paul-graham skills

21 tagged paul-graham, measured the same way as everything else here.

Browse within: guodegang 16mrbeast 16skills-expert 16zhangxuefeng 16llm-tools 5

hall-of-fame

01

konglong87/hall-of-fame

Skill Claude CodeCodex

Part of hall-of-fame

A collection of 13 expert-perspective skills with a router that chooses one based on keywords or language-model classification. It then loads that expert’s instructions and responds in the selected style.

11 1mo ago A 95 tokens original MIT

mrbeast-perspective

02

konglong87/hall-of-fame

Skill Claude CodeCodex

Part of hall-of-fame

A content-planning guide based on publicly discussed methods associated with MrBeast, a major online video creator. It presents advice in his first-person style and focuses on titles, thumbnails, openings, pacing, and audience retention.

11 1mo ago A 241 tokens original MIT

konglong87/hall-of-fame

Skill Claude CodeCodex

Part of hall-of-fame

A role-play skill based on Zhang Yiming’s public ideas about products, organizations, international growth, talent, and personal development. It frames questions as systems that can be examined with data and feedback.

11 1mo ago A 229 tokens original MIT

WinterDDo/paul-graham-skills

Skill Claude CodeCodex

Apply when an attempt at a task has failed, when Claude is debugging, when a previous answer did not work, when iterating on a solution that is not converging, or when the user reports that the last response missed the mark. Critical trigger: any moment where the temptation is to retry the same approach with cosmetic…

4 4mo ago A 93 tokens

WinterDDo/paul-graham-skills

Skill Claude CodeCodex

Apply when Claude is in any mode of investigation, analysis, critique, or disagreement. Triggers especially when: the user pushes back on a previous Claude position, Claude finds a conclusion that contradicts what the user seems to want, Claude is reviewing the user's work, or Claude is being asked to evaluate…

4 4mo ago A 110 tokens

WinterDDo/paul-graham-skills

Skill Claude CodeCodex

Apply whenever Claude is making any claim, recommendation, factual statement, or analysis. Always-on for any non-trivial assertion. Triggers especially when: Claude is producing content in domains where its training data is uneven, when the user is asking for facts Claude is not certain of, when the analysis depends…

4 4mo ago A 122 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: