agent-browser
claudecodexBrowser automation CLI for AI agents - interact with and test code in Chromium using natural language
10 skills
Find the single most useful next addition to a PR, branch or project, then offer to build it.
Plugin spark from marketplace powerful-plugins in StackOneHQ/powerful-plugins. Commands read from the repo's manifest — yesterday.
auditDeprecated alias kept so the old /spark:audit command still works: audit moved to the forge plugin as /forge:audit. Use only when /spark:audit or $spark:audit is invoked by name; for anything else use the forge plugin's audit skill.
forgeDeprecated alias kept so the old /spark:forge command still works: forge moved to the forge plugin as /forge:forge. Use only when /spark:forge or $spark:forge is invoked by name; for anything else use the forge plugin's forge skill.
sparkFinds the single smartest, highest-value addition to the current PR, branch or project, presents it, and offers to build it. Use on \"/spark\", \"what is the best thing you could add to this PR?\", \"what single feature would make this better?\", \"what is the most impactful next move?\", \"what wou
Browser automation CLI for AI agents - interact with and test code in Chromium using natural language
10 skills
Create web animations, interactive system and mechanism explanations, and short videos. Explain Machine lets readers inspect, follow, operate and compare using a source-grounded model, while retaining detailed exploded drawings and narrated lessons.
5 skills · 4 agents
Speak when Claude Code or Codex finishes a turn or is blocked, with offline stackvox voices or the macOS say fallback.
4 skills · 4 commands · hooks
Comprehensive PR review with specialized agents for code review, silent failure hunting, and test analysis
1 command · 6 agents
Learn from the current session or from recurring history across sessions, git changes and review feedback, and propose evidence-backed skill and guidance improvements.
2 skills · 2 commands
Write and edit like a person, not a language model: bans the words, sentence patterns and formatting that give AI text away, with a mechanical checker and a review command.
2 skills · 1 command
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.