Dstoic

Capture friction with any Praxis artifact (skill, CLAUDE.md, rule, workflow) in under 30 seconds. Use when user says "kaizen", "log friction", "this annoyed me", or invokes `/kaizen <target> <note>`. One-shot append to `/praxis/thinking/kaizen/<target>.jsonl` — no editor, no follow-up questions, no context switch. Friction signal (fix existing), distinct from lazy skills (build new).

Session scratch pad for parking side-thoughts during deep work without losing flow. Use when user says "scratch", "note this", "park this", "jot this down", "remember for later", or wants to capture a quick thought mid-task. Always use this skill for any /scratch command — even for simple captures — because it manages numbered storage and stable IDs.

Evaluate whether the CURRENT model+effort fits a task, and recommend a switch only when worth the cache cost. Use when user asks "which model", "pick model", "model for", "what effort", "is haiku enough", "Opus or Sonnet", "should I downgrade/upgrade", or when routing a non-trivial task to a tier before starting costly/complex work. Judges model AND effort level. Does NOT execute the prompt — only judges fit. Covers tech and non-tech tasks.

Streamlined git commit for praxis-managed repos. Single human gate for scope + message approval. Use when committing changes, "commit repo", "commit praxis", "commit nano-vc".

Recursive meta-prompt ledger for human-guided complex tasks spanning multiple sessions. Maintains RELIANCE.md — a single-source, append-aware file carrying FINALITÉ, the RAIL session-chain, and the decision/collaboration trail across context resets. Use when: a complex task spans sessions and you want loss-free hand-off + drift detection + proportional AI challenge, WITHOUT autonomous loops or heavy regression tests. Triggers: meta-prompt, reliance, start a guided task, resume reliance, close session, next RAIL.

Introspective end-of-session retrospective — the agent reflects on its OWN context (method, decisions, dead-ends, token spend, estimated API cost, lessons) and writes an honest, root-caused report ending in a reusable playbook. Use at the end of a long or complex session (30min+, multi-phase, sub-agents spawned, or a hard problem solved) when the user says "post-mortem", "retrospective", "session retro", "debrief this session", "what did we learn", "write up this session". Not a log parser — it digs context for the narrative; JSONL usage counters may be aggregated for cost only.

Resume session from CONTEXT-llm.md. Use when resuming work, loading saved context, continuing a previous session. Triggers include "load context", "resume session", "continue where I left off".

Diagnose an agent FAILURE and prescribe the cheapest/earliest guardrail to add NEXT — then scaffold it ready to paste. Craft-on-the-fly, friction-driven, minimal: grow a harness to fit the real failure mode instead of designing one upfront. Sibling of /pick-model (picks the model) and /pick-workflow (picks the topology); this picks the GUARDRAIL. Domain-general — any agentic task, not just code. Use when 'agent keeps failing at X', 'it hallucinated/broke the contract/wasted tokens', 'what guardrail do I add', 'harness for X', 'how do I stop it doing Y', or when starting a new agentic task and you want a minimal starter harness. Also has a gated 'pipeline harness' tier for multi-stage agent pipelines (logs+verdicts+clean-room). Recommends + scaffolds; does NOT run the task.

Convert an analysis just done in-session into a resumable, traceable plan file — frontmatter + dashboard + execution log + lots whose closure is a re-runnable shell command — then run the execution pass (/pick-workflow then /pick-model) so a FRESH session can orchestrate it lot by lot. Use when the analysis is done but too big to execute here, when context is filling and the work must survive a /clear, or on 'turn this into a plan', 'give me a resumable/traceable plan', 'workstream plan', 'make this resumable', 'hand this off to a fresh session'. WRITES the plan; never executes it.

Save session to CONTEXT-llm.md with conversation summary. Use when saving work, checkpointing progress, preserving session state. Triggers include "save context", "save session", "checkpoint", "save my progress".

Decide HOW work should EXECUTE — linear vs parallel fan-out, sub-agents vs teams vs dynamic Workflow, and the per-step seam — instead of defaulting to linear+single-model. Produces an execution design, does NOT run the task. Delegates the per-step model+effort call to a model-picker skill when the environment has one. Use when authoring/challenging a skill or agent, AND mid-task when deciding how to run real work — 'should I fan this out', 'should this fan out', 'parallel or linear', 'sub-agents or workflow', 'per-step seam', 'execution topology', 'execution architecture'. For a trivial few-item call, early-exit to linear cheaply rather than a full analysis.

Generate a copy-paste instruction block to steer Claude Code's /compact so the summary keeps what matters. Use when about to compact context intentionally, before a long session gets summarized, or when the user says "instruct compact", "compaction instructions", "steer compact", "custom compact", "prepare compaction".