poko8nada/agent-memory
.github/skills/agent-memory/SKILL.md
Core Skill. Save and recall reusable project knowledge across sessions. Result must be in Japanese.
$ install --global
skillsauthnpx skillsauth add poko8nada/pj_docs agent-memoryInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 9:46 PM2.3s1 file scanned
SKILL.md
- name:
- agent-memory
- description:
- Core Skill. Save and recall reusable project knowledge across sessions. Result must be in Japanese.
Agent Memory Skill
A lightweight persistent memory workflow for this repository.
Location
- Memory root:
.github/skills/agent-memory/memories/
When to use
Use this skill when the user asks to:
- remember / save / note something
- recall past decisions or findings
- organize or clean previous notes
Also use proactively when you find knowledge worth preserving:
- non-obvious decisions and rationale
- tricky fixes and gotchas
- research findings that took effort
- resumable in-progress context
Privacy rule for this project
- Treat
bio/as sensitive. - Save only the minimum necessary summary.
- Do not copy raw personal details unless explicitly requested.
File format
Store each memory as Markdown with frontmatter:
---
summary: "1-2 lines: what this memory contains and why it matters"
created: 2026-02-16
updated: 2026-02-16
status: in-progress # in-progress | pending | archived
tags: [strategy]
related: [source/trend/trend.md]
---
summary and created are required.
Suggested structure
memories/
├── project-context/
├── trend/
├── strategy/
└── content-ops/
Use kebab-case for folder/file names.
Search workflow
# list summaries quickly
rg "^summary:" .github/skills/agent-memory/memories/ --no-ignore --hidden
# filter by keyword
rg "^summary:.*keyword" .github/skills/agent-memory/memories/ --no-ignore --hidden -i
# filter by tags
rg "^tags:.*keyword" .github/skills/agent-memory/memories/ --no-ignore --hidden -i
Quality guidelines
- Write for future resumption (context, state, next step).
- Keep summaries decisive.
- Update stale notes or remove obsolete ones.
Related Skills
poko8nada/planning-project
tools
VerifiedTrustedCommunity
Composite Skill. This skill is used for project planning. Users request that a project plan be created, particularly during the initial stages.
1SKILL.mdUpdated Apr 16, 2026
poko8nada/planning-doc-creation
documentation
VerifiedTrustedCommunity
Core Skill. This skill is for document creation. User ask you to create planning documents, such as requirement and task breakdown.
1SKILL.mdUpdated Apr 16, 2026
poko8nada/nextjs-architecture
development
VerifiedTrustedCommunity
Core Skill. Next.js 15+ App Router architecture guidelines including component patterns, state management with Zustand, server actions, and project structure. Use when developing Next.js applications.
1SKILL.mdUpdated Apr 16, 2026
poko8nada/honox-architecture
development
VerifiedTrustedCommunity
Core Skill. HonoX architecture guidelines including file-based routing, Islands pattern, component types, performance optimization, and best practices for full-stack development.
1SKILL.mdUpdated Apr 16, 2026