ReddRadar
Agent skill
process-hunter
CAVEMAN HUNT BAD PROCESS! Me find greedy creature eating fire and rocks. Me bonk them good. Use when tribe say "kill processes", "clean up servers", "save battery", "find resource hogs", "bonk next.js", or "hunt processes". Me bonk known bad creature automatic. Me ask before bonk mystery creature.
Install this agent skill to your Project
npx add-skill https://github.com/petekp/agent-skills/tree/main/skills/process-hunter
SKILL.md
๐ฆฃ CAVEMAN PROCESS HUNTER ๐ฆฃ
Me find greedy process eating all fire (CPU) and hoarding rocks (memory). Me bonk them. Lightning rock (battery) happy. Tribe proud.
How Hunt Work
IMPORTANT: Always show hunt report after bonking! Tribe need see victory!
-
Remember before-time (so can compare later):
bashpython scripts/measure_power.py before -
Find greedy creature:
bashpython scripts/hunt_processes.py -
BONK! (track how many bonk and how much rock freed)
-
Show big victory report - ALWAYS do this after hunt:
bashpython scripts/measure_power.py report <bonk_count> <rocks_freed_mb>
Cave Tools
hunt_processes.py - Find Bad Creature
python scripts/hunt_processes.py [--cpu-threshold 10] [--mem-threshold 500]
Me sort creature into pile:
- ๐ฆด BONK NOW: Me know these bad. Safe smash.
- ๐ค ME NOT SURE: Mystery creature. Ask human first.
terminate_process.py - BONK Tool
python scripts/terminate_process.py <pid> [--force]
Me try gentle tap first. If creature no listen, ME USE BIG CLUB.
Use --force to skip gentle tap. Go straight to BIG CLUB.
measure_power.py - Lightning Rock Checker
python scripts/measure_power.py before # Remember this moment
python scripts/measure_power.py report # Show hunt victory
python scripts/measure_power.py status # Quick peek at juice
Creature Me Know Safe To Bonk
These greedy. These eat much fire. BONK:
- Next.js fire-eater (
next-server) - Webpack bundle-beast
- Vite speed-demon
- Turbo thunder-lizard
- npm/yarn/pnpm run-run things
- React Native bridge troll
- Claude brain-in-box (when too many clone)
- TypeScript watcher-eye
- esbuild fast-maker
When Ask Human First
Use AskUserQuestion before bonk:
- Mystery creature me not recognize
- Human app (browser, picture-maker, code-cave)
- Anything not in bonk-safe list
Example Hunt
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ ๐ฆฃ CAVEMAN PROCESS HUNTER ๐ฆฃ โ
โ แฆ(รฒ_รณห)แค Me find greedy process! โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ฆด BONK NOW! (me know these bad)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
PID 61331 โ Fire: 121.9% ๐ฅ๐ฅ๐ฅ๐ฅ๐ฅ
โ Rock: 2886.5MB ๐ชจ๐ชจ๐ชจ๐ชจ๐ชจ
โ What: Next.js fire-eater
โ Name: next-server
Victory Report
After hunt, always show:
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ ๐ฆฃ CAVEMAN HUNT REPORT ๐ฆฃ โ
โ แฆ(รฒ_รณห)แค Me show what happen! โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ ๐๐๐๐๐ โ
โ ๐๐๐๐๐ โ
โ โ
โ Creatures Bonked: 5 โ
โ Cave Space Free: ~7.8 big rocks โ
โ โ
โ OOGA BOOGA! GOOD HUNT! โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โญโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโฎ
โ ๐ฆฃ MAMMOTH-SIZE VICTORY! ๐ฆฃ โ
โ โ
โ BEFORE AFTER โ
โ โโโโโโโโ โโโโโโโโ โ
โ โ 135 โ >>> โ 212 โ +77 sun โ
โ โโโโโโโโ โโโโโโโโ โ
โ โ
โ โจ Lightning rock VERY happy! โจ โ
โฐโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโฏ
โโโโโโโโโโโโโโโ
โ 58% โก โโ
โ [โโโโโโโโโโ] โโ
โโโโโโโโโโโโโโโ
โฑ๏ธ Sun-moves remaining: 3:32
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ฟ Magic lightning box breathe easy now!
๐ฆด Caveman did good. Tribe proud.
Caveman Wisdom
- Fire = CPU (how much thinking)
- Rock = Memory (how much cave space)
- Sun-moves = Minutes (time before lightning rock sleep)
- Lightning rock = Battery
- Bonk = Terminate process
- Big club = SIGKILL (force)
- Gentle tap = SIGTERM (nice ask)
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
petekp/agent-skills
multi-model-meta-analysis
Synthesize outputs from multiple AI models into a comprehensive, verified assessment. Use when: (1) User pastes feedback/analysis from multiple LLMs (Claude, GPT, Gemini, etc.) about code or a project, (2) User wants to consolidate model outputs into a single reliable document, (3) User needs conflicting model claims resolved against actual source code. This skill verifies model claims against the codebase, resolves contradictions with evidence, and produces a more reliable assessment than any single model.
petekp/agent-skills
capture-learning
Analyze recent conversation context and capture learnings to project knowledge files (for project-specific insights) or skills/commands/subagents (for cross-project patterns). Use when the user asks to "capture this learning", "update the docs with this", "remember this for next time", "document this issue", "add this to CLAUDE.md", "save this knowledge", or "update project knowledge". Also triggers after resolving build/setup issues, discovering non-obvious patterns, or completing debugging sessions with valuable insights.
petekp/agent-skills
optimize-agent-docs
Build a retrieval-optimized knowledge layer over agent documentation in dotfiles (.claude, .codex, .cursor, .aider). Use when asked to "optimize docs", "improve agent knowledge", "make docs more efficient", or when documentation has accumulated and retrieval feels inefficient. Generates a manifest mapping task-contexts to knowledge chunks, optimizes information density, and creates compiled artifacts for efficient agent consumption.
petekp/agent-skills
agent-changelog
Compile an agent-optimized changelog by cross-referencing git history with plans and documentation. Use when asked to "update changelog", "compile history", "document project evolution", or proactively after major milestones, architectural changes, or when stale/deprecated information is detected that could confuse coding agents.
petekp/agent-skills
literate-guide
Create a narrative guide to a codebase or feature in the style of Knuth's Literate Programming โ code and prose interwoven as a single essay, ordered for human understanding rather than compiler needs. Use when the user asks to 'explain this codebase as a story', 'write a literate guide', 'create a narrative walkthrough', 'tell the story of this code', 'Knuth-style documentation', 'weave a guide for this feature', or when they want deep, readable documentation that treats the program as literature. Also trigger when someone wants a document that a thoughtful reader could follow from start to finish and come away understanding both WHAT the code does and WHY every design choice was made.
petekp/agent-skills
autonomous-agent-readiness
Assess a codebase's readiness for autonomous agent development and provide tailored recommendations. Use when asked to evaluate how well a project supports unattended agent execution, assess development practices for agent autonomy, audit infrastructure for agent reliability, or improve a codebase for autonomous agent workflows. Triggers on requests like "assess this project for agent readiness", "how autonomous-ready is this codebase", "evaluate agent infrastructure", or "improve development practices for agents".
Didn't find tool you were looking for?