by session

Other Community v1.0

Skill notes

When to Use This Skill

Use this skill when you have: ✅ A new session opening in a BY project directory — the SessionStart hook fires this skill automatically ✅ No .by/config.json yet — run the first-run questionnaire to capture compute provider, model profile, campaign defaults ✅ A request to refresh environment discovery — re-scan local tools, conda envs, GPU, API keys ✅ A request to switch compute provider — update compute.default_provider cleanly without overwriting unrelated fields

Quick Start

Total time: ~1 second when config exists; ~30 seconds for first-run questionnaire.

Inputs

Required: Working directory — the BY project root (current directory by default). User input (first run only) — answers to the 3-round questionnaire (compute provider, model profile, campaign defaults). Optional (auto-detected): .by/config.json — if present, skip questionnaire entirely.

Outputs

All outputs land under .by/ in the project root. File · Type · When written · Purpose .by/config.json · JSON · First run, or on user-driven update · User preferences: compute provider, providers_priority, model_profile, campaign defaults .by/environment.json · JSON · First run + /by:setup refresh · Auto-detected hardware/tools snapshot (GPU model, VRAM, conda envs, tool paths, API keys present)

Clarification Questions

⚠️ CRITICAL: ASK THIS FIRST — Confirm .by/config.json does not already exist before running the questionnaire. Re-running the questionnaire would overwrite the user's saved preferences. Config file presence (ASK THIS FIRST) — Does .by/config.json already exist? If yes, skip the questionnaire and go straight to the session banner. If no, proceed to Q2. (You can check this silently — only ask the user if there's ambiguity, e.g., the file exists but is corrupted.)

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Other
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
92 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@001TMF · v1.0 · no license declared
Token usage
Lean
Setup complexity
Manual integration
External API key
Required · Vendor-specific
Operating systems
macOS · Linux · Windows
Runtime requirements
Node.js · Python >=3.10
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
  • Env read
Network behavior
External requests
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

01
Step 1 — Detect first-run vs returning session

✅ VERIFICATION: Output is exactly `returning` or `first-run`.

02
Step 2a — First-run: run the questionnaire

Or for a non-interactive default install (CI, automated scaffolding): ✅ VERIFICATION: Expect `✓ Wrote .by/config.json with provider=local` (or whichever provider the user selected). The questionnaire collects answers in three rounds (compute, profile, campaign defaults) and writes `.by/config.json`. The default provider is `local` and `providers_priority` is `["local", "hpc", "tamarind"]`. If the user picks `hpc`, the

03
Step 2b — Returning session: read config + environment

✅ VERIFICATION: Expect `✓ Config valid: provider=<name>, profile=<name>`. If validation fails, surface the specific field error to the user and ask before overwriting anything. Do NOT silently re-run the questionnaire.

04
Step 3 — Show banner

Step 3 — Show banner

05
Step 4 — Check for in-progress campaigns

Count campaigns and inspect each `status` field. See `references/resume-protocol.md` for the exact rules on what counts as "in progress" and what gets restored.

06
Step 5 — Display status

Build the compute line from `compute.default_provider` and any populated provider blocks. Examples: `Compute: Local GPU ✓ (BoltzGen, Protenix, PXDesign)` `Compute: HPC ✓ (target=runpod, key=RUNPOD_API_KEY)` `Compute: Tamarind ✓ (free tier)`

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.