519 skills · sorted by relevance
Split independent debugging or repair tasks among multiple AI agents. Define a focused scope, constraints, and expected report for each agent, then review their changes, check for conflicts, and test the combined result.
Build beta versions of the Composio CLI, promote a tested beta to a stable release, and investigate failed releases. Guides verification of published binaries and installation tests through the Build CLI Binaries workflow.
Retire a FastGPT workflow node while preserving existing workflows. The skill guides changes to templates, execution handlers, and interface references so the node disappears from creation menus but still loads, runs, and displays a replacement notice.
Publish a Mastra preview package from a pull request or branch. Check the exact commit, confirm publication, monitor the release workflow, and report verified npm tags with a ready-to-copy installation command.
Review Pascal pull requests or branches against documented architecture rules. Check package responsibilities, node extension patterns, state management, and rendering subscriptions to identify misplaced code, compatibility breaks, and changes that could cause excessive redraws.
Investigate failing or flaky NemoClaw end-to-end tests, which check complete workflows. Trace each assertion through its inputs and implementation, including cleanup and dependent jobs, and produce an evidence ledger to guide authorized repairs and reruns.
Run NemoClaw live end-to-end tests, which check complete workflows, or inspect existing release evidence. Routes requests to local or trusted GitHub workflows and reports the tested commit, results, workflow link, and relevant job links.
Continuously monitor automatic end-to-end tests on NemoClaw main, group failures by root cause, and coordinate fixes and peer reviews through GitHub. Track ownership and merge readiness while checking whether later runs confirm each repair.
Explore relationships between functions and files using a prebuilt code graph, a map of code dependencies. Trace bugs, inspect callers and execution paths, and assess the impact of refactoring or proposed changes.
Guide a Kortix production release from choosing a version and writing release notes to testing on staging, merging the release pull request, and verifying production. Diagnose blocked promotions and direct fixes back to the dev branch.
Roll back Kortix production to a previously released version using existing builds. Covers frontend and backend rollback, database compatibility checks, prevention of unintended frontend rebuilds, and returning to the latest version through a later release.
Debug json-render interfaces with an inspector panel that shows screen specifications, editable runtime state, action history, and streamed updates. Select a rendered page element to locate its definition and investigate display or interaction problems.
Improve MNN's Vulkan backend by separating CPU scheduling bottlenecks from GPU computation costs. It guides operator and shader changes, new feature integration with compatibility fallbacks, and device testing to verify both correctness and end-to-end performance.
Find why MNN CPU inference is slow by examining threads, scheduling, memory layout, and the processor instruction path actually used. Operator-level measurements and comparisons with other inference frameworks help identify which layer needs improvement across ARM, x86_64, and RISC-V.
Test Omnigent’s GitHub Copilot SDK integration on a live local server. Build test agents, run real conversations, and inspect authentication, model selection, tool connections, policy enforcement, and leftover processes to investigate integration failures.
Check project progress, summarize recent work and remaining tasks, and move to the next GSD workflow step. It also supports automatic step chaining and routes plain-language requests to suitable GSD commands.
Run several small development tasks as one batch, from planning through execution and merging. Control concurrency, add research or validation, and resume eligible unfinished items from a saved batch.
Deploy ClawHub to production or publish a stable CLI release to npm. Check prerequisites for the exact commit, run the release workflow, and verify the deployed behavior or published version with traceable release evidence.
Record operations across multiple AI agents and connect events into a traceable history. Search records by tracking ID, time window, or responsible component to support audits and investigations, with local storage available when the vector database fails.
Investigate independent bugs or test failures concurrently by assigning each problem area to a separate agent. Define clear boundaries and expected reports, then review the fixes, check for conflicts, and run the full test suite before integration.
Helps decide whether to handle a task directly, create a subagent, or route it to an agent already familiar with the work. The choice depends on required background knowledge and whether plausible but incorrect results can be checked.
Add a dashboard or admin panel across the server and interface. This skill follows existing project patterns to build API routes, service logic, components, registration, and styles, then connects request handlers so the new endpoint is reachable.
Add a complete dashboard panel in plain TypeScript, from server routes and data services to the visible component and registration. The workflow checks existing routing patterns and includes request failure handling, caching, and saved panel state.
Routes bulk RNA-seq requests to workflows for generating expression counts and checking quality, or comparing gene expression between groups. Checks input data, sample information, and analysis requirements before directing the next step.