Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

SETUP

ASecurity

Determine the project name for `home_plans/<project>/` path:

8 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agents

Works with

claude codecli

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add tstapler/dotfiles --skill SETUP --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of SETUP?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for SETUP
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tstapler-setup/badge)](https://www.skillsdirectory.com/skills/tstapler-setup)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
## Verify prerequisites before any home: command

### Check 1: Identify the project

Determine the project name for `home_plans/<project>/` path:

- If `home_plans/` already exists with subdirectories, list them and ask which project to work on (or whether to start a new one)
- If this is a new project, ask for a short kebab-case project name that describes the work (e.g., `basement-bathroom-tile`, `kitchen-faucet-replacement`, `garage-shelving`)
- Store as `PROJECT_NAME` for use throughout the session

### Check 2: Working directory context

These commands are designed for use inside the personal wiki repo. The `home_plans/` directory lives at the repo root alongside `logseq/`. Verify you are in the right directory if unsure.

### Check 3: Track progress with the task tool (if available)

Each `home:N-*` command is one discrete stage. If a task-tracking tool is available in this environment, use it to record which stage `PROJECT_NAME` is in — this preserves position if the session is interrupted:

- **Claude Code**: `TaskCreate` one task per stage the first time you touch a project (e.g. "home:`<PROJECT_NAME>` — Phase 2 Research"); `TaskUpdate` it to `in_progress` when you start the stage and `completed` when its exit gate (Check 4) passes.
- **Gemini CLI / Antigravity**: `write_todos` with one entry per stage, updated the same way.

If no task tool is available in this environment, skip this — it's a convenience for resuming, not a requirement for the workflow to function.

### Check 4: Respect stage gates

Every `home:N-*` command is a discrete stage with two gates:

- **Entry gate** — halt and name the missing prerequisite if the required input file from the previous stage doesn't exist (e.g. `/home:3-plan` halts if `scope.md` is missing, telling the user to run `/home:1-scope` first). Never guess or fabricate a missing input to keep moving.
- **Exit gate** — before printing "Next step" and advancing, verify this stage's own output actually exists and is non-trivial (the file was written, isn't empty, and — where the stage defines one — its verdict/checklist passes, e.g. `/home:3-plan`'s adversarial review verdict, `/home:4-prep`'s readiness gate). Don't advance on the agent's summary alone; check the artifact.

Never silently skip a gate to save time — a gate failing is a normal, expected outcome that the command should surface, not suppress.

Attribution

tstaplertstapler
View sourceMore from tstapler →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →