Automated summary
Generates a new SKILL.md scaffold from an MCP server config, a README, or an OpenAPI spec via the `ct generate skill` CLI, then validates it and rebuilds the index.
Strengths
- Supports three distinct input sources: MCP config, README, and OpenAPI spec
- Useful flags such as `--dry-run` to preview output and `--examples N` to control how many examples are generated
- Includes post-generation steps: validation via `validate_skill.py` and index rebuild via `build_index.py`
- Lets you target a destination platform (anthropic, openai, universal)
Limitations
- Relies on an external `ct` CLI that must be installed and available
- The generated SKILL.md requires manual review and correction for accuracy
- Does not address updating an existing skill or handling generation failures
Use it to bootstrap a new skill quickly from an existing API, spec, or README instead of writing the SKILL.md by hand.
Avoid it when authoring a skill manually or when your source is not an MCP config, a README, or an OpenAPI spec.
Security analysis
CautionThe skill uses legitimate file-generation and bash tooling, with no destructive commands, obfuscation, credential exfiltration, or curl|sh patterns. However, it executes an external CLI and writes files, so it warrants caution rather than a fully safe rating.
- •Invokes bash commands and an external `ct` CLI to generate files under `./skills/<slug>/` without requiring confirmation, though `--dry-run` is available.
- •Reads input files such as MCP configs, READMEs, and OpenAPI specs that may contain sensitive configuration; generated output could inadvertently include secrets if the source does.
- •Does not declare allowed-tools despite including executable bash snippets.
Examples
Generate a skill named github-tools from my MCP config at ./configs/github-mcp.json into ./skills/github-tools/, but do a dry run first so I can review the output.Create a skill called stripe-api from ./specs/stripe-openapi.json with 5 examples, then validate it with tooling/validate_skill.py.Build a skill called acme-sdk from ./README.md, add the CHANGELOG, and rebuild the index when you're done.Generate a new skill from various sources.
Arguments: $ARGUMENTS (source type and path)
From MCP Server
ct generate skill --from-mcp <config.json> --name <skill-name> --output ./skills/<slug>/
From README
ct generate skill --from-readme <README.md> --name <skill-name> --output ./skills/<slug>/
From OpenAPI Spec
ct generate skill --from-openapi <openapi.json> --name <skill-name> --output ./skills/<slug>/
Options
--platform anthropic|openai|universal- Target platform (default: universal)--dry-run- Preview without writing files--examples N- Number of examples to generate (default: 3)
After generation:
- Review generated SKILL.md for accuracy
- Validate:
python tooling/validate_skill.py skills/<slug>/ - Add CHANGELOG.md if not generated
- Rebuild index:
python tooling/build_index.py
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/generate-skill-from-various-sources-mrwakdvb/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/generate-skill-from-various-sources-mrwakdvb' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/generate-skill-from-various-sources-mrwakdvb/download' --output '.skill-downloads/generate-skill-from-various-sources-mrwakdvb/SKILL.md.part' && mv '.skill-downloads/generate-skill-from-various-sources-mrwakdvb/SKILL.md.part' '.skill-downloads/generate-skill-from-various-sources-mrwakdvb/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/generate-skill-from-various-sources-mrwakdvb/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.