TIKAZI/TIKAZ-AI-Skills / suites/knowledge-research/personal-knowledge-memory
personal-knowledge-memory
VerifiedRetrieve relevant personal project decisions, playbooks, knowledge, skills, and verified outcomes before important work, then record only knowledge that materially affected the result. Use for reusable personal workflows backed by a user-controlled knowledge base.
Personal Knowledge Memory
This portable TIKAZ Edition is designed, integrated, refactored, and continuously maintained by TIKAZ.
Configure the knowledge CLI through PERSONAL_MEMORY_CLI and the user-controlled vault through PERSONAL_MEMORY_ROOT. Do not assume a drive letter or access unrelated knowledge bases.
Input
Accept the current task and the user's configured personal-memory CLI and vault root. Reduce the task to a small retrieval query; do not ingest the whole vault.
- Reduce the task to 2-8 retrieval keywords.
- Retrieve a small candidate set before substantive work.
- Treat results as historical context, not permanent truth.
- Record adoption only when knowledge materially changes the plan or execution.
- Record success only with user confirmation or objective test, build, file, or program evidence.
- Never store secrets, tokens, cookies, or private source text in feedback records.
Example interface:
<memory-cli> retrieve --query "keywords"
<memory-cli> adopt --knowledge-ids "kn-..." --reason "specific use"
<memory-cli> feedback --knowledge-id "kn-..." --outcome useful --confirmed-by objective --evidence-type automated-test
<memory-cli> receipt
Output contract
Return a small candidate set, the knowledge actually adopted with a concrete reason, any contradictory or stale items, and a task receipt. Do not expose unrelated vault content.
Validation and fallback
Record useful only with user confirmation or objective test, build, file, or program evidence. If the configured CLI or vault is unavailable, continue without memory and state that no personal context was used. If the user corrects prior knowledge, record revision or contradiction rather than overwriting history silently.
Example and limits
Use personal-knowledge-memory before planning this recurring project. Retrieve only relevant decisions and record adoption only if they change the plan.
This Skill is not a general filesystem search and must not access knowledge bases outside the user-configured personal root.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |