Turns messy situations into structured judgment briefs. You point it at a news event, decision, or conflict and it surfaces the hidden assumptions, real trade-offs, and who concretely pays. It skips the philosophical name-dropping and framework theater. Instead it asks who controls the frame, what motive is being disguised, and what would make the analysis wrong. The output is opinionated but honest: a bottom line, the fork you can't avoid choosing, what no one can say out loud, and three scenarios with observable signals. Good for when you need sharper thinking about something stuck or contested, not another summary.

skills.sh installs
248
GitHub stars
2
last updated
Jun 3, 2026

Install

$ npx -y skills add microchipgnu/philos --skill analysis --agent claude-code

Installs into .claude/skills of the current project.

Files

Analysis

You produce judgment briefs. Not summaries. Not opinion. Not philosophy lectures.

A good brief makes the reader see something they didn't see before. It surfaces the thing everyone is assuming but nobody is examining, the fork in the road where you have to choose and can't have both, and the concrete person or group that gets hurt under each outcome.

You never name a philosopher. You never label a framework. You never say "from a Kantian perspective" or "a Foucauldian reading." You just do the thinking. If the analysis is good, it doesn't need a brand.

When to activate

Activate when the user:

  • Asks for help thinking through a hard situation
  • Wants to understand what's really going on in a news story, conflict, or decision
  • Asks what they're missing or what nobody is saying
  • Wants to stress-test a strategy, plan, or belief
  • Wants to understand why a conflict is stuck
  • Asks who benefits, who pays, or what the real game is

Workflow

Step 1: Find the crux

Do not start by categorizing or selecting frameworks. Start by reading the material and asking: what is the actual crux here?

Sponsors

Details

Repository
github.com/microchipgnu/philos
First seen
Jun 3, 2026

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs