9 skills found
自动捕获经验并安全进化的技能。触发条件：(1)命令/操作失败时→记ERRORS.md (2)被用户纠正('不对'/'应该是')时→记LEARNINGS.md (3)用户需要不存在的能力时→记FEATURE_REQUESTS.md (4)外部API/工具出错时→记ERRORS.md (5)发现自己知识过时/错误时→记LEARNINGS.md (6)发现更好做法时→记LEARNINGS.md (7)每个任务完成时→回顾过程，有新经验则记LEARNINGS.md。去重原则：如果没有新经验或已有条目已覆盖则跳过不写。每次写入同时在.learnings/CHANGELOG.md追加JSONL日志。经验反复出现≥3次时晋升到AGENTS.md/TOOLS.md/SOUL.md。详见正文。
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. Communicates with EvoMap Hub via local Proxy mailbox.
dontbesilent 执行力诊断。用阿德勒心理学框架诊断你「知道该做什么但就是不做」的真正原因。 触发方式：/dbs-action、/action、「我知道该怎么做但就是不做」「为什么我总是拖延」 Execution block diagnosis using Adlerian psychology framework. Trigger: /dbs-action, "I know what to do but can't do it", "why do I procrastinate"
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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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.
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞
Initial project setup for goal coaching system. Use when user says "set up my project", "configure my coaching project", "initialize my goals", or when starting a fresh coaching project with no existing Project-Goals.md. Guides user through conversational setup (one question at a time), generates Project-Goals.md artifact, and introduces daily/weekly workflow trigger phrases.
Track progress toward 3-year, yearly, monthly, and weekly goals. Calculate completion percentages, surface stalled goals, connect daily tasks to objectives. Use for goal reviews and progress tracking.
Self-improving skill system for Makepad development. Features self-evolution (accumulate knowledge), self-correction (fix errors automatically), self-validation (verify accuracy), usage feedback (track pattern health), version adaptation (multi-branch support), and personalization (adapt to project style).
