dml/SKILL.md
Use DML (Deterministic Memory Layer) to track facts, constraints, and decisions. Invoke when helping with planning tasks, or when the user wants to track information with audit trails.
npx skillsauth add daveremy/deterministic-memory-layer dmlInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You have DML MCP tools available. Use them to track facts, constraints, and decisions.
Facts = raw data, attributes, values
Decisions = choices, confirmations, commitments
Key rule: When the user CHOOSES or CONFIRMS something, record it as a decision, not just a fact update.
Record facts for raw information:
Update facts when values change:
Record constraints for rules:
Record decisions for choices:
User: "My budget is $5000" → add_fact(key="budget", value="5000")
User: "Actually, my budget is only $3000 now" → add_fact(key="budget", value="3000") # Updates existing fact
User: "Planning for 6 guests" → add_fact(key="guest_count", value="6")
User: "Two more people are coming, so 8 total" → add_fact(key="guest_count", value="8") # Updates existing fact
User: "I need wheelchair accessible places" → add_constraint(text="wheelchair accessible required", priority="required")
User: "Let's do April 12-19" → record_decision(text="Travel dates: April 12-19, 2026", rationale="User confirmed dates", topic="dates")
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.