← Back to Skills Marketplace
114
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install nm-sanctum-tutorial-updates
Description
Generate tutorials from VHS tapes and Playwright specs with dual-tone markdown and GIF recording
Usage Guidance
This skill appears internally consistent with its purpose, but it executes repository commands and may rebuild/run local binaries. Before installing or running: (1) review .manifest.yaml and .tape files to ensure they don't contain destructive or sensitive commands, (2) run validation (--validate-only or --scaffold) first, (3) run in an isolated environment or container (not on a machine with sensitive data), and (4) be prepared that 'cargo install', 'vhs', Playwright specs, and background services may build code and open local ports. If you cannot review the tape/manifest contents, treat the operations as untrusted and use a disposable CI or VM.
Capability Analysis
Type: OpenClaw Skill
Name: nm-sanctum-tutorial-updates
Version: 1.0.0
The skill bundle implements a tutorial generation pipeline with high-risk capabilities, including the execution of arbitrary shell commands extracted from '.tape' files (modules/tape-validation.md) and the automated rebuilding of binaries via 'cargo install' or 'make' (SKILL.md). While these actions are aligned with the stated purpose of ensuring tutorials reflect the latest code, they create a significant RCE surface if the agent processes untrusted repository content. Additionally, SKILL.md contains a highly repetitive 'Verification' phrase ('Run the command with --help flag to verify availability') appearing 14 times, which is characteristic of prompt manipulation techniques intended to influence agent behavior.
Capability Assessment
Purpose & Capability
Name/description (tutorial generation, VHS/Playwright recordings, GIFs, dual‑tone markdown) match the SKILL.md and included modules. The declared config paths (night-market.sanctum/scry entries) are consistent with orchestrating local recording and media composition; no unrelated cloud credentials or unrelated binaries are requested.
Instruction Scope
The SKILL.md explicitly instructs the agent to scan the repository, parse manifests/tape files, run validation, run binaries (e.g., 'vhs', 'skrills', Playwright specs), possibly start background processes from manifest 'requires', and rebuild local binaries with cargo. All of these are within the stated purpose, but they involve executing commands extracted from tape files and running local build/serve processes. That means the agent will run arbitrary local commands referenced in tapes/manifests — review those inputs and avoid running on sensitive hosts.
Install Mechanism
Instruction-only skill (no install spec, no external downloads). Nothing is written to disk by the skill bundle itself. The SKILL.md recommends running local tooling (cargo install) but this is invoked by the agent/environment, not delivered by the skill package.
Credentials
No required environment variables or external API credentials are declared. The only requested configuration items are internal Night Market config paths related to recording/generation. The skill does read git repo metadata and file system paths (manifests, tape files); this is expected for its purpose. Note: tape files can include Env directives (e.g., SKRILLS_SKILL_DIR) which the skill reads to verify demo data — review tapes before execution.
Persistence & Privilege
Skill is not always:true, is user-invocable, and allows model invocation (the platform default). It does not request persistent system-wide privileges or modify other skills' configs. It may start background processes as part of recording (expected for Playwright/serve workflows), so be cautious about ports/services started on the host.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install nm-sanctum-tutorial-updates - After installation, invoke the skill by name or use
/nm-sanctum-tutorial-updates - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the "tutorial-updates" skill for orchestrating tutorial generation.
- Automates discovery, validation, recording, and generation of user-facing tutorials using VHS tapes and Playwright specs.
- Supports multi-step validation and binary rebuild before recording demos.
- Generates dual-tone markdown and optimized GIFs for documentation.
- Command options for updating, listing, or scaffolding tutorials.
- Integrates with other "night-market.sanctum" and "scry" components for media processing.
Metadata
Frequently Asked Questions
What is Nm Sanctum Tutorial Updates?
Generate tutorials from VHS tapes and Playwright specs with dual-tone markdown and GIF recording. It is an AI Agent Skill for Claude Code / OpenClaw, with 114 downloads so far.
How do I install Nm Sanctum Tutorial Updates?
Run "/install nm-sanctum-tutorial-updates" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Nm Sanctum Tutorial Updates free?
Yes, Nm Sanctum Tutorial Updates is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Nm Sanctum Tutorial Updates support?
Nm Sanctum Tutorial Updates is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Nm Sanctum Tutorial Updates?
It is built and maintained by athola (@athola); the current version is v1.0.0.
More Skills