weft

Returns the file path of the current session's JSONL log. With --stamp, adds provenance (session path + timestamp) to a file as YAML frontmatter (default) or HTML comment (--back). Use when a skill or agent needs to reference or annotate the current conversation's log file.

Onboarding interview for the personal development harness. Scans background/ for pre-loaded materials (code, resumes, writing, transcripts), runs a conversational interview to discover background, goals, current skills, and learning preferences, then generates a personalized CLAUDE.md and initial current-state.md. Use when setting up a new learner, onboarding, or bootstrapping the harness.

Cross-session learning pattern analysis. Reads multiple session logs and learning state to detect stalls, regressions, goal drift, and arc readiness that no single session review can see. Proposes updates to learning state files. Use when the user asks "how am I doing", "review my progress", "am I improving", or "progress review". Also dispatched automatically by startwork when enough sessions have accumulated.

Returns a structured learning-state diff from session evidence without quizzing or writing files. Callers (session-review, startwork, or the user's main context) handle presentation, approval, and writes. Use when learning state is stale, before startwork, or when the user wants to update scores without a full session review.

Discovers Claude Code conversation sessions on the local machine within a date range. Returns a structured manifest of sessions with metadata. Use when a skill or agent needs to find prior conversations — e.g., session-review gathering evidence, progress-review windowing, or startwork checking recent activity. Not user-facing; designed as infrastructure for other skills.

Audits Claude Code security configuration against the Safer YOLO guide. Checks sandbox, deny rules, hooks, DCG, and gitleaks. Surfaces findings in plain language with customized recommendations. Use when the user mentions YOLO mode, bypass permissions, skipping permissions, "dangerously-skip-permissions", security setup, or wants to harden their configuration.

Ships working changes: stage, commit, create PR via gh. Accepts --merge to squash-merge after PR creation, and --dry-run to preview without executing.

Composes a session plan from local state. Reads git status, learning state (goals, arcs, current-state, session logs), schedule, and project context to rank what matters most and propose a time-budgeted session plan. Use when starting a work session, or when the user says "startwork", "start work", "what should I work on", "session plan", or "what's next."

Guides debugging when something is broken or behaving unexpectedly. Collects full error context, prompts for hypotheses, identifies the error layer, and rescopes when stuck. Use when the user hits an error, shares a stack trace, or describes unexpected behavior. Teaches error-reading as a byproduct of fixing the problem.

Naive reader handoff test. Audits the session's primary artifact(s) for self-containedness before context is lost. Use before compaction, /clear, or end-of-session. Identifies what the artifact assumes but doesn't say.

Restructures external learning materials into a conceptual scaffold tailored to the learner's current level. Reads learning state (current-state, goals, session logs) to classify concepts and shape the scaffold. Writes a persistent scaffold file to learning/scaffolds/. Use when the user provides learning materials and wants to understand the "why" before executing.

Saves the current plan to plans/ with a descriptive name. Use after plan approval or before compaction.

Gives direct, concise answers to factual and structural questions. Use when the user needs a fast answer rather than a teaching interaction — lookups, syntax reminders, "how do I do X," or "what does Y do." Flags the bigger picture in one sentence when a narrow question hints at a structural gap, but never cascades into teaching.

End-of-session learning review. Analyzes session for learning patterns and concept coverage, quizzes on 4-6 concepts biased toward gaps, then logs results to session log frontmatter and current-state.md. Use at the end of a working session or when the user requests a review, quiz, or session summary.

Activates when composing, editing, or reviewing a SKILL.md file or any agent-facing instruction document (reference files, CLAUDE.md sections, sub-agent dispatch payloads). Guides the author toward token-efficient, behaviorally precise prose.

Generates a complete handoff prompt for the next agent from session memory. Conserves context. Use before compaction, /clear, or when context is running low and work needs to continue in a fresh session.