Loading...
Loading...
Found 1,153 Skills
Check for security risks in Skills/code repositories. When the user wants to check if a skill, GitHub repository, npm package, or local code is safe to download or use. This includes detecting malicious code, malware, key stealing, environment variable modification, suspicious network behavior, and evaluating repository reputation (stars, forks, contributors, age). Use this skill whenever the user mentions checking skills for security risks, scanning repositories for malware, verifying code safety, checking npm packages for threats, or asking if a download is safe.
Use this skill when crafting, iterating, or optimizing prompts for LLMs including zero-shot, few-shot, chain-of-thought, role prompting, structured output, and prompt chaining. Not for fine-tuning or training models. Not for evaluating model quality across benchmarks.
Prioritization frameworks — RICE, WSJF, ICE, MoSCoW, and opportunity cost scoring for backlog ranking. Use when prioritizing features, comparing initiatives, justifying roadmap decisions, or evaluating trade-offs between competing work items.
Porter's Five Forces, SWOT analysis, and competitive landscape mapping. Use when analyzing market position, evaluating competitive threats, building battlecards, or assessing industry dynamics.
Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a paper-ready formula document. Use when the derivation target is not yet fully fixed, the main object still needs to be chosen, or the user needs a coherent derivation package rather than a finished theorem proof.
BISON v1.1 — Conviction holder for top 10 Hyperliquid assets by volume. Enters on 4h trend structure + 1h momentum + SM alignment convergence. Holds through pullbacks with DSL High Water Mode (mandatory). Re-evaluates thesis every 5 min — exits when conviction breaks, not when price retraces. Wide Phase 1 floors, no time-based exits, infinite trailing at 85% of peak. v1.1: daily entry cap only enforced when day PnL is negative. When profitable, reloads in batches of 3 — BISON keeps trading as long as it's making money.
Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.
Expert in designing high-level enterprise solutions. Specializes in TOGAF adaptation, trade-off analysis, and aligning technology with business strategy.
Novel Writing Assistant that supports creating novels from scratch, continuing chapters, character design, worldbuilding, etc. Suitable for various genres (science fiction, fantasy, mystery, romance, wuxia, etc.). Trigger scenarios: (1) User requests to write a novel, such as "Help me write a sci-fi novel", "Create a mystery story"; (2) Continue or revise existing content, such as "Continue a chapter for this story", "Revise this character"; (3) Character-related tasks, such as "Help me design a villain character", "Design a love interest for the protagonist"; (4) Worldbuilding, such as "Help me design a magic system", "Build a cyberpunk world."
Coverage analysis measures code exercised during fuzzing. Use when assessing harness effectiveness or identifying fuzzing blockers.
Expert data science covering machine learning, statistical modeling, experimentation, predictive analytics, and advanced analytics.
Voice and tone rules for all written content. Use when writing prose that should sound human and be suitable for reading aloud.