القائمة
Use when running devloop council analysis on a repo. Covers the correct op run invocation, model selection, and narrative output format. Invoke instead of `just analyze` which is broken.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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.
| name | devloop-analyze |
| description | Use when running devloop council analysis on a repo. Covers the correct op run invocation, model selection, and narrative output format. Invoke instead of `just analyze` which is broken. |
just analyzeThe just analyze recipe is broken because it doesn't handle env conflicts from shell-injected op:// vars.
# The op-conflict-resolver hook will auto-detect conflicts and suggest the prefix.
# Manual form if needed:
env -u TAVILY_API_KEY -u CONTEXT7_API_KEY -u GEMINI_API_KEY -u FIRECRAWL_API_KEY \
op run --account=my.1password.com --env-file=/Users/joe/.secrets -- \
devloop analyze --repo /path/to/repo
Note: If op-conflict-resolver hook is active, just run op run --account=my.1password.com --env-file=/Users/joe/.secrets -- devloop analyze --repo /path/to/repo and the hook will correct it automatically.
--model flag, specify explicitlyWhen presenting council results:
Before or after devloop analyze, query Pieces for historical context:
ask_pieces_ltm: "what was I working on in [repo name] recently?"
ask_pieces_ltm: "what problems did I hit with [specific feature]?"
Requires PiecesOS running: curl -s http://localhost:39300/.well-known/health
After analyze, export for sharing:
devloop export --repo /path/to/repo --output /tmp/report.md
| Symptom | Fix |
|---|---|
op run resolves wrong secret | Shell has conflicting var — use env -u or let hook auto-fix |
| Council returns no results | Check --repo path is correct git repo |
| qwen3 model errors | Switch to OpenAI model explicitly |
| PiecesOS not responding | curl http://localhost:39300/.well-known/health — restart if down |