self-learning-code-intelligence

name	self-learning-code-intelligence
description	Use when working inside D:\skills\codex\LLMWIKI and the task involves project-local learning, self-improvement, correction, code understanding, knowledge-base updates, LLM Wiki, GitNexus, Graphify, or preventing cross-project contamination.

Self Learning Code Intelligence

Core Rule

Treat this repository as a closed learning system. Capture useful interaction facts into project-local sources, query code intelligence before risky changes, refresh graph indexes after changes, and keep all generated memory inside this repository unless the user explicitly asks to export it.

Automatic Loop

1. Start with project-local context:
   • Run npm run graphify -- query "<task/question>" when graphify-out/graph.json exists.
   • Run npm run gitnexus:status; if stale, run npm run gitnexus:analyze.
   • Read AGENTS.md, docs/OPERATING_MODEL.md, or knowledge/README.md only when the task touches project boundaries or learning behavior.
2. During the task, prefer project-local wrappers:
   • LLM Wiki: npm run llmwiki -- <args>
   • GitNexus: npm run gitnexus:analyze, npm run gitnexus:status
   • Graphify: npm run graphify -- <args>
   • Imported global digest: npm run digest:imported
   • Obsidian inbox: npm run obsidian:sync
   • Obsidian intelligence publish: npm run obsidian:publish-intelligence
   • One-click digestion: npm run learn:all
   • Health check: npm run doctor
3. After meaningful work, capture the learning:
   • Run powershell -NoProfile -ExecutionPolicy Bypass -File skills/self-learning-code-intelligence/scripts/capture-learning.ps1 -Title "<short title>" -Summary "<what changed or was learned>"
   • Include decisions, corrections, and open questions when useful.
4. Refresh local intelligence:
   • Run npm run gitnexus:analyze
   • Run npm run graphify -- update .
   • Run npm run llmwiki:status
   • Run npm run llmwiki -- compile --review --lang zh-CN only when LLM Wiki provider credentials are available or the user asked for compilation.
   • For broad automatic ingestion or routine learning refreshes, prefer npm run learn:all so Obsidian, imported digests, LLM Wiki review, GitNexus, Graphify, Obsidian intelligence publishing, and learning capture stay in one closed loop.

Tool Roles

Tool	Use for	Writes
LLM Wiki	Persistent project knowledge, decisions, summaries, Q&A, reviewable compiled wiki	sources/, .llmwiki/, wiki/
GitNexus	Code dependency graph, impact analysis, stale-index detection, refactor safety	.gitnexus/
Graphify	Fast task-oriented graph query, project map, post-change graph refresh	graphify-out/, .codex/hooks.json
Obsidian	Human-facing inbox and project intelligence mirror for notes, graph reports, and status summaries	sources/obsidian-inbox/, Obsidian LLMWIKI/project-intelligence/

Capture Quality

Write source notes as facts and operational rules, not chat transcripts. Include:

• user intent and exact acceptance boundary,
• commands or tools that worked,
• commands or assumptions that failed,
• project-local decisions,
• portability or isolation implications,
• next trigger that should cause this skill to be used.

Isolation Rules

• Do not write global Codex, Claude, Cursor, or MCP config by default.
• Do not import memories or skills from other workspaces unless the user asks.
• When global project assets are imported under project-imports/global-new-project/, treat them as references and candidate skills. Prefer LLMWIKI-local skills, memory, .env, and AGENTS.md rules.
• Before using an imported global skill, read docs/IMPORTED_GLOBAL_DIGEST.md or the digest sources under sources/imported-global-new-project/digests/. Promote imported skills into the main skills/ directory only on explicit request or repeated local use.
• Do not run Graphify --global, GitNexus global setup, or plugin global installers unless explicitly requested.
• Keep API keys in project .env; never hardcode them in sources or skill files.
• Import only the Obsidian LLMWIKI inbox by default; do not scan the whole vault unless explicitly requested.
• Generated state is rebuildable. Portable logic belongs in tools/, skills/, knowledge/, and docs/.

Common Mistakes

Mistake	Correction
Answering from memory without updating local sources	Capture a compact source note before finishing
Running global setup because a tool suggests it	Use project-local wrappers and document any exception
Rebuilding Graphify but not GitNexus	Refresh both after code or workflow changes
Compiling LLM Wiki without credentials	Save sources first, then leave compile in review for later
Mixing unrelated project experience into this repo	Mark it as external or keep it out
Letting imported global skills override local rules	Use imported skills as references until explicitly promoted

References

• Read references/tool-contracts.md when choosing which tool to call.
• Use scripts/capture-learning.ps1 for deterministic learning capture.