메뉴
SkillsMP는 kimasplund/clawdbot-skills-pack에서 13개의 skill을 수집했습니다. skill을 열어 소스와 세부 정보를 확인하세요.
수집된 skill 13개 중 13개를 표시합니다.
Self-improving agent architecture using ChromaDB for continuous learning, self-evaluation, and improvement storage. Agents maintain separate memory collections for learned patterns, performance metrics, and self-assessments without modifying their static .md…
원문 언어: 영어
Guide for manually creating custom skills from scratch with templates and validation. Use when designing NEW skills with specific requirements. For auto-generating skills from existing git repos, use /generate-skills instead.
원문 언어: 영어
Display QAVR (Q-Value Augmented Vector Retrieval) system status including mode, interaction counts, top memories by Q-value, and configuration.
원문 언어: 영어
Enables continuous self-improvement through learning from failures, user corrections, and capability gaps. Integrates with QAVR for learned memory ranking.
원문 언어: 영어
Stress-test solutions using the STRIKE framework. Systematically attack proposals to find weaknesses before deployment.
원문 언어: 영어
Exhaustive solution space exploration. Use when you need ALL viable options (not just the best), solution space is unknown, or you can't afford to miss alternatives.
원문 언어: 영어
Diagnostic reasoning for finding root causes. Generates multiple hypotheses, designs tests to eliminate each, and converges on the true cause through evidence.
원문 언어: 영어
Meta-orchestrator that selects optimal reasoning patterns based on problem characteristics. Analyzes 11 dimensions and recommends ToT, BoT, SRC, HE, AR, DR, AT, RTR, or NDF patterns.
원문 언어: 영어
Systematic evaluation methodology for finding THE best solution among known options. Explores multiple reasoning paths, scores branches, and prunes low-confidence paths.
원문 언어: 영어
Periodic "sleep-like" memory optimization. Detects patterns, resolves conflicts, applies decay, and transfers knowledge across contexts.
원문 언어: 영어
Q-Value Augmented Vector Retrieval for learned memory ranking. Tracks which memories are most useful over time and prioritizes them in retrieval.
원문 언어: 영어
Pre-implementation validation requiring ≥90% confidence before coding. Prevents wrong-direction work by assessing duplicates, architecture alignment, and root cause understanding.
원문 언어: 영어
Security assessment using STRIDE threat modeling, OWASP Top 10, and CVSS scoring. Use for security reviews, threat modeling, and secure coding guidance.
원문 언어: 영어