Loading...
Loading...
Found 2,164 Skills
Guides product support specialist work—customer tickets about how the product works, configuration, permissions, workflows, and expected behavior; empathetic replies, triage and routing, macro and KB guidance, feature-request capture, and escalation to technical support or product when needed. Use when answering "how do I…" questions, clarifying plan limits, drafting support responses, deciding bug vs education vs config issue, or documenting feedback—not for deep log/API debugging and engineering repro (support-engineer), billing/dunning programs (customer-ops-specialist), exec/VIP escalation programs (community-executive-escalations-program-manager), or public API reference authoring (tech-writer-researcher), or structured developer training programs (developer-education-lead).
Optimize Harness CI/CD pipeline performance via MCP. Configure parallel test execution with Test Intelligence, design multi-layer caching strategies, analyze pipeline bottlenecks with stage-level timing breakdowns, optimize cache hit rates, and design monorepo CI pipelines with selective builds. Use when asked to speed up pipelines, improve cache hit rates, set up parallel testing, optimize build times, or configure monorepo builds. Do NOT use for creating new pipelines (use create-pipeline instead) or debugging failures (use debug-pipeline instead). Trigger phrases: pipeline speed, slow pipeline, cache hit rate, parallel tests, test intelligence, build optimization, caching strategy, monorepo pipeline, pipeline bottleneck, build speed.
Help developers integrate Chainlink Data Feeds into smart contracts and applications. Use for price feed integration, feed address lookup, consumer contract generation, multi-chain data feeds (EVM, Solana, Aptos, StarkNet, Tron), MVR bundle feeds, SVR/OEV feeds, feed monitoring, historical data, L2 sequencer checks, rates/volatility feeds, SmartData/RWA feeds, or debugging feed integrations. Trigger on any mention of Chainlink price feeds, oracle data, AggregatorV3Interface, latestRoundData, or feed addresses.
SOP for Vehicle Entry/Exit Operation Process of AIKE Smart Parking Open Platform (End-to-end Orchestration for Entry/Exit). This skill is applicable when users want to complete the full entry/exit of a vehicle, simulate the real physical entry/exit process, run through the entire link of 'Supplement/Capture Entry → Correction' or 'Exit Capture → Correction → Fee Inquiry → Payment', or ask questions like 'How does a vehicle enter/exits the parking lot?', 'Entry/exit process', 'Entry/exit SOP', 'How to move a vehicle into/out of the parking lot', 'Simulate vehicle entry/exit', or encounter stuck/debugging issues during entry/exit (e.g., vehicle fails to enter after capture or correction, capture returns error code 908, unsure how to proceed to the next step). This skill is a cross-domain orchestration layer that connects multiple commands from parking (supplement/correction/inventory), device (capture), and trade (fee inquiry/payment), and clarifies cross-command hard constraints (paired exit, capture device, channel release mode, token validity) and failure handling. Boundary: For querying a single record, checking on-site vehicles, locking vehicles, or calling a single command, please directly use the corresponding domain skills openydt-record / openydt-device / openydt-billing instead of this process skill.
Sui Programmable Transaction Blocks (PTBs). Use when writing, reviewing, or debugging code that composes multiple Sui transaction commands into a single atomic transaction — including TypeScript SDK `Transaction` usage, CLI PTB construction, gas coin handling, sponsored transactions, shared-object inputs, chaining command results, or troubleshooting PTB execution errors.
The agentmemory plugin hooks that capture observations automatically across the agent session lifecycle. Use when explaining how memory gets captured without manual saves, when debugging missing observations, or when tuning what gets recorded.
Capture a hard-won "golden path" from the current session as a reusable Agent Skill, so future sessions start already knowing it. Use it (1) right after non-trivial debugging, after working out a multi-step operational workflow, or after rediscovering project facts you didn't know up front — e.g. how to reach the dev/prod database, where credentials and env vars live, how to deploy, run migrations, or verify a change live; and (2) whenever the user says "remember this", "save this as a skill", "make a skill for this", "don't make me re-explain this next time", or otherwise wants a workflow preserved across sessions. Proactively recognize the moment even when unprompted: if a task took several attempts before it worked, used non-obvious tooling, or is likely to recur, harvest it without asking first. Delegates to a subagent when your tool supports one, or works inline, to extract the proven procedure into a new project-local or global skill.
Start here for any iOS or SwiftUI task. Coordinates best-practice guides, correctness checks, and full Apple API references. Use before navigating to other Apple skills — for building, reviewing, refactoring, or debugging iOS apps.
Edward de Bono's Random Stimulus technique — force-fit a random unrelated object, place, or phenomenon onto a creative target to break familiar association patterns. Use for product ideation, feature naming, brand direction, copywriting, architecture and design choices when ideas from outside the problem space would help. Triggers include "random stimulus", "random word", "force-fit", "de Bono", "inject a random object", "stare out the window", "see the tree and squeeze an idea". Do NOT use for analytical work like debugging, code review, or implementation tasks.
Use when writing, changing or debugging a Bagisto end-to-end test — Playwright specs, page objects, ACL role coverage, fixtures, or a failing E2E run in CI. Trigger phrases include "playwright", "e2e", "end to end", "spec.ts", "page object", "browser test", "flaky test", "shard".
Use when a repo already has an okteto.yaml / okteto.yml and the user wants it faster or reviewed — "make my okteto.yaml faster", "why is my dev environment slow to start or sync", "review this manifest for performance", "tighten the build / dev / test sections" — or when authoring the .dockerignore / .oktetoignore / .stignore files that go with a manifest. Do NOT use on a repo with no manifest yet: service discovery and the first draft belong to okteto-onboarding (optimize its draft here afterwards). Do NOT use to debug a broken environment (okteto-debugging) or to develop inside one (okteto).
Retrieve grounded ArkTS references for pure non-UI ArkTS work and ArkTS API usage. Use this skill whenever the user is writing, reviewing, testing, validating, running, or debugging ArkTS code and the answer should be backed by repository sources such as `docs/ArkTS-Language-Guide/`, `docs/ArkTS-API-Reference/`, the linter-derived `docs/linter/ArkTS_Syntax_Knowledge_From_Linter.md`, and the bundled lightweight lint tool docs `docs/linter/linter-cli.md` plus `linter-cli/` instead of model memory. This skill is especially useful for syntax rules, ArkTS-specific restrictions, API/module/member lookup, common-library usage, lightweight lint workflow lookup, runnable example lookup, snippet validation context, and figuring out which repository section to trust before suggesting code or fixes.