press-conference-principle

Guides editorial selection and framing decisions when writing and revising research papers.

Updated Aug 26, 2026
One-click install
npx skills add https://github.com/coollx/stable-harness --skill press-conference-principle-coollx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: press-conference-principle
Source: https://github.com/coollx/stable-harness/tree/main/paper/.claude/skills/press-conference-principle
Command: npx skills add https://github.com/coollx/stable-harness --skill press-conference-principle-coollx

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Research papers often read like experiment logs or progress reports, burying the strongest contributions under unfavorable results, self-deprecating language, and unfocused comparisons. This Skill provides editorial principles for deciding what to include, emphasize, de-emphasize, or delete so the paper presents its strongest defensible narrative. ## Core Features & Use Cases - Editorial Selection Rules: Twelve core requirements governing how to organize a paper around its genuine strengths, avoid volunteering weaknesses, and control the scope of comparisons. - Default Decision Rule: A seven-step priority order for handling unfavorable material, from deleting irrelevant content to redefining the paper's story. - Honesty Boundaries: Explicit constraints ensuring framing never misstates numbers, that required limitations sections are still written, and that losing comparisons are handled as a last resort. - Use Case: When revising an experiments section where the method loses on one benchmark, apply the decision rule to narrow the claim, reframe the comparison around a winnable dimension, and keep the headline result as the narrative center. ## Quick Start Use the press-conference-principle skill to review and restructure the experiments section of my paper draft around its strongest results.

Frequently Asked Questions about press-conference-principle

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I decide which results to highlight in a research paper?

Identify what is genuinely leading, unique, or irreplaceable in the work, such as a new capability, lower cost, or better scalability, and organize the paper around that strength. Results that do not support the core claim should be de-emphasized, moved, or deleted rather than presented evenly.

How should I present unfavorable experimental results in a paper?

Follow a priority order: delete irrelevant content, narrow the claim, switch to a more meaningful evaluation dimension, or interpret the result as a tradeoff. Only when the shortfall affects a headline claim should you concede it, always paired with a mitigation or boundary explanation.

Does framing a paper around strengths mean hiding weaknesses?

No. Required limitations sections are still written, and numbers must never be misstated. The principle governs what to raise and how to frame it, not what the facts are; claims the evidence cannot support are narrowed or dropped, not restated more favorably.

When should I rewrite a paper's storyline instead of defending it?

When the results cannot support the original narrative, redefine the problem the paper solves, reorder contributions, and reselect headline results. The story should serve the strongest evidence rather than fidelity to the initial conception.

What sections of a research paper does this editorial guidance cover?

It covers every section: abstract, introduction, related work, method, experiments, results, conclusion, and limitations. It applies whenever drafting, revising, compressing, or restructuring, even for requests framed as polishing or shortening.