428 skills · sorted by relevance
Coordinate bounded test runs for one Terminal-Bench task through Paperclip. Record evidence, diagnose failures, and manage approval for product fixes while keeping reruns in the same isolated working copy.
Set up and troubleshoot disposable runtime environments that Orca creates for each workspace. Review recipe settings in orca.yaml, scaffold scripts that create and dispose of environments, and investigate failures reported by the recipe diagnostic command.
Coordinate multiple Orca workers by assigning tasks, exchanging threaded messages, and waiting for results or escalations. Use task dependency graphs and decision gates to supervise work that needs ongoing coordination across agents.
Manage local oh-my-claudecode skills through commands and guided prompts. List and search available skills, create or edit custom ones, and compare or copy skills between personal and project folders to organize reusable instructions.
Break a large development brief into ordered goals and save plans, progress events, blockers, and evidence in the repository. Coordinate Claude Code sessions through handoff instructions, with final completion requiring cleanup, verification, and code review evidence.
Run repeated code improvement experiments with multiple agents. It plans and reviews candidate changes, compares benchmark results, merges candidates that pass rechecking, and records progress until a target, iteration limit, or another stopping condition is reached.
Upgrade a customized NanoClaw installation by recording changes in a reusable migration guide and reapplying them to a clean upstream version. The workflow includes backups, validation in a separate working directory, and rollback instructions.
Create a dedicated test project linked to the current worktree and check Agent Builder through APIs and browser interactions. It covers agent and skill management, permissions, defaults, and related features, with selectable test sections.
Coordinate multiple Mastra Code workers to investigate and fix GitHub issues in parallel. Keep each issue in a separate working directory, track progress in reports, review changes, and manage pull requests, reviewer feedback, and automated checks.
Investigate failed tests, type checks, builds, and CI jobs by recording exact evidence and repeating checks in a clean comparison environment. Use the results to distinguish existing failures, newly introduced problems, environment issues, and unresolved cases.
Manage coding agents and their workspaces in Paseo through its tools or command line. This reference covers project registration, workspace scripts, agent settings, recurring tasks, and reminders that return to the current conversation.
Configure a repository for Superset so new isolated Git workspaces have dependencies, environment files, and service access ready. Create lifecycle scripts in .superset/config.json and verify the setup by starting a real test workspace.
Classify failures in CI, automated checks run during development, to distinguish code regressions, temporary infrastructure problems, security test failures, and inconsistent results. Record each failure's category, suggested next action, and attempt count in a structured report.
Execute an implementation plan by assigning each independent task to a fresh helper agent in sequence. Review specification compliance and code quality after each task, track decisions in files, and finish with a review of the entire branch.
Coordinate feature development from product direction through architecture, planning, validation, and implementation. Run the whole workflow or start at a selected stage, with saved decisions, review checkpoints, and a final pull request.
Coordinate multiple AI agents by assigning tasks, tracking dependencies, exchanging messages, and monitoring progress. Separate Git working directories help organize parallel changes, while context checks and snapshots support handoffs and recovery.
Breaks large changes, migrations, or multiple fixes into clearly scoped work packages. Independent workers use separate Git working directories, run checks, and report results, while dependency validation determines which packages can run together.
Carry out a written implementation plan in a separate session, reviewing it before starting and tracking each task through verification. The workflow pauses for blockers and hands completed work to a development branch finishing process.
[omh] Lost track of agent sessions and worktrees: normalize Codex, Claude Code, Hermes, OpenCode, Cursor, MCP host, worktree, and wrapper session metadata into one drift-aware inventory. Use when the user says: harness-session-inventory, harness session inventory, session inventory, session adapter, session adapters, harness sessions, mcp inventory, mcp config inventory.
The English summary is being prepared. Showing the original description.
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
The English summary is being prepared. Showing the original description.
在保护无关脏改动、关联 worktree、子模块和用户明确边界的前提下，提交、推送、合并或完成范围明确的 Comet 变更。用户要求提交、推送、合并回目标分支、清理 worktree 或交付已准备好的改动时使用。
The English summary is being prepared. Showing the original description.
Create and manage git worktrees for parallel coding sessions with zero dead time. Use when blocked on tests, builds, wanting to work on multiple branches, context switching, or exploring multiple approaches simultaneously.
The English summary is being prepared. Showing the original description.
Isolates feature work in its own branch or worktree and integrates it cleanly when done. Use this when starting work that should not disturb the current workspace, when several efforts must proceed in parallel on one repository, or when implementation is finished and the change needs merging, rebasing, or splitting for review.
The English summary is being prepared. Showing the original description.
Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides git worktree commands and workflow patterns for parallel development with multiple working directories.
The English summary is being prepared. Showing the original description.