build-skill
Create, redesign or merge a skill, grounded in facts, then hand over the test. Started by you.
- License 许可
- MIT
- 最近更新
- 2026-10-26
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- build-skill
- description
- Create, redesign or merge a skill, grounded in facts, then hand over the test. Started by you.
- allowed-tools
- Bash(agentic-maker *) Bash(${CLAUDE_PLUGIN_ROOT}/bin/agentic-maker *) Bash(claude plugin validate *) Read Grep Glob Write Edit
- argument-hint
- <what the skill should do | path of a skill to redesign>
- disable-model-invocation
- true
02 资源文件 13
- 参考文档agents/openai.yaml256 B
- 参考文档references/anti-patterns-content.md4.9 KB
- 参考文档references/anti-patterns-process.md5.7 KB
- 参考文档references/checklist.md6.2 KB
- 参考文档references/frontmatter.md5.8 KB
- 参考文档references/instruction-strength.md6.3 KB
- 参考文档references/naming-and-boundaries.md6.0 KB
- 参考文档references/references-and-scripts.md6.8 KB
- 参考文档references/test-with-fresh-agents.md6.7 KB
- 参考文档references/troubleshooting.md6.8 KB
- 参考文档references/worked-examples.md4.5 KB
- 参考文档references/workflow-patterns.md5.7 KB
- 参考文档references/wrapping-mcp-tools.md5.9 KB
03 SKILL.md 正文
Build a skill
In Codex:
$ARGUMENTSis what the user wrote after the skill name.${CLAUDE_PLUGIN_ROOT}and${CLAUDE_SKILL_DIR}mean the plugin folder and this skill's folder (the plugin folder is two levels above this file);agentic-makeris on PATH or is<plugin folder>/bin/agentic-maker. A line that starts with an exclamation mark and a backtick is a command: run it yourself first.
Request: $ARGUMENTS
Pages are in ${CLAUDE_SKILL_DIR}/references/ (listed at the end); the two skill pages in the knowledge base are ${CLAUDE_PLUGIN_ROOT}/skills/agent-interface-design/references/skill/. Open a page when the step names it, not before. This runs in the main conversation, so ask the user directly, and only what changes the result.
Pick the mode
| The request is | Do |
|---|---|
| a new skill | steps 1-7 |
| an existing skill to redesign (a path, relative to the current working directory, not to the plugin) | ls that path in the current directory and read it first. If the user has derail findings for it, read them; they say how it fails today. Then steps 3-7 |
| several skills or sources to merge | step 2 builds a comparison table (what to inherit, what to drop, why) before any text is written. Every command, flag and path comes verbatim from a source; one found in no source goes in the report as a suggested addition, not in the skill |
| "turn this conversation into a skill" | list what was done as a nested outline, five levels at most: milestone, phase, step, error met and its correction, invariant learned. Corrections and invariants become the skill's rules; repeated commands become scripts. Then steps 2-7 |
Steps
- Scope. Who invokes it (the model on a matching request, or only the user), in which harnesses it must run, and one sentence for what changes for the agent when it is loaded. naming-and-boundaries.md if one skill or two.
- Ground it. For any non-trivial domain, gather verified facts first: the official docs, the real command output, the API as it is today. If the
researchplugin is installed use/research:ask(one question) or/research:deep(five or more sources); otherwise use whatever web and file tools you have. A skill drafted from memory carries the model's guesses into every future run; if you can verify nothing, say so and stop. Look at two or three existing skills for the same job and note what each does well. - Lay it out before writing. What stays in
SKILL.md(under 500 lines), what goes toreferences/, what becomes a script: references-and-scripts.md. Pick the body's shape: workflow-patterns.md. Show the layout to the user when the request was open-ended. - Write it.
- Frontmatter: frontmatter.md. Portable fields only if it must run outside Claude Code.
- Description: it is the only thing the model sees when deciding to load the skill. descriptions-that-trigger.md.
- Body: exact paths and commands, numbers instead of adjectives, a check on every phase, using only commands and flags that appear in the sources from step 2: text-as-program.md. How strict each step should be: instruction-strength.md.
- A skill that drives MCP tools: wrapping-mcp-tools.md.
- Check what a script can check. Run each check as its own Bash call, with no
&&,;or heredoc:claude plugin validate <skill dir>(frontmatter and structure),wc -l <skill dir>/SKILL.md, every bundled script on real input. A denied call skips only that check: redo it with Read, Grep or Glob (frontmatter fields, line count, each link and path) and name the denied command in the report. Then open checklist.md and build a table with one row per line, marked checked or unchecked. - Hand over the test. Only the user can start
/agentic-maker:derail; you cannot, so do not try. Write three scenarios into.agentic-maker/scenarios/<name>.md(format in${CLAUDE_PLUGIN_ROOT}/skills/derail/references/scenarios.md): a normal request in the user's words that never names the skill, an ambiguous one, and one with a missing input; each with receipts that check the disk, not the agent's words. Preview one withagentic-maker run <name> --dry-run. End by giving the user the exact command,/agentic-maker:derail <skill dir>. Until they run it the skill is untested, and your report says so. Procedure and what a pass looks like: test-with-fresh-agents.md. A skill only the user can start is tested through a slash-command prompt; the derail dry-run says so. - Ship. The final message is the checklist table from step 5: one row per line of checklist.md, marked checked (with the command and its output, or the file and line you read) or unchecked. A message without that table is not a ship.
Do this, not that
| Do | Not |
|---|---|
| Verify every API, flag and path against the real thing | Write them from memory |
| Fix the sentence that misled the agent | Add a "never do X" rule next to it |
Keep SKILL.md as the routing and the rules; move bulk to references |
Paste a 1,500-line guide into one file |
| Write scripts in Python or Node and run them before you ship | Ship a script you never ran |
| Report what you could not verify | Present a guess as a fact |
Pages
| Open | When |
|---|---|
| frontmatter.md | writing or fixing frontmatter |
| naming-and-boundaries.md | naming it, splitting or merging |
| references-and-scripts.md | deciding what goes where |
| workflow-patterns.md | choosing the structure of the body |
| instruction-strength.md | a step is too loose or too rigid |
| wrapping-mcp-tools.md | the skill calls MCP tools |
| test-with-fresh-agents.md | step 6 |
| checklist.md | before shipping |
| troubleshooting.md | it does not load, trigger or behave |
| anti-patterns-content.md, anti-patterns-process.md | reviewing a draft or your own process |
| worked-examples.md | you want a structure to copy |
04 同仓库更多 Skills
design
暂无简介
derailment-method
暂无简介
targets
暂无简介
derail
Test a skill, plugin, CLI or MCP tool with fresh agents and fix the text that misled them. Started by you; spends usage.
build-mcp
Build, extend or repair an MCP server for agents, probe it, hand over the test. Started by you.
build-cli
Build or repair an agent-facing CLI, probe it, hand over the test. Started by you.