micahcourey/mnemix-memory-judgment
examples/agent-memory-layer/mnemix-memory-judgment/SKILL.md
Use this skill when a repository uses Mnemix as a local memory layer and the agent needs to decide when to recall prior context or write back durable project knowledge. Helps with selective memory use for coding agents, project conventions, architecture decisions, reusable procedures, and avoiding noisy low-value memory writes.
$ install --global
skillsauthnpx skillsauth add micahcourey/temporal-plane mnemix-memory-judgmentInstall 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 7, 2026, 8:37 AM5.5s2 files scanned
SKILL.md
- name:
- mnemix-memory-judgment
- description:
- Use this skill when a repository uses Mnemix as a local memory layer and the agent needs to decide when to recall prior context or write back durable project knowledge. Helps with selective memory use for coding agents, project conventions, architecture decisions, reusable procedures, and avoiding noisy low-value memory writes.
- license:
- Apache-2.0
- author:
- mnemix
- version:
- 0.1
Mnemix Memory Judgment
Use this skill when working in a repository that treats Mnemix as selective project memory rather than a task log.
Workflow
- Classify the task as trivial or non-trivial.
- For non-trivial work, recall memory for the repository scope and task topic.
- Prefer pinned context and summaries before loading broader archival context.
- Complete the task using recalled context only when it materially affects the work.
- At the end, decide whether the task produced durable knowledge worth storing.
- Write back only durable facts, decisions, procedures, preferences, or repeated pitfalls.
- Skip writeback when the outcome is transient, obvious from the code, or low-signal.
Recall Guidance
Recall is usually appropriate when the task:
- spans multiple steps or files
- touches architecture, conventions, or recurring workflows
- is likely to repeat later
- has prior decisions or pitfalls that could change the implementation
For trivial edits, recall is optional unless the user explicitly asks for memory usage.
Writeback Guidance
Prefer one compact memory over several noisy ones.
Write a memory only if a future agent would benefit from knowing:
- what decision was already made
- what procedure should be reused
- what preference should be preserved
- what mistake should be avoided
Do not store:
- raw transcripts
- command-by-command activity logs
- temporary debugging notes
- speculative ideas that were not adopted
- summaries that are already obvious from the final code or docs
Resources
See the reference guide for:
- a more explicit decision rubric
- good and bad memory examples
- suggested recall and writeback prompts
Related Skills
steipete/skill-creator
testing
VerifiedTrustedCommunity
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
356,423SKILL.mdUpdated Apr 13, 2026
steipete/healthcheck
testing
VerifiedTrustedCommunity
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
356,423SKILL.mdUpdated Apr 13, 2026
openclaw/skill-creator
testing
VerifiedTrustedCommunity
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
353,662SKILL.mdUpdated Apr 10, 2026
openclaw/healthcheck
testing
VerifiedTrustedCommunity
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
353,662SKILL.mdUpdated Apr 10, 2026