Dev-Jahn

Use when the user runs "/waystone:delegate" in Claude Code or "$waystone:delegate" in Codex, asks to delegate an implementation task, wants to inspect or independently verify a delegation result, or needs to apply or discard a reviewable delegated patch.

This skill should be used when the user runs "/waystone:ideate" in Claude Code or "$waystone:ideate" in Codex, has a new or half-formed project idea, says things like "I want to build X but haven't thought it through", "help me figure out what I'm actually building", "let's scope/shape this project", "brainstorm the direction", or asks to "write a design doc / SSOT" — especially at the very start, before any design document exists. It draws a project's north-star out of the user through Socratic questioning and writes it as a ready-to-adopt SSOT.md that the rest of the workflow anchors to.

This skill should be used when the user runs "/waystone:improve" in Claude Code or "$waystone:improve" in Codex, asks for workflow-improvement suggestions, wants to analyze their Claude Code or Codex 작업 이력 (work history), requests 개선 제안 grounded in past sessions, or asks "how can I work better / where am I wasting effort across my projects". It mines the user's existing host session logs plus round/review evidence into deterministic facts, then presents evidence-grounded, provenance-labeled recommendations for the user to accept or reject — recording each decision without applying anything automatically.

This skill should be used when the user runs "/waystone:init" in Claude Code or "$waystone:init" in Codex, asks to "initialize the workflow harness", "set up waystone", "adopt the workflow in this project", or "re-sync the workflow setup". One-click setup for new projects and non-destructive retrofit for projects already in progress.

This skill should be used when the user runs "/waystone:review" in Claude Code or "$waystone:review" in Codex, pastes an external review reply (e.g. from web ChatGPT / GPT reviewer) to be processed, or asks to "ingest the review", "process the reviewer feedback", "record the external review". Preserves the review verbatim and triages findings into the task registry.

This skill should be used when the user runs "/waystone:round" in Claude Code or "$waystone:round" in Codex, says to "close the round", "wrap up this round", "finish the work cycle", or when an autonomous work round (implement → verify → push) reaches its end and the project's host instruction file mandates round closeout. Updates the task registry, PROGRESS, roadmap, SSOT views, and writes the round's markdown review request.

This skill should be used when the user runs "/waystone:status" in Claude Code or "$waystone:status" in Codex, asks "what's the status across my projects", "show the project dashboard", "which tasks are active/blocked", or wants a cross-project overview of branches, rounds, and task progress.

This skill should be used when the user runs "/jahns-workflow:brain-tempest", has a new or half-formed project idea, says things like "I want to build X but haven't thought it through", "help me figure out what I'm actually building", "let's scope/shape this project", "brainstorm the direction", or asks to "write a design doc / SSOT" — especially at the very start, before any design document exists. It draws a project's north-star out of the user through Socratic questioning and writes it as a ready-to-adopt SSOT.md that the rest of the workflow anchors to.

This skill should be used when the user runs "/jahns-workflow:init", asks to "initialize the workflow harness", "set up jahns-workflow", "adopt the workflow in this project", or "re-sync the workflow setup". One-click setup for new projects and non-destructive retrofit for projects already in progress.

This skill should be used when the user runs "/jahns-workflow:review", pastes an external review reply (e.g. from web ChatGPT / GPT reviewer) to be processed, or asks to "ingest the review", "process the reviewer feedback", "record the external review". Preserves the review verbatim and triages findings into the task registry.

This skill should be used when the user runs "/jahns-workflow:round", says to "close the round", "wrap up this round", "finish the work cycle", or when an autonomous work round (implement → verify → push) reaches its end and the project CLAUDE.md mandates round closeout. Updates the task registry, PROGRESS, roadmap, SSOT views, and writes the round's markdown review request.

This skill should be used when the user runs "/jahns-workflow:status", asks "what's the status across my projects", "show the project dashboard", "which tasks are active/blocked", or wants a cross-project overview of branches, rounds, and task progress.

This skill should be used when the user asks to "start the autoresearch loop", "kick off overnight iteration", "begin autonomous experiment runs", "run /autoresearch:run", "run the autoresearch expr <slug>", "continue the autoresearch loop", "resume autoresearch", "chain through follow-up experiments", or otherwise hand off an ML experiment to the autonomous runner. Drives the self-propelling train.py iteration loop on a configured `.autoresearch/{expr}/` experiment — one-line edit, `ar run`, read `result.json`, decide next edit, repeat — for hours or days until a termination condition fires. Context-minimized so thousands of iterations fit in a single session. Invoke immediately without asking clarifying questions beyond the structured interview; the skill itself is self-driving and must never stop mid-loop to ask the user "continue?" — Ctrl+C is the only authorized interrupt.

Scaffolds a new autonomous-research experiment directory (`.autoresearch/{YYMMDD}-{slug}/`) inside a deep-learning project so Claude can run a long train.py-mutation loop without blowing context. This skill should be used when the user asks to "start an autoresearch experiment", "set up autonomous research loop on this project", "create a new .autoresearch run", "scaffold autoresearch", "initialize autoresearch for this repo", "kick off an autonomous training loop", "set up Karpathy-style autoresearch here", or otherwise indicates they want Claude to begin autonomous iteration on their ML research code. The skill performs a venv preflight, analyzes the project's editable-install Python packages, surfaces primary-metric candidates from whichever tracker the host uses (wandb / tensorboard / plain stdout logs), introspects the host's training entrypoint (argparse-CLI script vs importable main() function vs hydra app), infers the distributed framework (accelerate / torchrun / FSDP / DDP / pytorch-lightning / none

This skill should be used when the user asks to "replace A with B", "substitute a word", "rename a term across files", "치환", or any find-and-replace across lines, sections, files, or directories. **ALWAYS** use this skill over native Write/Edit tools, if your task is simple string substitution.