skill CX Codex

propose-hypotheses — Claude Code skill: full FPF cycle

Q: How do I install propose-hypotheses in Claude?

Run `npx skills add NeoLabHQ/context-engineering-kit --skill propose-hypotheses -a claude-code`. The skill lands at `~/.claude/skills/propose-hypotheses/SKILL.md`.

Q: Where does the skill keep its output?

Inside `.fpf/`: context in `.fpf/context.md`, hypotheses by level under `.fpf/knowledge/`, audit reports in `.fpf/evidence/` and the decision record in `.fpf/decisions/`.

Runs the whole First Principles Framework cycle: generates competing hypotheses, verifies logic, validates evidence and produces a decision record.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓

npx skills add NeoLabHQ/context-engineering-kit --skill propose-hypotheses -a claude-code

Open on GitHub

What propose-hypotheses does

The skill scaffolds a .fpf/ directory with evidence, decisions, sessions and knowledge folders split into L0, L1, L2 and invalid. An fpf-agent subagent on the sonnet[1m] model then reads your problem, writes context to .fpf/context.md and drops hypotheses into .fpf/knowledge/L0/.

From there it is a pipeline. Parallel subagents verify each L0 hypothesis and move it to L1 or to invalid. Survivors get their evidence validated and land in L2. A trust audit then scores R_eff and names the weakest link, with the report saved under .fpf/evidence/. The last step writes a decision record to .fpf/decisions/ with a table of hypotheses, scores and statuses.

Between stages the skill asks whether you want to add hypotheses of your own and loops on that step until you decline. Everything runs through subagents, so you need a platform that can launch them in parallel — Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode all install it with one command. Once a decision exists, the skill points you to /fpf:status for the current state or /fpf:actualize when the codebase has moved on.

What it helps with

break a vague problem into competing hypotheses
drop hypotheses with broken logic before writing code
check what actually backs each hypothesis
score trust in the conclusions and find the weakest link
record the chosen option with its rationale in a file

Example prompts for the agent

Run propose-hypotheses: we need to pick how to store user sessions
Take this through the FPF cycle: rewrite the auth layer around tokens
propose-hypotheses: should background jobs move to a separate service

How to install propose-hypotheses

1Skills CLI (Vercel)

npx skills add NeoLabHQ/context-engineering-kit --skill propose-hypotheses -a claude-code

2Manually: put the files in place

~/.claude/skills/propose-hypotheses/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/propose-hypotheses/

1Skills CLI (Vercel)

npx skills add NeoLabHQ/context-engineering-kit --skill propose-hypotheses -a codex

2Manually: put the files in place

.agents/skills/propose-hypotheses/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add NeoLabHQ/context-engineering-kit --skill propose-hypotheses -a cursor

2Manually: put the files in place

.cursor/skills/propose-hypotheses/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install NeoLabHQ/context-engineering-kit propose-hypotheses

2Manually: put the files in place

.github/skills/propose-hypotheses/SKILL.md

1Skills CLI (Vercel)

npx skills add NeoLabHQ/context-engineering-kit --skill propose-hypotheses -a gemini-cli

2Platform CLI

gemini skills install https://github.com/NeoLabHQ/context-engineering-kit --path skills/propose-hypotheses

Manually: put the files in place

.devin/skills/propose-hypotheses/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add NeoLabHQ/context-engineering-kit --skill propose-hypotheses -a opencode

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about propose-hypotheses

How do I install propose-hypotheses in Claude?

Run npx skills add NeoLabHQ/context-engineering-kit --skill propose-hypotheses -a claude-code. The skill lands at ~/.claude/skills/propose-hypotheses/SKILL.md.

What does propose-hypotheses do?

It executes the First Principles Framework cycle: generate hypotheses, verify their logic, validate evidence, audit trust and write a decision record to .fpf/decisions/.

Where does the skill keep its output?

Inside .fpf/: context in .fpf/context.md, hypotheses by level under .fpf/knowledge/, audit reports in .fpf/evidence/ and the decision record in .fpf/decisions/.

thinking-model-router tjboudreaux A router skill that maps domain and problem type to one thinking skill, or returns NONE. Useful when you would otherwise guess or stack frameworks. CX Codex +1 605installs openspec-propose openspec Generates a complete OpenSpec proposal with design, spec deltas, and implementation tasks in one run. Ideal for scoping changes before editing codebase files. CX Codex +1 4,000installs asb-interview-hypotheses asmartbear Turns your guesses about customers into numbered, falsifiable statements mapped to your goal questions. Use it before you start interviewing. CX Codex +1 630installs propose-security-hardening official OpenAI This skill turns vulnerability evidence and scan findings into architectural hardening options. Use it when a single-finding patch does not address the wider design. CX Codex GP ChatGPT 13installs critical-thinking-logical-reasoning sammcj A skill that picks apart the reasoning in written content: articles, transcripts, reports. Not code, and only when you explicitly ask for a critique. CX Codex +1 2,400installs consciousness-council K-Dense-AI Runs a council of thinking archetypes over a hard choice, keeps facts apart from assumptions and values, and returns a conditional recommendation. CX Codex +1 1,900installs

From the same set55

multi-agent-patterns A skill that lays out three ways to split work across subagents: supervisor, peer-to-peer and hierarchical. Useful once one agent runs out of context. CX Codex +1 1,300installs write-concisely This skill enforces classic style rules from William Strunk Jr.'s 1918 guide across human-facing docs. It strips filler words and switches passive phrasing into active voice. CX Codex +1 1,300installs setup-codemap-cli Configures the Codemap CLI utility to inspect project file trees and module dependencies. Helpful when giving an AI agent clear architectural context across Git branches. CX Codex +1 1,200installs load-issues The skill pulls every open issue from the current repository with gh and writes each one to its own markdown file. Handy when you want tasks outside GitHub. CX Codex +1 1,200installs create-command Interactive helper for drafting custom slash commands. Configures frontmatter, argument handling, and pre-run bash context. CX Codex +1 1,200installs setup-arxiv-mcp Sets up an academic paper search MCP server through Docker MCP and records its tools in CLAUDE.md. Use it when an agent needs to search or read research papers. CX Codex +1 1,200installs attach-review-to-pr This skill shows the agent how to post review comments on specific lines of a pull request using GitHub CLI or an MCP tool. Handy when review happens in the terminal. CX Codex +1 1,200installs git-worktrees Teaches your AI coding assistant to manage multiple linked Git working trees. Helpful for handling hotfixes, PR reviews, and parallel builds without stashing changes. CX Codex +1 1,200installs