一键在 Manus 中运行任何 Skill

writing-prompt-extra

星标209

分支24

更新时间2026年5月10日 10:48

Writing target-specific .prompt-extra.md files for Specula. Use when: (1) the user is setting up Specula on a new target system, (2) the user asks to write or revise a .prompt-extra.md, (3) the user wants to add bug-family hypotheses, scope guidance, or production-incident context to a target's pipeline runs.

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

specula-org

specula-org/Specula

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

相关职业SOC

基于 SOC 职业分类

其他计算机职业计算机与数学类职业·SOC 15-1299

文件资源管理器

2 个文件

SKILL.md

readonly

name	writing-prompt-extra
description	Writing target-specific .prompt-extra.md files for Specula. Use when: (1) the user is setting up Specula on a new target system, (2) the user asks to write or revise a .prompt-extra.md, (3) the user wants to add bug-family hypotheses, scope guidance, or production-incident context to a target's pipeline runs.

Read guide.md for the full methodology, hard rules, and procedure.

同仓库更多 Skills

同仓库

bug-confirmation

specula-org/Specula

Bug confirmation and reproduction. Use when: (1) a bug has been found by model checking and needs code-level validation, (2) reproducing a bug in the real system to confirm it is not a false positive, (3) assessing whether a TLA+ counterexample maps to a real triggerable scenario.

2026-07-16209

tla-checking-workflow

specula-org/Specula

TLA+ Model Checking workflow. Use when: (1) running TLC model checking or simulation on a TLA+ spec, (2) analyzing counterexamples from invariant violations, (3) determining whether a violation is an invariant mismatch, a spec issue, or a real bug in the system implementation.

2026-07-16209

bug-classification

specula-org/Specula

Severity classification of Phase 4a results. Assign severity to REPRODUCED bugs and ENV_LIMITED/MASKED findings, while recording non-severity dispositions such as FALSE POSITIVE, PENDING REPAIR, DEFERRED, and INCOMPLETE.

2026-07-12209

validation-workflow

specula-org/Specula

TLA+ Verification workflow (orchestration). Use when: running the full verification loop — iterating between trace validation and model checking until both pass, ensuring spec faithfully models the system.

2026-07-12209

harness-generation

specula-org/Specula

Trace harness generation (Phase 2.5). Use when: (1) instrumenting a system's source code to emit NDJSON traces for TLA+ trace validation, (2) writing test scenarios that exercise protocol code paths, (3) producing the first batch of traces from instrumented tests.

2026-06-30209

tla-trace-workflow

specula-org/Specula

TLA+ Trace Validation workflow. Use when: (1) validating if a trace matches a TLA+ spec, (2) debugging trace validation failures (TLC reports 'Temporal properties were violated' or validation stops unexpectedly), (3) fixing spec/trace inconsistencies after root cause is identified.

2026-05-20209

一键运行任何 Skill