一个技能，一个新的可能。找到适合你的 AI 工作流。
alibabacloud-pts-task
【开发与工程】Alibaba Cloud PTS task CRUD worker skill — executes concrete PTS scenario operations (create / query / start / stop / report / delete) for both PTS native HTTP/HTTPS and JMeter-based stress testing. This is a WORKER skill, typically delegated from the `alibabacloud-pts-pilot` router. Do NOT use this skill for tuning advice or general PTS Q&A. Trigger…
sidechain-setup
【效率与协作】Use when the user wants to set up sidechain compression - typically kick → bass, kick → pads, vocals → music bed. Examples - "sidechain my bass to the kick", "make the synths duck under the vocal", "add pumping to the chords".
tracing-with-chrome
【开发与工程】Use when running a Chrome lab trace for a specific CWV bottleneck — investigating LCP/INP/CLS with browser tools after RUM has identified the target phase, element, and cause. Typically called by the cwv-superpower orchestrator at Step 3. Requires either chrome-devtools-mcp (preferred) or claude-in-chrome (fallback).
deduplicate-security-issue
【效率与协作】Merge two <tracker> tracking issues that describe the same root-cause vulnerability (typically discovered independently by two reporters, arriving via different channels), preserving every reporter's credit, every mailing-list thread reference, and every independent attack-vector description. Updates the kept issue's body in place, closes the duplica…
deploying-ransomware-canary-files
【部署与运维】Deploys and monitors ransomware canary files across critical directories using Python's watchdog library for real-time filesystem event detection. Places strategically named decoy files that mimic high-value targets (financial records, credentials, database exports) in locations ransomware typically enumerates first. Monitors for any read, modify, re…
github-voice
【开发与工程】Shared writing style rules for GitHub-facing output (PR comments, PR descriptions, PR titles). Differentiates insider vs outsider voice based on author association. Not typically invoked directly — loaded by other skills before composing GitHub text.
import-security-issue-from-md
【开发与工程】Open one or more `<tracker>` tracking issues from a markdown file containing a batch of security findings (typically the output of an AI security review or a third-party scanner). Each finding in the file becomes one tracker, landing in the `Needs triage` board column with the standard issue-template body fields populated from the markdown sections. …
security-issue-deduplicate
【效率与协作】Merge two <tracker> tracking issues that describe the same root-cause vulnerability (typically discovered independently by two reporters, arriving via different channels), preserving every reporter's credit, every mailing-list thread reference, and every independent attack-vector description. Updates the kept issue's body in place, closes the duplica…
security-issue-import-from-md
【开发与工程】Open one or more `<tracker>` tracking issues from a markdown file containing a batch of security findings (typically the output of an AI security review or a third-party scanner). Each finding in the file becomes one tracker, landing in the `Needs triage` board column with the standard issue-template body fields populated from the markdown sections. …
agentic-r-learning-to-retrieve-for-agentic-search
【设计与创意】Agentic search has recently emerged as a powerful paradigm, where an agent interleaves multi-step reasoning with on-demand retrieval to solve complex questions. Despite its success, how to design a retriever for agentic search remains largely underexplored. Existing search agents typically rely on similarity-based retrievers, while similar passages a…
ak-maintainer
【开发与工程】Manage authorized project work through Agent Kanban and Realmroot Toolbox, typically in scheduled-task or heartbeat-triggered Sessions. Proactively inspect what needs doing, delegate execution to other Agents, and coordinate and review their Tasks as a manager.
alfworld-object-state-inspector
【开发与工程】Checks the current state or contents of a specified object or receptacle. Trigger this skill when the agent needs to determine if an object is present, missing, or in a certain condition before proceeding with a task, such as verifying if a holder is empty or if an item is available. It typically follows navigation and involves observing the environm…
asr-rebuttal
【开发与工程】Use when writing the response to an American Sociological Review (ASR) revise-and-resubmit. ASR R&Rs typically demand substantial revision and reviewers may span different methodological traditions, so the response must convert each reviewer while keeping the editor confident. Structures the response letter; it does not fabricate new results.
auditor-frontend-ui-ux
【设计与创意】Audit frontend code quality, UI/UX, forms, state management, and translations. Typically loaded by the audit-orchestrator skill via sub-agents, but can be used standalone.
cash-collateral-motion
【效率与协作】Drafts motions to use cash collateral under 11 U.S.C. § 363. Use when a debtor-in-possession needs court authorization to use cash collateral, typically as a first-day pleading.
cash-collateral-motion
【效率与协作】Drafts motions to use cash collateral under 11 U.S.C. § 363. Use when a debtor-in-possession needs court authorization to use cash collateral, typically as a first-day pleading.
ceq-rebuttal
【开发与工程】Use when drafting the response letter for a revise-and-resubmit (R&R) at 《经济学(季刊)》 (China Economic Quarterly, CEQ) — where reviewers are typically field-trained and press hardest on identification, modern-DID compliance, and inference. Structures a point-by-point reply that concedes or rebuts with evidence. Use only after the manuscript itself has be…
choose-a-focus-that-suits-you-best
【数据与研究】This prompt asks the AI to use the user’s year in school, major, and chosen subject to recommend advanced, research-oriented topics aligned with current trends in that field. The result is a tailored shortlist of specialized areas to explore—typically highlighting emerging subfields, key methods or technologies, and promising research directions suit…