提示词与推理

gemini

2.2Kprompting-reasoning

Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.

softaworks

sequential-thinking

2.2Kprompting-reasoning

Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.

mrgoonie

acestep

2.2Kprompting-reasoning

AI music generation with ACE-Step 1.5 — background music, vocal tracks, covers, stem extraction, audio repainting, and continuation for video production. Use when generating music, soundtracks, jingles, or working with audio stems. Triggers include background music, soundtrack, jingle, music generation, stem extraction, cover, style transfer, repaint, continuation, or musical composition tasks.

digitalsamba

llm-council

2.1Kprompting-reasoning

Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.

aiwithremy

high-output-management

2Kprompting-reasoning

Manage for output using Grove''s "High Output Management": a manager''s output is their organization''s output, raised by high-leverage activities. Use when the user mentions "high output management", "managerial leverage", "one-on-ones", "1:1 agenda", "OKRs", "performance review", "task-relevant maturity", "delegation", "meeting overload", "new manager", "how do I run a 1:1", or "just got promoted to manager". Also trigger when structuring a manager''s calendar and meeting cadence, designing team metrics, running planning, coaching delegation, or preparing performance reviews. Covers leverage, production principles, meetings as the medium of management, decisions, OKRs, and task-relevant maturity. For intrinsic motivation, see drive-motivation. For a company operating system, see traction-eos.

wondelai

skill-optimizer

1.9Kprompting-reasoning

Optimizes AI skills for activation, clarity, and cross-model reliability. Use when creating or editing skill packs, diagnosing weak skill uptake, reducing regressions, tuning instruction salience, improving examples, shrinking context cost, or setting benchmark/release gates for skills. Trigger terms: skill optimization, activation gap, benchmark skill, with/without skill delta, regression, context budget, prompt salience.

mcollina

omp-delegate

1.9Kprompting-reasoning

Delegate a coding task to Oh My Pi (`omp`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Oh My Pi / omp - phrasings like "have omp implement X", "delegate this to oh my pi", "run it through omp", "use oh-my-pi to implement/fix/refactor" - or wants to run a queue of coding tasks through omp while staying the reviewer. DO NOT USE for tasks small enough to do inline, when the user wants the code written directly without delegating, or when they mean the original Pi CLI (`pi`) — that is pi-delegate.

amelnagdy

claude-reflect

Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.

bayramannakov

reset

Reset the FPF reasoning cycle to start fresh

create-agent

Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns

test-prompt

Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing

agent-evaluation

Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.

unlazy

Enforces completion discipline for substantial autonomous work by writing acceptance gates before execution, decomposing work with the Depth Tree, running approved checks, and re-verifying evidence before reporting. Use when Codex faces a long or multi-part task, work that has returned half-done, an exhaustive audit or build, parallel leaves or pipelines, or explicit triggers such as /unlazy, $unlazy, "tree N", "gates", and "do not stop until it is done".

leonxlnx

implement-task

Implement a task step by step with automated LLM-as-Judge verification at the end of each phase

write-judge-prompt

Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.

hamelsmu

error-analysis

Help the user systematically identify and categorize failure modes in an LLM pipeline by reading traces. Use when starting a new eval project, after significant pipeline changes (new features, model switches, prompt rewrites), when production metrics drop, or after incidents.

hamelsmu

generate-synthetic-data

Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.

hamelsmu

shuorenhua

按用户要求审稿或去 AI 味，支持中英文；保留事实、术语与责任主体，支持只标问题。

mrgediao

brainstorm

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

mantis-structural-index

Builds a content-addressed semantic-unit index from source code for structural context. Use when a pinned or live codebase is available and structural cross-reference data would improve research quality. Don't use for findings analysis, patching, or reporting.

google

thought-based-reasoning

Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting fails - provides comprehensive guide to Chain-of-Thought and related prompting techniques (Zero-shot CoT, Self-Consistency, Tree of Thoughts, Least-to-Most, ReAct, PAL, Reflexion) with templates, decision matrices, and research-backed patterns

mantis-summarize

Pre-processes the repository by generating security-focused summaries (mantis-summary.md) for each directory to make planning and research more efficient. Use when starting a review campaign to map the codebase before threat modeling and planning. Don't use for executing code reviews, writing test scripts, or patching code.

google

mantis-review

Independently reviews findings and filters out false positives. Use when consolidated findings need validation against the actual source code. Don't use for reproducing crashes or patching code.

google