agent-memory
78Remember Project Context Across Sessions
by yamadashy
Important project details are easy to lose between AI sessions. This skill gives Claude, Codex, and Claude Code a structured local memory workflow.
Personalize AI Conversations With Local Memory
Generic assistants lose context across conversations and notes. This skill uses local personas, notes, logs, and vector search to make Claude, Codex, or Claude Code respond with more personal context.
Do not auto-install this skill.
The canonical policy requires operator review before any installation action.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "ai-partner-chat" from https://skillstore.io/skills/cz07cring-ai-partner-chat.md and its manifest at https://skillstore.io/api/skills/cz07cring-ai-partner-chat/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "ai-partner-chat". What should I study next based on my React notes?
Expected outcome:
A short summary of related React notes, a recommendation for the next concept, and a practice task matched to your learning style.
Using "ai-partner-chat". Remember what we decided about my project direction.
Expected outcome:
A concise memory-style summary of the decision, the reason behind it, and suggested tags for later retrieval.
Using "ai-partner-chat". Why do I keep getting stuck on this topic?
Expected outcome:
A pattern-based reflection that connects recent notes, confusion points, and a practical next action.
The skill intentionally stores notes, profiles, conversation logs, and vector indexes under local Claude skill directories. Most static hits are false positives from markdown code fences, documentation snippets, or local paths, but the package still needs review because it installs scripts, writes local databases, reads cache paths, and documents scoped recursive deletion commands.
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/cz07cring-ai-partner-chat/audits/10?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/cz07cring-ai-partner-chat?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/cz07cring-ai-partner-chat?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/cz07cring-ai-partner-chat/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/cz07cring-ai-partner-chat.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Cz07cring. (2026). ai-partner-chat security audit report (audit version 10) [Author version unspecified]. Skillstore. https://skillstore.io/skills/cz07cring-ai-partner-chat/audits/10@techreport{cz07cring-cz07cring-ai-partner-chat-2026,
author = {Cz07cring},
title = {ai-partner-chat security audit report (audit version 10)},
institution = {Skillstore},
year = {2026},
number = {10},
url = {https://skillstore.io/skills/cz07cring-ai-partner-chat/audits/10},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "ai-partner-chat security audit report (audit version 10)"
version: "unspecified"
type: report
authors:
- name: "Cz07cring"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/cz07cring-ai-partner-chat/audits/10"
identifiers:
- type: other
value: "skillstore:cz07cring-ai-partner-chat:audit:10"
description: "Skillstore immutable audit report identifier"
Use prior notes and reflections to receive responses that match your current learning stage and recurring questions.
Record conversation summaries and retrieve related history when discussing long-running projects or goals.
Find related ideas in local markdown notes without relying only on exact keyword matches.
Use my persona and notes to answer this question in a style that fits my learning preferences: [question].
Search my local notes for ideas related to [topic], then summarize the most relevant themes before answering.
Review this exchange and identify what should be remembered for future conversations: [conversation summary].
Use my notes, prior conversations, tags, and emotion timeline to identify recurring blockers and suggest a focused next step.
Author
Cz07cringLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
7db9b9f06e0ab79c575b58bc48c4d8dc9849f424
Maintenance freshness
7/18/2026
Usage
10 downloads ยท 182 views
File structure
๐ assets/
๐ config/
๐ tags_taxonomy.json
๐ notes/
๐ example-learning.md
๐ scripts/
๐ chunk_schema.py
๐ code_parser.py
๐ emotion_analyzer.py
๐ example_usage.py
๐ note_processor.py
๐ orchestrator.py
๐ requirements.txt
๐ tag_generator.py
๐ tag_indexer.py
๐ thinking_analyzer.py
๐ vector_indexer.py
๐ vector_utils.py
๐ install.sh
๐ README.md
๐ SKILL.md
Remember Project Context Across Sessions
by yamadashy
Important project details are easy to lose between AI sessions. This skill gives Claude, Codex, and Claude Code a structured local memory workflow.
Organize Obsidian Notes with AI
by ZhanlinCui
Obsidian vaults can become hard to review and update consistently. This skill helps Claude and Codex create daily notes, capture ideas, and summarize recent work.
Manage Google Keep Notes with gws
by googleworkspace
Managing Google Keep resources from an AI workflow requires precise CLI commands and API parameters. This skill guides structured note, attachment, and permission operations.
Capture corrections and update your CLAUDE.md memory
by BayramAnnakov
Claude Code forgets your corrections between sessions, so you repeat the same guidance again and again. claude-reflect captures those corrections automatically and lets you review and apply them to your CLAUDE.md memory files with one command.
Aggregate Cross-Task Learning
by Clouder0
Teams lose useful lessons when task reflections stay isolated. This skill aggregates repeated patterns into a compact record for future improvement.
Build Obsidian Bases for Dynamic Notes
by ZhanlinCui
Obsidian Bases can be hard to write correctly by hand. This skill helps create valid views, filters, formulas, and summaries.