lwy-dispatch
Internal single-process coordinator for the three IDE-hook events used by the learnwy-* skills. UserPromptSubmit aggregates english-learner + llm-wiki + prompt-optimizer scans; Stop aggregates english-learner + knowledge-consolidation scans; SessionStart aggregates llm-wiki + english-learner + learnwy-status scans. Not user-invokable — installed automatically alongside the underlying skills. Triggers on every UserPromptSubmit / Stop / SessionStart event in Claude Code / Trae.
What this skill does
# learnwy-dispatch Single-process coordinator for the three IDE-hook events shared by the learnwy-* skills. ## Why Before this skill, every event fired N separate hook commands — one Node process per skill — and the user saw N back-to-back `<system-reminder>` blocks per turn. That multiplies the per-turn hook startup cost (~50 ms × N vs ~50 ms) and clutters context. This skill replaces those entries with **one hook per event** that imports each skill's pure scanner function, runs them in-process, and emits a single combined reminder. ## What runs per event ### UserPromptSubmit (`hooks/user-prompt-submit.cjs`) | Order | Module | Returns reminder when | |---|---|---| | 1 | `english-learner/lib/prompt-scan.scanPrompt` | English ratio ≥ 0.6 OR Chinese learn-intent OR Chinese ratio ≥ 0.3 | | 2 | `llm-wiki/lib/prompt-scan.scanPrompt` | wiki/topics.txt has any keyword overlapping a 4+ char word in the message | | 3 | `prompt-optimizer/lib/prompt-scan.scanPrompt` | explicit "optimize my prompt" trigger OR long structured prompt-shape | ### Stop (`hooks/stop.cjs`) | Order | Module | Returns reminder when | |---|---|---| | 1 | `english-learner/lib/stop-scan.scanStop` | Assistant response has 2–4 advanced English words worth surfacing | | 2 | `knowledge-consolidation/lib/stop-scan.scanStop` | Response shows substantive resolution signals (race condition / regression / "subtle"), not session-local trivia | ### SessionStart (`hooks/session-start.cjs`) | Order | Module | Returns reminder when | |---|---|---| | 1 | `llm-wiki/lib/session-scan.scanSession` | wiki/topics.txt exists — inject ≤30 topics | | 2 | `english-learner/lib/session-scan.scanSession` | First session of the day — push 3 due-for-review cards | | 3 | `learnwy-status/lib/session-scan.scanSession` | First session of the ISO week — prepend a compact cross-skill digest | Each scanner is a pure `(message | payload) => string | null` (a couple have minor side effects: prompt-optimizer appends to `~/.learnwy/prompt-optimizer/events.jsonl`; KC writes a debounce stamp). If any scanner throws, the failure is swallowed and the others still run. ## Installation This skill is installed by `pnpm run install:hooks` like any other skill. The corresponding `UserPromptSubmit` entries in `english-learner`, `llm-wiki`, and `prompt-optimizer` `hooks.json` files have been removed — only this skill registers a UserPromptSubmit handler now. After upgrading from a version without `learnwy-dispatch`, run: ```bash pnpm run uninstall:hooks # remove the old per-skill UserPromptSubmit entries pnpm run install:hooks # install the dispatcher (and re-register the others) ``` The `pnpm run install:hooks` orchestrator performs an uninstall sweep before installing, so you can re-run it any time as a one-shot, idempotent operation. ## Not for direct invocation There is no user-facing slash command and no `cli.cjs <subcommand>` other than `install` / `uninstall`. The skill description's trigger keywords exist purely so the AI surface area knows it is registered — direct invocation has no value.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.