Skip to content

po4yka/llm-wiki-skills / skills/llm-wiki-agent-memory-bridge

llm-wiki-agent-memory-bridge

Verified

Decide what belongs in LLM-Wiki versus agent memory, AGENTS.md, CLAUDE.md, Auto Memory, Codex project memory, or other runtime memories. Use when instruction files are bloated, domain facts live in agent memory, or the user wants clean memory boundaries.

LLM-Wiki Agent Memory Bridge

Goal

Separate durable domain knowledge from runtime/project memory so agents load the right context at the right time.

When to use

  • AGENTS.md/CLAUDE.md has grown large because domain facts were pasted into instructions instead of the wiki.
  • A wiki page holds procedural agent prompts that belong in a Skill, not domain knowledge.
  • Agent memory (Auto Memory, Codex project memory) duplicates or has drifted from existing wiki pages.
  • You need to decide where a new piece of knowledge belongs: Skill, instruction file, or wiki.
  • Onboarding a new agent (Claude Code, Codex, Cursor, OpenCode) to a project and need to map its existing memory surfaces first.

Inputs

  • AGENTS.md, CLAUDE.md, project memory files, agent settings.
  • Existing wiki/vault.
  • Target agents: Claude Code, Codex, Cursor, OpenCode, etc.
  • Desired mode: audit, plan, or apply.

Procedure

1. Inventory memory surfaces

Find:

  • instruction files;
  • agent memory files;
  • skills;
  • wiki pages;
  • query logs;
  • project docs;
  • hidden or generated memory directories.

2. Classify memory items

Use this routing:

ContentBest home
stable proceduresAgent Skill
project conventionsAGENTS.md or CLAUDE.md pointer
domain factsLLM-Wiki page with provenance
source-backed claimswiki/sources, wiki/concepts, wiki/entities
user preferencesagent/user memory, not public wiki
temporary task statecurrent session or task log
sensitive factsrestricted wiki or local-only memory

3. Detect bloat and drift

Flag:

  • giant instruction files full of domain knowledge;
  • skills containing volatile facts;
  • agent memory duplicating wiki pages;
  • wiki pages containing procedural prompts;
  • missing pointers from instruction files to wiki index;
  • volatile facts (pricing, release notes, maintenance status) embedded directly in a skill or instruction file instead of a wiki page whose claims get re-verified against fresh sources before reuse.

4. Propose moves

Create a migration table:

| Item | Current location | Proposed home | Reason | Risk |
|---|---|---|---|---|

5. Apply safe pointer pattern

Keep instruction files short. Replace long domain dumps with pointers such as:

For domain knowledge, read `wiki/index.md` first and then relevant linked pages.

Output

## Memory boundary summary

## Memory surfaces found

## Misplaced content

## Proposed moves

## Instruction-file pointer updates

## Risks

Safety gates

  • Do not move user preferences into a shared wiki without approval.
  • Do not delete memory content during migration; archive or link it.
  • Do not hide domain facts in skills.
  • Do not leave instruction files without pointers to the wiki.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall