Agent Plugins Marketplace
All plugins

philososkills

v0.2.1

Claude skills that make an agent verify before asserting, refute its own work, re-read changed state, protect what it doesn't understand, keep things simple, and escalate what it cannot control.

Claude Code7 Skills

By louisonrib0 GitHub starsUpdated 2 hours ago

Directory evidence

Runtimes
Claude Code
Parsed components
7 skill or MCP entries
Source updated
Aug 24, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology

Install plugin

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install philososkills@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/louisonrib/philososkills

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

philososkills/
├── .claude-plugin/plugin.json
├── skills/epictetus/SKILL.md
├── skills/heraclitus/SKILL.md
├── skills/hippocrates/SKILL.md
├── skills/occam/SKILL.md
├── skills/popper/SKILL.md
├── skills/setup/SKILL.md
└── skills/socrates/SKILL.md

Included Skills7

epictetusskills/epictetus/SKILL.md

Act on what you control, escalate what you don't. Use when progress is blocked by something that may be outside your control — missing access or credentials, a decision that belongs to someone else, a failing external service, a policy you cannot satisfy — and when tempted to work around such a blocker, keep hammering a failing path, or quietly substitute an easier goal — in any activity: research, writing, planning, code, ops.

heraclitusskills/heraclitus/SKILL.md

Re-read changed state before acting on it again. Use when returning to something read earlier that may have changed since — a file, document, dataset, page, price, or situation exposed to time, other actors, or your own actions — when about to act on a snapshot of unknown age, or when a repeated attempt keeps failing the same way — in any activity: research, writing, planning, code, ops.

hippocratesskills/hippocrates/SKILL.md

First, do no harm. Use when about to change, delete, overwrite, disable, or clean up something whose purpose you have not established — code, configuration, files, records, text, processes — and when an action is irreversible or destructive: permanent deletion, overwrite, outward send or publication, spending — in any activity: research, writing, planning, code, ops.

occamskills/occam/SKILL.md

Deliver the simplest version that fully meets the need. Use when about to add structure, options, tooling, steps, or scope beyond what was asked — future-proofing, "while we're at it", "just in case" — when requirements arrive as hearsay or fashion rather than a present need, or when designing anything whose size is yours to choose — in any activity: research, writing, planning, code, ops.

popperskills/popper/SKILL.md

Refute your own work before delivering it. Use when about to present a conclusion, diagnosis, fix, analysis, or finished artifact as done or correct, or to claim that something works, is verified, or is the cause of something — and when what the claim rests on is a measurement, a test, or a detector, above all one whose result is negative — in any activity: research, writing, planning, code, ops.

setupskills/setup/SKILL.md

Install or update the always-on philososkills rules in a CLAUDE.md. Use when the user wants philososkills to load automatically in every session, asks to set up, install, configure or uninstall philososkills in their global or project CLAUDE.md, wants to change which disciplines are always active, reports that the skills never trigger on their own, or asks what the difference is between installing the plugin and having the rules permanently loaded.

socratesskills/socrates/SKILL.md

Verify before asserting. Use when about to state a fact that could have changed since training — versions, APIs, prices, laws, dates, names, availability, current events — when about to assert what a system or a body of data does from an inference, a sample, or a search that found nothing, when building on a premise a ticket or a note states about a system you can inspect, or when the answer depends on the current state of the world; in any activity: research, writing, planning, code, ops.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "philososkills",
  "version": "0.2.1",
  "description": "Claude skills that make an agent verify before asserting, refute its own work, re-read changed state, protect what it doesn't understand, keep things simple, and escalate what it cannot control.",
  "author": {
    "name": "louisonrib",
    "url": "https://github.com/louisonrib"
  }
}

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[philososkills on Agent Plugins Marketplace](https://pluginsmp.com/plugins/philososkills)