メニュー
Use before starting work on a feature or bug to get historical context from 9 months of LTM. Use when you need to know "what did I try before", "why was this decision made", or "what was the state of X last month".
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
| name | pieces-ltm |
| description | Use before starting work on a feature or bug to get historical context from 9 months of LTM. Use when you need to know "what did I try before", "why was this decision made", or "what was the state of X last month". |
curl -s http://localhost:39300/.well-known/health
# Should return: {"status":"ok"} or similar
# If not: open PiecesOS app on this machine
Temporal queries (what was I doing when):
"What was I working on in the devloop project in January?"
"What did I research about BAML in the last 3 months?"
Decision archaeology (why did I do X):
"Why did I switch from Docker Desktop to colima?"
"What problems did I hit when setting up the Gitea runner?"
"What was the reason I chose mise over nvm?"
Prior art (have I solved this before):
"Have I written a script to parse op:// env vars before?"
"Did I ever debug a source_up chain issue in direnv?"
"What was the fix for the BAML version mismatch I hit before?"
Current project context (before starting work):
"What's the current state of the minibox CI pipeline?"
"What was I last working on in maestro?"
"What problems were blocking the devloop release?"
1. curl -s http://localhost:39300/.well-known/health # verify running
2. ask_pieces_ltm: "What was I last working on in [repo]?"
3. ask_pieces_ltm: "What known issues or blockers exist for [feature]?"
4. Proceed with session informed by historical context
| Symptom | Fix |
|---|---|
| Health check fails | Open PiecesOS app; wait 30s for startup |
| ask_pieces_ltm not found | Check personal-mcp is running in Claude settings |
| Empty/irrelevant results | Rephrase query; try more specific date range or project name |
| Results from wrong context | Add project name to query to narrow scope |
Deep codebase analysis — architecture health, test coverage gaps, tech debt, and actionable findings
Run pre-commit checks (fmt, clippy, test) then stage, commit, and push with a conventional message
Review staged or recent changes for correctness, style, and Rust conventions before committing
Use when SSHing into remote machines, looking up credentials, renaming Tailscale devices, or accessing services on the tailnet. Symptoms - SSH auth failures, too many authentication failures, command not found tailscale, need to find credentials for remote machines.
Use when mixing Tokio async code with synchronous blocking I/O libraries (tar, flate2, zip, csv), or when seeing "cannot block the current thread from within the async context" panics, or needing to stream async bytes into a sync reader.
Structured BAML schema edit → validate → test loop for the devloop project. Use when editing any *.baml file in crates/baml/baml_src/ — covers version parity gotchas, uvx invocation, regeneration workflow, and the analyze verify step.