agent-setup-wizard/SKILL.md
Interactive installer for agent skills and rules across any AI coding agent framework. Guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.
npx skillsauth add lidge-jun/cli-jaw-skills agent-setup-wizardInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
An interactive, step-by-step installation wizard for skill and rule libraries. Guides users through selective installation of skills and rules, verifies correctness, and offers optimization.
Ask the user for the source repository containing skills and rules:
Question: "Where is the skill/rule library located?"
Options:
- "Git URL" — "Clone from a remote repository"
- "Local path" — "Use a local directory"
If a git URL is provided, clone to a temporary directory and set SOURCE_ROOT to that path. If a local path is provided, set SOURCE_ROOT directly.
Ask the user where to install:
Question: "Where should components be installed?"
Options:
- "User-level" — "Applies to all projects (e.g., ~/.config/agent/)"
- "Project-level" — "Applies only to the current project (e.g., .agents/)"
- "Both" — "Shared items user-level, project-specific items project-level"
Store the choice as INSTALL_LEVEL. Set the target directory based on the agent framework in use. Create the target directories if they don't exist:
mkdir -p $TARGET/skills $TARGET/rules
Scan $SOURCE_ROOT for directories containing SKILL.md files. Group by category if the source uses a category structure, otherwise list them flat.
Present the discovered skills to the user for selection. For large catalogs (more than 10 skills), organize by category and offer batch selection:
Question: "Which skills do you want to install?"
Options:
- "All skills" — "Install everything"
- "Select by category" — "Choose categories, then refine"
- "Pick individually" — "Select specific skills from the full list"
For each selected skill, copy the entire skill directory (not just SKILL.md — some skills include config files, scripts, or reference documents):
cp -r $SOURCE_ROOT/skills/<skill-name> $TARGET/skills/
Scan $SOURCE_ROOT for rule files (typically .md files in a rules/ directory). Present them for selection using the same pattern as skills.
Execute installation:
cp -r $SOURCE_ROOT/rules/<selected>/* $TARGET/rules/
If the source organizes rules into base and extension sets, warn when extensions are selected without their base.
Confirm all selected files exist at the target location.
Scan installed .md files for hardcoded paths that may not match the installation target. Flag:
For each issue found, report:
Ask the user whether to tailor the installed files:
Question: "Optimize the installed files for your project?"
Options:
- "Optimize skills" — "Remove irrelevant sections, adjust paths, tailor to your tech stack"
- "Optimize rules" — "Adjust targets, add project-specific patterns"
- "Optimize both"
- "Skip" — "Keep everything as-is"
If optimizing:
Clean up any temporary directories (e.g., cloned repos in /tmp).
Print a summary:
## Installation Complete
### Target
- Level: [user-level / project-level / both]
- Path: [target path]
### Skills Installed ([count])
- skill-1, skill-2, ...
### Rules Installed ([count])
- [list]
### Verification
- [count] issues found, [count] fixed
- [remaining issues if any]
### Optimizations
- [changes made, or "None"]
SKILL.md file (not just loose .md files)development
Goal execution guidelines with PABCD integration, verification tiers, documentation workflow, and AI-driven planning
tools
A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.
development
Use this skill any time a spreadsheet file is the primary input or output (.xlsx, .xlsm, .csv, .tsv). This includes: creating, reading, editing, analyzing, or formatting spreadsheets; cleaning messy tabular data; converting between formats; and data visualization with charts. Also use for pandas-based data analysis when the deliverable is a spreadsheet. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration.
tools
Use this skill when the user wants to build a financial model, 3-statement model, DCF valuation, cap table, scenario analysis, or financial projections in Excel. Trigger on: 'financial model', '3-statement model', 'DCF', 'cap table', 'pro forma', 'projections', 'sensitivity analysis', 'waterfall', 'debt schedule', 'break-even', 'discounted cash flow', 'capitalization table', 'fundraising model', 'WACC calculation', 'scenario analysis model'. Input is a text prompt with assumptions. Output is a single .xlsx file with formula-driven, interconnected statement sheets.