Results for “cloze-questions”

Fuzz Rust projects with libFuzzer using cargo-fuzz, including harness writing, sanitizer integration, and coverage analysis.

对 wiki 提问，综合检索相关页面后回答，好的回答可 crystallize 回 wiki

Load this skill when the user says "close issue", "close-issue", or "/close-issue". Verifies IT and UC acceptance criteria for a story issue, ticks off passing checkboxes, and closes the issue only if all criteria pass and the linked PR has been merged.

融合未来蓝图与虚空凝视能力，通过批判性思维构建未来愿景，突破传统界限，创造新的未来可能性。

Gera até cinco perguntas dirigidas para resolver pontos ambíguos do requirements e integra as respostas no documento. Use quando o usuário digitar "/reversa-clarify", "reversa-clarify", "esclarecer dúvidas" ou pedir para tirar pontos abertos do requirements antes de planejar. Etapa opcional do ciclo forward, entre `/reversa-requirements` e `/reversa-plan`.

Applies TRIZ cross-domain analogical reasoning to find solutions from adjacent fields. Use when stuck on a problem and needing inventive perspectives.

Adversarial one-question-at-a-time questioning to verify deep reading comprehension of alignment pages, specs, or any document

Ask a local external advisor CLI (Claude or Gemini) and capture a reusable artifact

Investigate and fix bugs, crashes, null references, and runtime errors in QuizVerse.

Deprecated compatibility shim for Claude advisor requests

Clarify requirements before implementing by asking targeted questions when a request has multiple plausible interpretations or key details are unclear.

Patch code to bypass checksums, global state, and validation checks that block fuzzer progress, using conditional compilation for C/C++ and Rust.

Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.

融合分类系统与虚空凝视能力，通过批判性思维突破传统分类边界，创造新的分类视角。

Runs a relentless interview that sharpens a plan or design. Use when the user wants to be grilled on an idea, pressure-test a plan, or refine a design through questioning.

Restrict file edits to a specific directory for the session. (gstack)

Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")

Routes short slash commands to Claude Code relay sessions, including starting, stopping, and tailing sessions, and forwarding messages in relay mode.

Restrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Use when debugging to prevent accidentally "fixing" unrelated code, or when you want to scope changes to one module. Use when asked to "freeze", "restrict edits", "only edit this folder", or "lock down edits". (gstack)

Restrict file edits to a specific directory for the session. (gstack)

Clarifies ambiguous or conflicting requests by researching first, then asking only judgment calls. Use when prompts say "grill me", ask hard questions, request relentless interrogation, pressure-test assumptions, clarify scope/requirements, define success criteria, or request system-design/optimization decisions.

在创造之前先进行解构，突破当前限制的幻觉。当需要批判性思维、假设挑战或可能性扩展时调用。

Query Google Places for text search, place details, resolve, reviews, or scriptable JSON via goplaces.

Put the user in the hot seat — one question at a time until their plan, decision, or idea actually holds up. Use whenever the user says "hot seat me", "grill me", "stress-test this", "poke holes in this", "am I missing anything", or drops a plan and wants it challenged before anyone acts on it — even if they never say the words. Also used as a sub-procedure by the whiteboard and connotation-cop skills.