dojo.md
University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning req...
General-purpose self-healing loop that learns from past failures, retries safely, and records reusable fixes.
请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求,再添加到工作流。
SkillHub CLI
skillhub install dalomeve/memory-self-heal打开来源仓库,查看说明和兼容环境后,按来源提供的命令或步骤安装。
将来源链接提供给你的 Agent,让它先读取说明、核对依赖,并向你说明将执行的安装步骤。
Use this skill when the agent starts failing repeatedly, stalls, or keeps asking the user for steps that could be inferred from prior evidence.
Trigger when any of these appear:
Scan these in order; skip missing paths silently:
memory/ (or equivalent workspace memory path)tasks/ or queue filesskills/*/SKILL.md) for known fallback recipesTOOLS.md, CAPABILITIES.md, AGENTS.md)Shell examples (use whichever shell is active):
# PowerShell
Get-ChildItem -Recurse memory, tasks -ErrorAction SilentlyContinue |
Select-String -Pattern "error|blocked|retry|fallback|auth|token|proxy|timeout|context" -Context 2
# POSIX shell
rg -n "error|blocked|retry|fallback|auth|token|proxy|timeout|context" memory tasks 2>/dev/null
Classify first, then act:
syntax_or_args: command syntax/argument mismatchauth_or_config: key/token/env/config missing or invalidnetwork_or_reachability: timeout, DNS, handshake, region restrictionsui_login_wall: page requires manual login/attachresource_limit: context window, rate limit, memory pressurefalse_done: no artifact/evidence but reported completeunknown: no confident class这些信息来自收录时的来源分析,可能滞后;使用前请核对最新来源文件。
# Memory Self-Heal Skill Use this skill when the agent starts failing repeatedly, stalls, or keeps asking the user for steps that could be inferred from prior evidence. ## Goals 1. Recover execution without user micromanagement 2. Reuse previous fixes from memory/logs/tasks 3. Escalate only with minimal unblock input when truly blocked 4. Leave reusable evidence for future runs ## When To Trigger Trigger when any of these appear: - Same or similar error occurs 2+ times in one task - Tool call fails due to argument mismatch, missing config, auth wall, or context overflow - Agent claims completion without verifiable artifact - Task progress stalls (no new artifact across 2 cycles) ## Inputs - Current task objective - Latest error/output - Available evidence locations (memory, tasks, logs) ## Portable Evidence Scan Order Scan these in order; skip missing paths silently: 1. `memory/` (or equivalent workspace memory path) 2. `tasks/` or queue files 3. runtime logs / channel logs 4. skill docs (`skills/*/SKILL.md`) for known fallback recipes 5. core docs (`TOOLS.md`, `CAPABILITIES.md`, `AGENTS.md`) Shell examples (use whichever shell is active): ```powershell # PowerShell Get-ChildItem -Recurse memory, tasks -ErrorAction SilentlyContinue | Select-String -Pattern "error|blocked|retry|fallback|auth|token|proxy|timeout|context" -Context 2 ``` ```bash # POSIX shell rg -n "error|blocked|retry|fallback|auth|token|proxy|timeout|context" memory tasks 2>/dev/null ``` ## Failure Classification Classify first, then act: - `syntax_or_args`: command syntax/argument mismatch - `auth_or_config`: key/token/env/config missing or invalid - `network_or_reachability`: timeout, DNS, handshake, region restrictions - `ui_login_wall`: page requires manual login/attach - `resource_limit`: context window, rate limit, memory pressure - `false_done`: no artifact/evidence but reported complete - `unknown`: no confident class ## Recovery Policy (3-Tier) ### Attempt 1: Direct Fix - Ap...
University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning req...
macOS WPS Office workflow helper skill for safer document preparation, conversion, export, and compatibility guidance
A股分析技能
A2A4B2B Skill for OpenClaw