Loading...
Loading...
Found 34 Skills
Encodes a continuous improvement loop for goal-seeking agents: EVAL, ANALYZE, RESEARCH (hypothesis + evidence + counter-arguments), IMPROVE, RE-EVAL, DECIDE. Auto-commits improvements (+2% net, no regression >5%) and reverts failures. Works with all 4 SDK implementations. Auto-activates on "improve agent", "self-improving loop", "agent eval loop", "benchmark agents", "run improvement cycle".
Meta-skill for making the agent self-improving. Covers updating AGENTS.md, creating new skills from repeated workflows, and deciding what to systematize. Invoke after completing tasks, when noticing repeated friction, or at session end.
Load this skill immediately when the user expresses any intent. System capabilities (tools/knowledge/scripts) live inside the plugin and are maintained through plugin updates. User data must live at project-level `.claude/pensieve/` and is never overwritten by the plugin. When the user asks to improve Pensieve system behavior (plugin content), you must use the Self-Improve tool (`tools/self-improve/_self-improve.md`).
Self-improve AI Factory skills based on project context, accumulated patches, and codebase patterns. Analyzes what went wrong, what works, and enhances skills to prevent future issues. Use when you want to make AI smarter for your project.
Use when the system needs to track its own effectiveness, learn from errors, adapt workflows, and continuously improve performance - activates automatically every session to collect metrics, classify errors, recognize patterns, and implement evidence-based workflow improvements
Loaded by blazor-architect when --self-improve is active. Not user-invokable — appears in the skills list but can only be loaded by blazor-architect, not called directly. Handles improvement report generation, C# server auto-launch, and CLI staging.
Route a full Blazor work request across the appropriate specialist lane(s). Use when the request spans more than one concern (authoring, data, auth, review) or when lane selection itself is uncertain. Triggers on full-request phrasing: "implement this feature", "review and refactor this page", "build this form end-to-end". Distinct from blazor-component-architect (user-level, external, single-lane authoring guidance that may be invoked as a specialist resource).
Gain wisdom from setbacks — Go through the 5-step interactive reflection (Setback → Automatic Output → Old Weights → New Parameters → Alternative Action), move from "emotional review" to "behavioral training", and update the L3 weights of your first reactions. Use when Wang Jianshuo reflects on a personal setback, mistake, or recurring pattern (reflection, post-mortem review, review, draw lessons, learn from a setback, gain wisdom, "I messed up again", "Why does this keep happening?", "Why do I always…?", "I can't just let it go", "I know the principles but can't put them into practice"). For the user as a human, not for Claude's task post-mortems.
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.
botlearn Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.