Menu
O SkillsMP coletou 13 skills de kimasplund/clawdbot-skills-pack. Abra uma skill para revisar a origem e os detalhes.
Mostrando 13 de 13 skills coletadas.
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…
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
Display QAVR (Q-Value Augmented Vector Retrieval) system status including mode, interaction counts, top memories by Q-value, and configuration.
Idioma do texto original: inglês
Enables continuous self-improvement through learning from failures, user corrections, and capability gaps. Integrates with QAVR for learned memory ranking.
Idioma do texto original: inglês
Stress-test solutions using the STRIKE framework. Systematically attack proposals to find weaknesses before deployment.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
Diagnostic reasoning for finding root causes. Generates multiple hypotheses, designs tests to eliminate each, and converges on the true cause through evidence.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
Systematic evaluation methodology for finding THE best solution among known options. Explores multiple reasoning paths, scores branches, and prunes low-confidence paths.
Idioma do texto original: inglês
Periodic "sleep-like" memory optimization. Detects patterns, resolves conflicts, applies decay, and transfers knowledge across contexts.
Idioma do texto original: inglês
Q-Value Augmented Vector Retrieval for learned memory ranking. Tracks which memories are most useful over time and prioritizes them in retrieval.
Idioma do texto original: inglês
Pre-implementation validation requiring ≥90% confidence before coding. Prevents wrong-direction work by assessing duplicates, architecture alignment, and root cause understanding.
Idioma do texto original: inglês
Security assessment using STRIDE threat modeling, OWASP Top 10, and CVSS scoring. Use for security reviews, threat modeling, and secure coding guidance.
Idioma do texto original: inglês