← Back to Skills Marketplace
117
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install training-content-extractor
Description
根据用户粘贴的录音转写文本，提炼企业内部培训总纲（模块→课时→要点→案例→练习→作业），并支持按 lesson 逐步扩写为细致培训文档。
Usage Guidance
This skill is internally consistent and doesn't request system access or secrets. Before using it, avoid pasting sensitive PII or confidential data into transcripts because outputs will reflect the provided text. Note it does NOT do audio transcription — supply a transcript or use a separate transcription tool first. Verify timestamps and extracted claims against the original transcript (the skill marks gaps as “待补充” but always review for accuracy). If you need integrations (automatic transcription, cloud storage, or sharing), those are outside this skill and would require additional, separate capabilities.
Capability Analysis
Type: OpenClaw Skill
Name: training-content-extractor
Version: 1.0.0
The skill bundle consists entirely of Markdown instructions and templates designed to help an AI agent transform audio transcriptions into structured training materials. There is no executable code, and the instructions are strictly focused on content extraction, clustering, and document formatting without any indicators of data exfiltration, malicious execution, or prompt injection attacks. Key files include SKILL.md for workflow orchestration and several instruction files (e.g., instructions/outline.md) that enforce quality constraints like requiring original evidence from the source text.
Capability Assessment
Purpose & Capability
The name/description (extract training outlines from transcript and expand lessons) matches the actual files and declared requirements: no binaries, no credentials, and detailed instruction/template files. Requiring only a transcript is appropriate for the stated goal; the skill explicitly excludes audio-to-text transcription.
Instruction Scope
SKILL.md and instructions/*.md stay within scope: they require only the transcript and optional contextual fields, mandate provenance (time‑stamps/quotes), forbid fabrication, and define precise output templates. There are no directives to read unrelated system files, access environment variables, or transmit data to external endpoints.
Install Mechanism
No install spec and no code files that execute; this is an instruction-only skill (templates and instructions only), so nothing is written or downloaded at install time. This is the lowest-risk install profile.
Credentials
The skill requests no environment variables, credentials, or config paths. All required inputs are user-provided transcript and optional metadata, which is proportionate to the task.
Persistence & Privilege
always is false; the skill does not request persistent system presence or modify other skills. It is user-invocable and may be invoked autonomously by the agent per platform defaults, which is expected and acceptable for this kind of utility.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install training-content-extractor - After installation, invoke the skill by name or use
/training-content-extractor - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of training-content-extractor skill.
- Extracts structured enterprise training outlines from pasted transcription text (modules → lessons → key points → cases → exercises → assignments).
- Supports step-by-step expansion of each lesson into detailed training documents.
- Offers three output modes: outline, lesson expansion, and compilation into long-form documents.
- Includes workflows for cleaning transcription, identifying structure, extraction, and document assembly.
- Enforces constraints such as no fabrication, source attribution, actionable assignments, and segmented output to avoid excessively long text.
- File structure separates instructions, templates, and sample outputs for clarity and maintainability.
Metadata
Frequently Asked Questions
What is training-content-extractor?
根据用户粘贴的录音转写文本，提炼企业内部培训总纲（模块→课时→要点→案例→练习→作业），并支持按 lesson 逐步扩写为细致培训文档。 It is an AI Agent Skill for Claude Code / OpenClaw, with 117 downloads so far.
How do I install training-content-extractor?
Run "/install training-content-extractor" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is training-content-extractor free?
Yes, training-content-extractor is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does training-content-extractor support?
training-content-extractor is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created training-content-extractor?
It is built and maintained by 0x00pluto (@0x00pluto); the current version is v1.0.0.
More Skills