一键在 Manus 中运行任何 Skill

gpt5-5-prompt-grill

星标5

分支1

更新时间2026年7月9日 09:02

Pressure-test, reduce, and rewrite prompts for GPT-5.5. Use when the user asks to grill, audit, critique, harden, improve, optimize, simplify, de-noise, or rewrite a prompt, system prompt, developer instruction, agent playbook, or tool-use workflow specifically for GPT-5.5; especially when it may contain no-op instructions, contradictions, vague rules, missing success criteria, missing output rules, missing validation, unsupported claims, or unclear stop rules.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

flpbalada

flpbalada/fb-skills

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

GPT-5.5 Prompt Grill

Make GPT-5.5 prompts shorter, sharper, and executable.

Flow

Read references/primitives.md.
Read the prompt, failure examples, and desired behavior.
Ask for the prompt only if it is missing.
Classify each issue as blocker, no-op, or rewrite.
Ask only when the missing answer changes behavior; include a recommended answer.
Rewrite after blockers are clear.
Re-check the rewrite against the primitives.
Use TEMPLATE.md.

Rules

Preserve intent, useful constraints, and examples.
Remove no-ops: vague, duplicated, decorative, or intensity-only rules.
Replace vague quality words with observable behavior.
Keep only instructions that change behavior, output, validation, tool use, evidence, or priority.
Use cause -> effect -> fix.
Do not invent product facts, metrics, tools, policies, or model capabilities.

同仓库更多 Skills

同仓库

answer-open-questions

flpbalada/fb-skills

Analyze a list of open questions and suggest up to three answers for each. Use when the user wants options, recommendations, or help resolving multiple unanswered questions.

2026-07-155

prd-delivery

flpbalada/fb-skills

Deliver a PRD through orchestrated task decomposition, implementation agents, and independent QA. Use when every acceptance criterion must be verified before completion.

2026-07-145

explain-yesterday-changes

flpbalada/fb-skills

Explain changes made yesterday as a simple list. Use when user asks what changed yesterday, what was implemented yesterday, or needs a non-technical change summary from recent git work.

2026-07-145

discuss-task

flpbalada/fb-skills

Build shared understanding before action by interviewing the user about ambiguous implementation, product, planning, or design tasks. Use when goal, scope, constraints, risks, success criteria, done state, or next action are unclear; when user wants a thinking partner; or when user needs a handoff-ready task prompt. Do not write PRDs; use to-prd for product requirements.

2026-07-095

codebase-slop-audit

flpbalada/fb-skills

Detect sloppy-code signals with repo-wide search metrics and sampled evidence. Use when asked to audit codebase quality, "vibe coding", `isRecord`, broad `Record<string, unknown>` guards, fallback usage, excessive null guards, non-null assertions, unsafe type assertions, `node:*` imports in browser/shared code, swallowed errors, TODO debt, or code smell hotspots before refactoring.

2026-07-085

prd-loc-estimator

flpbalada/fb-skills

Estimate line additions and deletions from a PRD or spec by reading the requirements and inspecting the target repo. Use when the user asks for changed LOC, additions, deletions, diff size, PR size, or implementation size before building.

2026-07-065

name

gpt5-5-prompt-grill

description

GPT-5.5 Prompt Grill

Make GPT-5.5 prompts shorter, sharper, and executable.

Flow

Read references/primitives.md.
Read the prompt, failure examples, and desired behavior.
Ask for the prompt only if it is missing.
Classify each issue as blocker, no-op, or rewrite.
Ask only when the missing answer changes behavior; include a recommended answer.
Rewrite after blockers are clear.
Re-check the rewrite against the primitives.
Use TEMPLATE.md.

Rules

Preserve intent, useful constraints, and examples.
Remove no-ops: vague, duplicated, decorative, or intensity-only rules.
Replace vague quality words with observable behavior.
Keep only instructions that change behavior, output, validation, tool use, evidence, or priority.
Use cause -> effect -> fix.
Do not invent product facts, metrics, tools, policies, or model capabilities.