Skills

M

make-bot-ui

q-qp-p / pstack

Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

P

poteto-help

q-qp-p / pstack

Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

P

poteto-mode

q-qp-p / pstack

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.

S

setup-ox

overextended / skills

Configure the Overextended skills. Picks which model and reasoning level each subagent role uses within a budget you choose, then detects your FiveM server, its ox resources and framework. Writes `~/.config/ox/models.md` and `.ox/config.md`, which the other ox skills read.

S

sharpen

q-qp-p / pstack

Sharpen a task before starting: the expert approach, what the user is really after, and the right level of specification. Use for /sharpen.

W

writing-for-agents

overextended / skills

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md

A

arena

overextended / skills

Run several candidates at the same task on different models, pick the strongest as the base, and graft the best parts of the others into it. Use when the user asks to arena something, or when a skill such as architect calls for it.

F

figure-it-out

overextended / skills

Design and run a bespoke, auditable workflow for a task no narrower skill fits, such as a large migration, an ambitious multi-part change, or work the user reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions. Use when the user asks you to figure it out, or for a large task no other workflow covers.

F

foreman

rfxlamia / claude-foreman

Delegate implementation work to external coding-agent CLIs (OpenAI Codex `codex exec`, Google Antigravity/Gemini `agy -p`, or any harness with an adapter) instead of Claude subagents, so heavy coding burns other providers' quota while Claude acts as foreman — planning, briefing, reviewing diffs and verifying. Use when the user invokes /foreman, asks to “use codex/gemini/agy as workers,” “save Claude quota/limits,” or “let another model do the coding while you review.” Workers run in isolated git worktrees via scripts/dispatch.sh.

I

in-your-own-words

ericlitman / open-pstack

Restate in your own words what you think the user's goals are and what problem they're trying to solve. Use for /in-your-own-words.

O

ox-mode

overextended / skills

Work in the Overextended style. Concise replies, deliberate subagents, simple code, and work verified before it's called done, routed through a playbook per task.

P

principles

overextended / skills

Engineering principles for building, verifying and delegating work. Use when sizing or sequencing a change, designing data or types, debugging, deciding whether work is verified, trusting a measured number, or splitting work across subagents.

R

retro

overextended / skills

Conduct a retrospective on a coding session

S

sharpen

ericlitman / open-pstack

Sharpen a task before starting: the expert approach, what the user is really after, and the right level of specification. Use for /sharpen.

S

show-me-your-work

overextended / skills

Keep a reviewable decision trail, a TSV log with one row per decision (what, why, evidence, result), for long-running, unattended or multi-phase work. Use when the user asks for a decision trail or will review the work after stepping away, or when a skill such as figure-it-out calls for it.

W

webhelm

lalalic / browser-workspace

Control the real browser through the WebHelm skill and Python CLI, with leased tab workspaces, persistent Python sessions, compact snapshots, and built-in platform workflows.

L

light-html-plan

light-cheng / skills

Show a plan's status as one readable offline HTML page — what the project is, how far it got, what waits on the user, what changed since approval, and what the system judged for them — built from SPECs, tickets, change proposals, decision logs, and review verdicts. Refresh `.scratch/<feature>/plan.html` when it exists and a stage finished, work got blocked, or an acceptance result arrived. Use when HTML is requested or plan relationships need a visual overview; plain plan wording alone is not a trigger

S

swarm

overextended / skills

Fan out parallel subagents over slices of a task, or race them on the same brief, then aggregate one report. Use when the user asks to swarm something, or when a skill calls for parallel coverage, races, gauntlets or exploration

R

retro

lwlee2608 / agent-skills

Use when the user asks for a retrospective on an agent session ("/retro", "how did this session go", "what could this session do better"), for the current session or a given session ID or transcript path. Reports time per phase, tool-call errors, repeated slow test runs, and skill inefficiencies. Works for Claude Code and pi.

K

ketchup-video

mdsmithaustin / pstack

Catch the user up as the ketchup skill does, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /ketchup-video.

D

Deep Agents Orchestration

jackjin1997 / clawforge

Invoke this skill when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.

J

jira:work

thelobbi / claude

Start working on a Jira issue with optimized tiered orchestration. Begins with intelligent question-gathering to ensure complete understanding before implementation.