菜单
Use this skill when the repo is an llm-wiki-memory vault and the task is to ingest a source, answer from the persistent wiki, create or review reusable skills, use pk-qmd for repo-local evidence retrieval, consult brv for durable memory, or lint and maintain the wiki.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when the user wants the KADE System itself, including Layer 1 and Layer 2 context loading, KADE session structure, HUMAN.md and kade/ overlays, or project initialization and handoff workflows. This packet-owned wrapper is installable into ~/.agents/skills, ~/.codex/skills, and ~/.claude/skills.
Use when the task should consult, capture, validate, evolve, or retire reusable workflow shortcuts through the local `llm-wiki-skills` skill/CLI surface. MCP is optional transport only. This packet-owned wrapper explains the full tool lifecycle in depth and is installable into ~/.agents/skills, ~/.codex/skills, ~/.claude/skills, and ~/.pi/agent/skills.
Repo-local harness for evaluating agents, classifying failures, validating regressions, and producing review artifacts.
Use the repo-local harness to benchmark Gym-Anything-compatible agents, cluster failures, and generate human-gated improvement proposals.
Run the repo-local harness to evaluate agents, classify failures, propose human-gated improvements, validate regressions, and generate review packets.
Use when the user wants the KADE plus gstack bridge, including session kickoff with user-profile context, /g-kade install style project scaffolding, repo adaptation, or structured handoff logging tied to llm-wiki-memory packet setup. This packet-owned wrapper is installable into ~/.agents/skills, ~/.codex/skills, and ~/.claude/skills.
| name | llm-wiki-organizer |
| description | Use this skill when the repo is an llm-wiki-memory vault and the task is to ingest a source, answer from the persistent wiki, create or review reusable skills, use pk-qmd for repo-local evidence retrieval, consult brv for durable memory, or lint and maintain the wiki. |
This skill helps maintain a persistent markdown wiki backed by an explicit retrieval and memory stack.
AGENTS.md.LLM_WIKI_MEMORY.md if present.SKILL_CREATION_AT_EXPERT_LEVEL.md if present when the task touches skill creation, feedback, or retirement..llm-wiki/config.json if present.pk-qmd, brv, or GitVizz are not ready, run scripts/setup_llm_wiki_memory.ps1 or scripts/setup_llm_wiki_memory.sh before substantive work.wiki/index.md.wiki/log.md.pk-qmd is the default evidence lookup tool for repo-specific work.pk-qmd first for difficult searches when the target repo area is not known yet.pk-qmd first for prior skill lookup when the right skill page is not yet known.brv is for durable preferences, prior decisions, and costly rediscoveries.GitVizz is the local graph and web surface.GitVizz to inspect repo topology, API routes, dependency context, and to narrow in once pk-qmd has located the relevant area.wiki/skills/active/.wiki/skills/feedback/.wiki/skills/retired/..llm-wiki/skill-pipeline/.wiki/skills/index.md whenever a skill is added, amended, merged, or retired.-3, retire the skill instead of silently patching history.