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