and playbooks from past sessions.
| name | reflexio |
| description | Cross-session memory via Reflexio server. Search is automatic (hook-injected before every response). Use reflexio_publish tool to flush corrections and learnings immediately. Manual search fallback via exec if hook injection is empty. |
Reflexio remembers corrections and preferences from past conversations. A hook automatically searches Reflexio before every response and injects relevant context — you don't need to do anything for retrieval.
User Profiles — facts about the user: expertise, preferences, environment, constraints.
User Playbooks — behavioral corrections from past sessions:
Agent Playbooks — shared corrections aggregated from all agent instances.
A hook runs reflexio search on every user message and injects matching profiles and playbooks as context before your response. No action needed.
If no context appears for a task — the hook may not have found results, or the server may be starting. Run a manual search:
reflexio search "<the user's task or request>"
If the command fails with a connection error and REFLEXIO_URL is unset or points to localhost, the plugin will start the server automatically. If it points to a remote server, report the issue to the user.
reflexio_publish)Conversations are automatically published to Reflexio at session end and periodically mid-session. For high-signal moments, call the reflexio_publish tool to flush immediately:
The Reflexio server handles extraction (profiles, playbooks) from the published conversations. You don't need to structure the data — just publish, and the server does the rest.