ワンクリックでManusで任意のスキルを実行

vision-factory

スター2

フォーク0

更新日2026年5月21日 19:55

Forge, validate, and stress-test a startup vision using Paul Graham's filters. Three modes — CREATE (Socratic grilling → vision narrative), RESEARCH (extract claims → execute research → validation report), STRESS-TEST (10-filter PG rubric → hardened vision). Load on "vision", "create/build/write a vision", "validate/stress-test/pressure-test a vision", "one-pager", "north star", "founding narrative".

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

mreza0100

mreza0100/professor

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

Codex-only execution mapping

Mode A interview asks one question at a time — surface each question and wait for the founder's answer.
Mode B research executes via the shared RR skill (or the project's research pipeline) — internal, no intermediate prompt handed to the user.
Artifacts (vision-draft.md, vision-research.md, vision-scorecard.md) save where the user specifies. No commits.

このリポジトリの他の Skills

同じリポジトリ

wave-build

mreza0100/professor

Cross-project build pipeline. Invoked as $wave-build <feature> or $wave-build with Pipeline/Task manifest/Wave args. Runs the full pipeline end to end including all git work.

2026-07-052

wave

mreza0100/professor

Wave task runner. Reads a wave.md file and runs each pipeline sequentially. Invoked as `$wave <path/to/wave.md>`. Argument is the path to the wave manifest file.

2026-07-052

p-tokens

mreza0100/professor

Attributes Claude Code runtime token spend per sub-agent and per workflow run, parsed from local JSONL transcripts, and ranks the heaviest burners with estimated USD cost. Answers 'which agent burned the most tokens', 'what did this workflow/wave/pipeline cost', 'token breakdown', 'per-operation tokens', and any retrospective spend analysis. Triggered by 'token ledger', 'token attribution', 'heaviest token burner', 'which agent burned the most tokens', 'what did the run/workflow/wave cost', 'token breakdown', 'per-agent tokens', 'per-operation tokens'. Complements /pcm:context-meter: that audits STATIC context size, this covers RUNTIME spend attribution — route static-budget questions to context-meter, after-the-fact spend questions here.

2026-07-052

audit-code-hygiene

mreza0100/professor

Code hygiene audit — ghost fields, dead code, deps, arch, types, naming, quality. Domain-hydrated at install time.

2026-06-172

audit-security

mreza0100/professor

Security deep scan — injection, auth, API, LLM/prompt, sensitive data, crypto, transport, supply-chain. Domain-hydrated at install time.

2026-06-172

p-360

mreza0100/professor

Exhaustive multi-angle analysis. Invoked by `360`, `three-sixty`, `do a 360`, "what could go wrong", or explicit blind-spot sweep requests.

2026-06-172

name

vision-factory

description

Read .claude/skills/vision-factory/SKILL.md in full — it is the source-of-truth protocol, and read the references/*.md it points to as each mode instructs. Follow it verbatim.

Codex-only execution mapping

Mode A interview asks one question at a time — surface each question and wait for the founder's answer.
Mode B research executes via the shared RR skill (or the project's research pipeline) — internal, no intermediate prompt handed to the user.
Artifacts (vision-draft.md, vision-research.md, vision-scorecard.md) save where the user specifies. No commits.