Loading...
Loading...
Found 1,287 Skills
A workflow for generating video titles and saving them to disk. Use when the user asks to title a finished or planned video, especially for Douyin/Xiaohongshu video titles, 视频标题.md, a title file in the same directory as the final video, common patterns in benchmark titles, two-part titles, generating a title from the video topic, titles after content rewriting, or replacing the generic dbs-xhs-title for video titles. It first identifies the actual topic, studies benchmark title patterns when provided, generates 8-12 topic-first two-part candidates, recommends or selects one, and writes 视频标题.md next to the final MP4 when requested.
Use when putting the agent in this repository on a Veris Bench bench as a "Your image" candidate, when updating that candidate to a new version, or when its bench attempts show empty replies, failed tool calls, no model calls for the grader, or never reach the bench's twins.
Query IBM i software products, licensing, and product health via SQL services. Use when user asks about: (1) installed software products and versions, (2) product details for a specific product ID, (3) software products with load errors, (4) license compliance and usage limits, (5) unsupported or incompatible products, (6) replacing DSPSFWRSC, WRKLICINF, DSPPTF commands, or (7) any software product management task.
Assess IBM i security posture including user privileges, object authorities, vulnerability detection, and function usage via SQL services. Use when user asks about: (1) user profiles with special authorities or limited capabilities, (2) object privileges and *PUBLIC authority exposure, (3) files vulnerable to trigger, rename, or library list attacks, (4) user impersonation vulnerabilities, (5) group profile membership, (6) function usage and access control, (7) security audit and compliance, or (8) replacing WRKOBJAUT, DSPUSRPRF, DSPAUTL commands.
Monitor and analyze PTFs, PTF groups, and system patching status on IBM i via SQL services. Use when user asks about: (1) PTF group currency or update status, (2) finding outdated or critical PTF groups, (3) individual PTF details by product, (4) installed PTF group levels, (5) defective PTF checks, (6) PTF patching summaries, (7) replacing DSPPTF, WRKPTFGRP commands, or (8) any PTF management or compliance task.
Manage and query IBM i library lists, library contents, authorization lists, and object privileges via SQL services. Use when user asks about: (1) current library list configuration, (2) library contents and object inventory, (3) authorization lists and secured objects, (4) object-level privilege details, (5) library information and sizes, (6) system vs user library list entries, (7) replacing DSPLIBL, DSPLIB, DSPAUTL, DSPOBJAUT commands, or (8) any library management task.
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting Z-Wave smart home devices (door locks, sensors, garage controllers) — common in mid-2010s smart home deployments still in production.
Use when upgrading a Spree 5.x application to Spree 6.0, or when fixing code that broke after that upgrade. Common phrasings include "upgrade to Spree 6", "migrate from 5.6 to 6.0", "Spree 6 breaking changes", "checkout_flow / state machine is gone", "Spree::Adjustment not found", "master variant removed", "PermissionSets NameError", "staff locked out after upgrade", "what replaced Shipment / Taxon / ReturnAuthorization / metafields", "spree_admin gem not found". Covers preconditions (5.6 first, Rails 8.1, Gemfile swaps, roles as data), the ordered 5.6 → 6.0 data backfills, grep recipes for code that must change, and the behavioral review checklist.
Use when working with post-purchase flows in Spree 6 — returns (money back), exchanges (different items), and claims (damaged / missing / wrong item, refund or replacement without the goods coming back). Covers Spree::Return / Spree::Exchange / Spree::Claim, their statuses and workflows, return windows per market and staff overrides, custom return policy via the returns.create.validate hook, receiving and restocking (resellable), refunds to the original payment vs store credit, prepaid return labels, return and claim reasons, events, and the Store/Admin API endpoints. Common phrasings include "RMA", "return window", "30-day returns", "final sale items can't be returned", "restock returned items", "refund a return", "store credit refund", "exchange for a different size", "item arrived damaged", "send a replacement", "return label", "ReturnAuthorization", "CustomerReturn", "Reimbursement".
Use when the user wants to run custom code inside a Spree 6 business flow — veto an add-to-cart, block checkout completion, enforce a purchase limit or B2B rule, add data to tax or promotion calculation, react inside the order-placement transaction, customize returns eligibility, or write a new multi-step operation with compensation and gateway calls. Common phrasings include "Spree.hooks.register", "workflow hook", "carts.add_item.validate", "carts.complete.before_finalize", "set_tax_line_context", "reject!", "Spree::Workflow", "step / external_step / on_flow_failure", "run_hooks", "halt!", "has_status", "add_status", "state machine replacement", "where do I put business logic", "step.spree_workflow", "trace a workflow". Covers services vs workflows, the three hook kinds, the hook catalog, writing your own workflow, statuses, instrumentation and testing. Reach for this BEFORE swapping a class via Spree.dependencies or decorating a model.
Use when the user wants to replace a whole Spree 6 service, workflow or API serializer with their own class — swap the add-to-cart workflow, checkout completion, cart totals recalculation, order status writer, storefront access policy, or an API v3 serializer. Common phrasings include "Spree.dependencies", "Spree::Dependencies", "swap a service", "replace Spree::Carts::AddItem", "cart_add_item_workflow", "carts_complete_workflow", "cart_recalculate_totals_workflow", "storefront_access_policy_class", "override an API serializer", "Spree.api.product_serializer", "dependency injection in Spree", "spree:dependencies:list", "spree:dependencies:overrides", "my cart_add_item_service override stopped working", "what can I swap". Covers when a swap is justified (usually a workflow hook is better), subclassing a shipped workflow, service vs workflow seams, legacy *_service keys that are stashed not applied, API serializer seams, per-controller overrides, and the introspection rake tasks.
Implement a chosen contribution in a fork of an open-source project: verify the user's fork already exists (stop and ask the user to fork if it does not), strictly follow the upstream repository's conventions (CONTRIBUTING.md, AGENTS.md, CLAUDE.md, PR template, commit and sign-off format), work on a branch of the fork without opening any fork PR, write equivalence-first tests, run the upstream CI/CD checks locally before pushing (the fork will not run them), sign commits per the upstream DCO/CLA convention, and post the PR body — built from the upstream PR template — in a markdown pasteable format on the Multica issue. In review iterations (the PR is already open and a maintainer left review comments), address only the explicit requests on the same fork branch and post a pasteable PR comment per PR in the same fenced-markdown format; PR discussions — replies, resolutions, ambiguous asks — are left for the humans. Use whenever a Multica issue asks to "work on the contribution", "implement <candidate> in <owner/repo>", "prepare the branch for <repo>", "turn the scouted contribution into a PR-ready diff", or to "address the review comments on <PR>" — even if the issue only names the target repo and the change to make.