software-factory
software-factory — an installable skill for AI agents, published by mattpocock/skills.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-12 00:15
Agents & models
26,128 results
neovim
Neovim remote control and socket management for tmux environments. Use this skill when you need to control Neovim instances from agents, open files in existing…
converse
Start an ongoing voice conversation
voicemode
Voice interaction for Claude Code. Use when users mention voice mode, speak, talk, converse, voice status, or voice troubleshooting.
voicemode-connect
Remote voice via VoiceMode Connect. Use when users want to add voice to Claude Code using their phone or web app, without local STT/TTS setup.
clarify
Bounded clarification/refinement pass for planning. Use before finalizing a phased plan when unresolved [?] markers or plan-changing ambiguity remain. Triggers…
drive-mcpjam-playground
Drive an API Playground session through MCPJam's remote MCP tools or cloud CLI, inspect browser evidence, and hand the live session to its owner. Use for…
ai-ready
Make any repo AI-ready — analyzes your codebase and generates AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and more. Mines your PR review…
boost-prompt
Interactive prompt refinement workflow: interrogates scope, deliverables, constraints; copies final markdown to clipboard; never writes code. Requires the…
brag-sheet
Turn vague "what did I do?" into evidence-backed impact statements for performance reviews, self-reviews, promotion packets, and weekly updates. Uniquely mines…
handoff
Compact the current conversation into a handoff document for another agent to pick up.
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM,…
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude…
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an…
skill-publisher
Publish a local SKILL.md skill to multiple marketplaces with one click: ClawHub, Tencent SkillHub, skills.sh, LobeHub, SkillsMP, Agensi, Coze, etc. Trigger words include: "publish skill", "publish to multiple marketplaces", "publish to clawhub", "one-click publish", "publish to…
agent-harness-design
Agent Harness engineering design and productization: 14 mechanisms + 30 anti-patterns + Loop + multi-Agent graph + 5 axes. Triggers: building an Agent/design/review/adding a new mechanism/building an automated Loop/upgrading to multi-Agent.
audit-answers
Adversarially validate a completed /planning:interview's answers with independent fresh-context agents — runs over any filled decision ledger, whether the…
audit-settings
Audit Claude Code settings.json files for quality, compliance, and security. Use to validate configuration before deployment or check for exposed secrets.
audit-statuslines
Audit Claude Code status lines for quality and cross-platform compatibility. Use when creating or validating custom status line scripts, or troubleshooting…
continue-in-background
Delegate the task to a fresh background agent that continues it NOW — produce a save-point, then launch a detached claude --bg session seeded with the resume…
explore-deep
Run the full explore workflow in an isolated forked subagent so verbose file reads and search output stay out of the main conversation; only a short summary…
find-handoff
Recover a lost handoff after `/clear` — find the save-point file or resume prompt when the resume prompt was written but never copied and the fresh session has…
improve-prompt
Improve and optimize prompts using Anthropic's 4-step prompt improvement workflow
sweep-all
Compose this plugin's discipline correctors into ONE batched pass — not a corrector itself, but a router that fans out an audit-only subagent per in-scope…