jstack-skills

What jstack-skills does, in the publisher's words

From the project README, punctuation lightly normalized · Open the README on GitHub →

Links

• github.com/jonosin/jstack
• plugin.json (manifest)

Skills · 46

adscan

Scan the Meta Ad Library for advertisers and pull their ads (creative, flight dates, video files, store/landing links) with no API key or identity verification. Use when the user says /adscan, "scan the ad library", "find advertisers running ads for X", "pull [app/brand]'s Meta ads", "who's adverti…

asciiexplain

Explain a topic with a terminal-safe ASCII diagram and short legend. Use for "explain this with ASCII" or when the user requests a text diagram of a process, system, architecture, relationship, or idea.

autoresearch

Autonomous goal-directed iteration loop: modify, verify, keep/discard against ANY mechanical metric, until the metric stops improving or the iteration budget runs out. A faithful port of Karpathy's autoresearch (via uditgoenka/autoresearch, the generalized Claude-skill version). Use when Jono says…

brainwork

Compile pending raw evidence into canonical second-brain knowledge, run a bounded migration, or maintain the brain. Use when the user asks for brainwork, compile, migration, schema or link checks, overlay freshness, generated views, verification, or a dry run.

cc-find

Find a Claude Code session by natural-language description and return the claude --resume command. Use when the user says /cc-find, find a Claude session about X, where is the Claude session where I discussed Y, search my past Claude sessions, locate an old Claude conversation, or wants to resume a…

cdesign

Two-way bridge between a Claude Code session and Claude Design (claude.ai/design). Use when Jono says /cdesign (optionally with a mode arg: new-system | build | edit | assets), 'hand this to Claude Design', 'set up Claude design for this', 'build a design system in Claude Design', 'build this on my…

codex

Router for using GPT-5.5 via the OpenAI Codex CLI as a subagent. Four modes: advisor (adversarial pressure-test of the user's position; replaces jstack-challenge), review (independent code/plan review), implement (clear-spec bulk implementation), investigate (research/diagnosis/data analysis). Use…

excalidraw

Author beautiful, hand-drawn-style Excalidraw diagrams and export them to PNG/SVG headlessly. Use when you need to draw a clear, designed-looking visual, a flow, architecture, system, tree, sequence, or concept, anything where a picture beats text. Routes to an auto-layout pipeline (author in Mer…

focus

Wait, re-pitch that. Then stay tight: shorten ~40%, plain words, ASCII where it helps. Triggered by "/focus", "focus", "wait-what", "wait what", "re-pitch that", "less wordy", "stop explaining", "keep it short", "tired of reading". Turn off with "/focus off" or when asked for normal detail.

fopus-tileforge

Use when the user asks to create, process, package, repair, or validate reusable pixel-art environment tiles and objects for a named world style.

ggdesign-init

DEPRECATED: do not invoke. Use when you would otherwise reach for ggdesign-init to initialize a design system (DESIGN.md); that trigger now routes to /init instead. New build repo needing a design system → /init (build path, can init DESIGN.md deterministically). Standalone DESIGN.md init in an ex…

git-guardrails

Install a PreToolUse hook that mechanically blocks destructive git commands (push, reset --hard, clean -f, branch -D, checkout.) before they execute. Use when setting up git safety guardrails, 'protect my repo from destructive git', or after any near-miss with a destructive git command.

grilling

gtmarketing

handoff-from-cc

handoff

html

hyperframe

imgen

init

last30days

linkedin-leads

linkedin-salesnav

linkedin-send

linkedin

myvoice

openbrain-sync

opencli

otagallery

premortem

querybrain

research-router

savetobrain-from-cc

savetobrain

schedule-cc

second-brain-sync

second-brain

show-me

skillify

skilltune

suite

teach

to-spec

vercel-debug

vidgen

vision

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

Category

Productivity & Workflow. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.

Keywords

agent-skills · agent-plugins · workflow · codex · claude-code

Related by publisher and keywords

• rad-plugin-converterRadOrigin-LLC

  Create, audit, and convert Agent Plugins 1.0.0 packages, then guide reviewed marketplace release. Agent Plugins 1.1.0 is a working draft, and local checks cannot prove support in every client.

• cog-second-brainhuytieu

  Self-evolving second brain with 36 AI agent skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle (spec to evidence, criterion-traced checkpoints), read-only verifier agents that observe artifacts instead of trusting worker summaries, risk lanes, multi-session ultragoals with a north-star acceptance gate, plus craft skills for writing, visual work, and a paired anti-slop design system for marketing and product UI. Works with Claude Code, Antigravity, Cursor, Kiro, Gemini CLI, Codex, and any Agent Plugins conformant client.

• agent-brainSpillwaveSolutions

  Local-first RAG memory for AI agents: hybrid BM25/semantic search, GraphRAG, and an MCP server with OAuth 2.1. Index docs and code, then search from Claude Code, Cursor, Codex, OpenCode, or Grok Build.

• document-specialistSpillwaveSolutions

  Software documentation specialist with arc42 DESIGN_DOC.md, architecture docs, Mermaid-first diagrams, and PlantUML Salt UI wireframes. STE100 default. Google docs style on request. Claude Code, Grok Build, Codex, Cursor, and Agent Plugins 1.0.

• automating-mac-appsSpillwaveSolutions

  Automate macOS apps via Apple Events using AppleScript (discovery) and JXA (production).

• hermes-jailbenchhermes-labs-ai

  Jailbreak regression benchmark for LLM endpoints with repeatable known-pattern attacks and deterministic scoring