원클릭으로
skill-authoring
Use when authoring or maintaining DotCraft workspace skills via SkillManage.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use when authoring or maintaining DotCraft workspace skills via SkillManage.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Create and configure DotCraft lifecycle hooks (hooks.json) for workspaces. Use when the user wants to add hooks, create hook scripts, set up security guards, auto-formatting, logging, notifications, or any shell-based automation triggered by DotCraft agent lifecycle events.
Create and scaffold DotCraft local plugin directories with `.craft-plugin/plugin.json`, plugin-contained skills, optional plugin-bundled MCP server config, optional lifecycle hooks, and optional assets. Use when developing DotCraft plugins or creating a skill/MCP/hooks plugin bundle for `.craft/plugins` or `~/.craft/plugins`.
Find and export DotCraft session, trace, and memory context for external coding agents or DotCraft Doctor troubleshooting. Use when a user needs to locate related sessions from an error, provider message, tool failure, symptom, or thread id, then produce a clean Markdown handoff.
Diagnose DotCraft LLM, agent, tool-call, LiteLLM, provider, context, or session failures by inspecting a workspace's `.craft/state.db` and `.craft/threads/active|archived/*.jsonl` evidence. Use when a user reports that an LLM request failed, an agent turn errored, a thread cannot resume correctly, tool calls behaved unexpectedly, or DotCraft trace/thread persistence needs to be correlated to find the root cause.
Turn a DotCraft failure or diagnosis into a clear, well-structured GitHub issue for the DotHarness/dotcraft repository, and produce a prefilled "new issue" URL the user can review and submit. Use after error-diagnosis (or when a user wants to report a bug), to draft the issue title and body and hand off a ready-to-open link. Does not submit on the user's behalf.
Browser automation for the DotCraft in-app browser. Use to open, navigate, inspect, test, click, type, screenshot, or verify local targets such as localhost, 127.0.0.1, ::1, file://, dotcraft-viewer:, the current app browser tab, and approved http/https pages.
| name | skill-authoring |
| description | Use when authoring or maintaining DotCraft workspace skills via SkillManage. |
| tools | SkillManage |
Skills are procedural memory: reusable, narrow instructions for task types that are likely to recur. Load this skill when you need to create, rewrite, or patch a workspace skill with SkillManage.
Do not create skills for simple one-off answers. A good skill teaches when to use it, what exact steps to follow, what pitfalls to avoid, and how to verify the result.
Use SkillManage when:
Do not use it for:
| Action | Required Parameters | Use For | Example |
|---|---|---|---|
create | name, content | New reusable workspace skill | SkillManage(action: "create", name: "debug-api", content: "<full SKILL.md>") |
patch | name, oldString, newString | Targeted fixes to SKILL.md or a supporting file | SkillManage(action: "patch", name: "debug-api", oldString: "old", newString: "new") |
edit | name, content | Full rewrite after reading the current skill | SkillManage(action: "edit", name: "debug-api", content: "<full updated SKILL.md>") |
write_file | name, filePath, fileContent | Add or replace supporting files | SkillManage(action: "write_file", name: "debug-api", filePath: "scripts/check.sh", fileContent: "...") |
remove_file | name, filePath | Remove a supporting file | SkillManage(action: "remove_file", name: "debug-api", filePath: "assets/example.json") |
delete | name | Remove obsolete or harmful workspace skills, only when enabled | SkillManage(action: "delete", name: "old-skill") |
Prefer patch for small changes. Use edit only for major overhauls after reading the current skill.
Every SKILL.md created through SkillManage must start with YAML frontmatter:
---
name: my-skill
description: One-sentence trigger description
version: 0.1.0
---
Rules:
--- with no leading whitespace.name must match the name parameter.description should describe the trigger class, not the current task.Use this structure unless a skill has a strong reason to differ:
# Title
## Overview
What this skill is for and why it exists.
## When To Use
- Concrete trigger conditions.
- Counter-triggers if useful.
## Workflow
1. Exact steps, commands, files, APIs, or checks.
2. Keep steps specific enough to execute later.
## Common Pitfalls
- Known mistakes and fixes.
## Verification
- How to confirm the workflow succeeded.
Supporting files must stay inside the skill directory under one of:
scripts/ for helper scripts.assets/ for static assets.Use write_file for supporting files. Use patch with filePath for targeted edits to supporting files. Absolute paths and .. traversal are rejected.
SkillManage enforces size limits for SKILL.md and supporting files.SKILL.md focused on triggers, workflow, pitfalls, and verification. Put executable helpers in scripts/ and static examples in assets/.edit for a tiny correction. Prefer patch with enough context in oldString.Before finishing, confirm the frontmatter starts at byte 0 and includes name, description, and version; name matches the directory and the SkillManage request; the description explains when to use the skill; the body includes workflow, pitfalls, and verification guidance; supporting files stay under scripts/ or assets/; and the skill is narrow enough to be reused without confusion.