跳到正文
cccskills
免费在 GitHub 公开

observe-before-editing

Investigate bugs by checking generated files, directories, logs, and the actual output of a failing command before editing code. The workflow also checks project and global paths to help distinguish missing output from looking in the wrong location.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Observe Before Editing

parcadei/Continuous-Claude-v3
查看安装方法

适用场景

  • Checking whether a hook actually ran
  • Investigating missing generated files
  • Comparing project and global cache locations
  • Reproducing an error before changing code

包含的文件（1）

  • SKILL.md1.0 KB

SKILL.md（原文）

安装前可以查看交给 AI 代理的指令内容。

Observe Before Editing

Before editing code to fix a bug, confirm what the system actually produced.

Pattern

Outputs don't lie. Code might. Check outputs first.

DO

  1. Check if expected directories exist: ls -la .claude/cache/
  2. Check if expected files were created: ls -la .claude/cache/learnings/
  3. Check logs for errors: tail .claude/cache/*.log
  4. Run the failing command manually to see actual error
  5. Only then edit code

DON'T

  • Assume "hook didn't run" without checking outputs
  • Edit code based on what you think should happen
  • Confuse global vs project paths (check both: .claude/ and ~/.claude/)

Source Sessions

  • a541f08a: Token limit error was invisible until manual run revealed it
  • 6a9f2d7a: Looked in wrong cache path (~/.claude/ vs .claude/), assumed hook failure
  • a8bd5cea: Confirmed hook worked by finding output files in project cache
  • 1c21e6c8: Verified Artifact Index indexing by checking DB file exists

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护，适用 Google 的隐私权政策和服务条款。

同一仓库的技能

agent-context-isolation

免费

Coordinate background agents through saved files, keeping lengthy work transcripts out of the main conversation. It defines how to pass results between agents, monitor progress, and verify completed work with tests.

中文简介正在准备中。当前显示英语简介。

  • Keeping long agent transcripts out of the main conversation
  • Passing research and plans between agents through files
  • Checking for stalled background agents
parcadei/Continuous-Claude-v339462026年1月27日 更新

agent-orchestration

免费

Delegate implementation, file reading, and testing to separate agents, then bring concise summaries back to the main conversation. The rules explain when delegation helps and when a small edit is better handled directly.

中文简介正在准备中。当前显示英语简介。

  • Implementing a feature across multiple files
  • Completing a specific phase of an implementation plan
  • Delegating feature development and testing
parcadei/Continuous-Claude-v339462026年1月27日 更新

agentic-workflow

免费

Organize implementation work across research, planning, validation, implementation, and review agents. Each stage passes files to the next, while implementation starts with failing tests and the main conversation coordinates the workflow.

中文简介正在准备中。当前显示英语简介。

  • Dividing implementation work among specialized agents
  • Checking a plan against research before implementation
  • Writing failing tests before implementing changes
parcadei/Continuous-Claude-v339462026年1月27日 更新

agentica-claude-proxy

免费

Connect Agentica SDK agents to Claude Code CLI through a proxy, an intermediary server. Use setup and debugging guidance to address file permissions, streamed responses, result formatting, and agents reporting success without performing the requested operations.

中文简介正在准备中。当前显示英语简介。

  • Connecting Agentica agents to Claude Code tools
  • Investigating file write and edit permission errors
  • Debugging streaming and REPL response formats
parcadei/Continuous-Claude-v339462026年1月27日 更新

agentica-infrastructure

免费

Consult Agentica APIs when building workflows where multiple AI agents cooperate. This reference covers eleven coordination patterns, agent tracking, shared state, handoffs, and ways to combine results, with pointers to detailed API specifications.

中文简介正在准备中。当前显示英语简介。

  • Choose a coordination pattern for multiple agents
  • Check pattern constructors and methods
  • Implement custom coordination patterns
parcadei/Continuous-Claude-v339462026年1月27日 更新

agentica-prompts

免费

Write clearer instructions for Agentica and REPL agents by specifying roles, file operations, and output formats. Includes templates for dividing research, coordinating specialists, reviewing solutions, and passing results between agents through files.

中文简介正在准备中。当前显示英语简介。

  • Clarifying instructions for reading and editing files
  • Dividing research among multiple agents
  • Passing findings and plans between agents
parcadei/Continuous-Claude-v339462026年1月27日 更新

查看 parcadei 的全部技能

报告此技能的问题