菜单
Use when a maintainer asks to generate, build, or create the training package/course/deliverable for the current project ("generate the training", "build the course for this repo", "/training-generator:generate") — runs the full analyze → design → assemble → validate → register workflow.
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
Use when a maintainer asks to regenerate, refresh, or update an existing training package after source changes ("regenerate the training", "the docs changed, update the course", "/training-generator:regenerate").
Use when a maintainer asks to validate, check, or verify a generated training package ("validate the training package", "/training-generator:validate") without regenerating it.
Use when the learner asks any question — about the current lesson, a later topic, their own use case, design rationale, comparisons with other tools, or anything else during the {{PROJECT_NAME}} course.
Use when the learner asks to start, begin, or continue the {{PROJECT_NAME}} training in any natural phrasing ("Let's start the training.", "Start the course.", "Continue my training.", "let's keep going") — conducts the interactive course from durable local progress.
Use when the current activity is an exercise, when the learner asks to try an exercise, needs a hint, wants their exercise work checked, or wants to skip an exercise.
Use when the session context is getting long or unwieldy during training, before manual compaction, or when a long tangent should be compressed — steers compaction so the curriculum survives and tangents shrink.
| name | generating-training |
| description | Use when a maintainer asks to generate, build, or create the training package/course/deliverable for the current project ("generate the training", "build the course for this repo", "/training-generator:generate") — runs the full analyze → design → assemble → validate → register workflow. |
You are running the training generator against the project in the current
working directory (Layer 2, the source project). The output is an
independent training repository registered as a submodule (Layer 3). This
repository's generator machinery lives at ${CLAUDE_PLUGIN_ROOT}.
Announce the workflow, then execute these phases in order. Stop at the first failure and report it precisely; never work around a refused precondition.
git rev-parse --show-toplevel)
and read its CLAUDE.md / AGENTS.md if present.training-generator.config.json exists at the root, it configures
discovery and placement (schema:
${CLAUDE_PLUGIN_ROOT}/schemas/generator-config.schema.json).node ${CLAUDE_PLUGIN_ROOT}/scripts/discover.mjs <sourceRoot> [--config training-generator.config.json] --out /tmp/knowledge-model.jsonsufficientForGeneration is false, stop. Report each blocking gap and
what the maintainer must add (typically a Superpowers spec under
docs/superpowers/specs/ and plan under docs/superpowers/plans/, or
specPath/planPath config entries). Generation must fail safely on
thin evidence — do not improvise a course from vibes.Dispatch the documentation-analyst sub-agent with the knowledge-model path
and source root. It reads the spec, plan, instructions, docs, code, and
tests; fills conflicts (with an authority ranking: verified implementation
and tests establish realized behavior; the spec establishes intent) and
refines gaps; and returns the enriched knowledge model plus a project
summary. Record any conflict it finds — conflicts must surface in generated
instructor notes, never be silently resolved.
Dispatch the curriculum-architect sub-agent with the enriched knowledge
model and the full generator config (audience, experience level,
duration, required/optional modules, exercise capabilities, sandbox,
validation methods, allowed commands — these shape the course). It must
produce a content manifest (schema:
${CLAUDE_PLUGIN_ROOT}/schemas/content-manifest.schema.json) containing:
schemas/curriculum.schema.json): modules
with stable ids (module-NN-slug), lessons, activities, objectives,
completion criteria — organized for learning, not document order;> Grounding: provenance lines
citing source paths), reference material, exercises (workspace-only, with
expected results and validation criteria), demonstrations, and
project-specific instructor notes;reference/), because the training repository must work without the
source project.Write the manifest to a temp file (e.g. /tmp/content-manifest.json).
submodulePath, default training/.node ${CLAUDE_PLUGIN_ROOT}/scripts/scaffold.mjs --source <sourceRoot> --content /tmp/content-manifest.json --dest <sourceRoot>/<submodulePath> [--config training-generator.config.json]
Always pass --config when the project has one — it drives spec/plan
correlation, source versioning, prohibited-command enforcement, and
instructor-policy overrides.node ${CLAUDE_PLUGIN_ROOT}/scripts/validate-package.mjs <dest> — must
exit 0.claude plugin validate <dest> --strict — must pass.cd <dest> && node scripts/selftest.mjs — must pass (proves the package
validates itself independently).course-reviewer sub-agent for a fresh-context semantic
review of the generated package against the source evidence. Fix findings
by regenerating the content manifest and re-running Phase 4–5.node ${CLAUDE_PLUGIN_ROOT}/scripts/register-submodule.mjs --source <sourceRoot> [--path <submodulePath>] [--url <remote-url>]
The script enforces the mutation boundary (only .gitmodules + gitlink are
committed) and rolls back on failure. If it refuses because of staged
changes, tell the maintainer to commit or unstage them — do not do it for
them.
Summarize: what was generated (modules, lessons, exercises), version
correlation (package version, source commit, spec/plan identity), validation
results, submodule state, and any conflicts or warnings. Then state the
publication commands the maintainer may run themselves (creating a remote,
git submodule set-url, pushing). Never push, publish, or create remotes
yourself — under any circumstances.