一键导入
create-skills
ALWAYS invoke this skill when creating, editing, or improving SKILL.md files.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
ALWAYS invoke this skill when creating, editing, or improving SKILL.md files.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | create-skills |
| description | ALWAYS invoke this skill when creating, editing, or improving SKILL.md files. |
Invoke the instructions:skill-standards skill before proceeding. If that skill is unavailable, report the missing skill and continue with the closest available workflow.
Invoke the instructions:agent-prompt-standards skill before proceeding. If that skill is unavailable, report the missing skill and continue with the closest available workflow.
<reference_loading>
Before creating, editing, or auditing any skill, read /skill-standards — the single source of truth for all skill standards (frontmatter, XML structure, naming, progressive disclosure, skill types, reference patterns, code-fence rules, bash restrictions, validation, script testing). Then check for spx/local/skills.md at the repository root and read it if it exists.
Also read /agent-prompt-standards for voice, description style, constraint language, and anti-pattern conventions before writing prompt text.
When the skill takes arguments, injects state-dependent context, restricts tools, or references files — the capabilities a slash command also carried — follow the command-capability rules /skill-standards carries (its <frontmatter> points to the command-capabilities reference) for argument-hint/arguments, !-dynamic-context, allowed-tools-security, and @-file references before authoring that surface.
This skill provides routing, workflows, templates, and domain-workflow references for creating skills. It does not restate standards. </reference_loading>
What would you like to do?Wait for response before proceeding.
| Response | Workflow |
|---|---|
| 1, "create", "new", "build" | ${SKILL_DIR}/workflows/create-new-skill.md |
| 2, "audit", "improve", "review", "check" | ${SKILL_DIR}/workflows/audit-skill.md |
| 3, "add workflow" | ${SKILL_DIR}/workflows/add-workflow.md |
| 3, "add reference" | ${SKILL_DIR}/workflows/add-reference.md |
| 3, "upgrade to router" | ${SKILL_DIR}/workflows/upgrade-to-router.md |
| 4, "patterns", "understand", "help" | Read /skill-standards for structure; then ${SKILL_DIR}/references/reusability-patterns.md for domain patterns |
Intent-based routing (if user provides clear context):
${SKILL_DIR}/workflows/verify-skill.md${SKILL_DIR}/workflows/audit-skill.md${SKILL_DIR}/workflows/create-new-skill.mdAfter reading the workflow, follow it exactly.
<reference_index>
All in ${SKILL_DIR}/references/:
| File | Purpose |
|---|---|
reusability-patterns.md | Varies-vs-constant analysis, domain-specific authoring patterns |
test-patterns.md | Evaluation-driven development, iterative testing, feedback loops |
technical-patterns.md | Error handling, security, dependencies for skills-that-do-things |
Standards live in /skill-standards. These references cover authoring workflow only.
</reference_index>
<workflows_index>
All in ${SKILL_DIR}/workflows/:
| Workflow | Purpose |
|---|---|
create-new-skill.md | Build a skill from scratch |
audit-skill.md | Check skill against best practices |
add-workflow.md | Add a workflow to existing skill |
add-reference.md | Add a reference to existing skill |
upgrade-to-router.md | Convert simple skill to router pattern |
verify-skill.md | Check if content is still accurate |
</workflows_index>
<templates_index>
All in ${SKILL_DIR}/templates/:
| Template | Purpose |
|---|---|
simple-skill.md | Single-file skill scaffold |
router-skill.md | Router pattern skill scaffold |
builder-skill.md | Builder type template |
guide-skill.md | Guide type template |
automation-skill.md | Automation type template |
analyzer-skill.md | Analyzer type template |
validator-skill.md | Validator type template |
</templates_index>
<scripts_index>
All in ${SKILL_DIR}/scripts/:
| Script | Purpose |
|---|---|
init_skill.py | Initialize skill directory structure |
package_skill.py | Validate and package skill |
quick_validate.py | Quick YAML/structure validation |
</scripts_index>
<success_criteria>
A well-structured skill passes /audit-skills with zero must-fix items against the standards in /skill-standards.
</success_criteria>
ALWAYS invoke this skill when diagnosing the health of a spec-tree or spx environment, when checking whether the SessionStart hook fired for the current session, or when troubleshooting a missing session identity, worktree claim, or unreachable spx CLI. NEVER guess why session state is missing without running these checks first.
ALWAYS invoke this skill when diagnosing the health of a spec-tree or spx environment, when checking whether the SessionStart hook fired for the current session, or when troubleshooting a missing session identity, worktree claim, or unreachable spx CLI. NEVER guess why session state is missing without running these checks first.
ALWAYS invoke this skill when diagnosing the health of a spec-tree or spx environment, when checking whether the SessionStart hook fired for the current session, or when troubleshooting a missing session identity, worktree claim, or unreachable spx CLI. NEVER guess why session state is missing without running these checks first.
ALWAYS invoke this skill when writing or fixing tests for Python. NEVER write or fix Python tests without this skill.
ALWAYS invoke this skill when selecting the next executable slice to implement or deciding which spec-tree nodes /apply should build next from an implementation plan. NEVER choose the next nodes by ad hoc selection — this skill scopes an existing plan to demonstrable value before /apply runs.
ALWAYS invoke this skill when writing or fixing tests for Python. NEVER write or fix Python tests without this skill.