Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
The English summary is being prepared. Showing the original description.
David-Li0406/meta-skill-evloving☆ 2Updated Jul 14, 2026
Create safe, deterministic git worktrees for large or risky workstreams using the repository-owned runtime helper and Windows-safe defaults.
The English summary is being prepared. Showing the original description.
ThiagoGuislotti/copilot-instructions☆ 2Updated Jun 29, 2026
Create safe, deterministic git worktrees for large or risky workstreams. Use when tasks are complex enough to warrant isolation from the main working tree.
The English summary is being prepared. Showing the original description.
ThiagoGuislotti/copilot-instructions☆ 2Updated Jun 29, 2026
Manage git worktrees using a centralized worktrees folder. Use for parallel development, PR reviews, or isolated work.
The English summary is being prepared. Showing the original description.
SomtoUgeh/somto-dev-toolkit☆ 2Updated Aug 26, 2026
Official · OpenClawFreeSummaryAI rating 90 Delegate feature development, large code refactors, and pull request reviews to Codex, Claude Code, or OpenCode as background workers. Use isolated project checkouts, monitor progress, and arrange completion or failure notifications.
- Delegating feature development to a background worker
- Running a large code refactor in an isolated checkout
- Requesting a pull request review from a coding agent
openclaw/openclaw☆ 392.7KUpdated Oct 21, 2026
Turn a specification and its tickets into code by coordinating multiple agents around task dependencies. Combine their work on one integration branch, use test-driven development, review the result, and close tickets through the issue tracker’s workflow.
- Implementing a specification with multiple tickets
- Working on independent tickets in parallel
- Combining implementations on one integration branch
mattpocock/skills☆ 299.7KUpdated Oct 20, 2026
Compare coding agents on tasks from your own codebase. Define success checks, run agents in separate Git working directories, and report pass rates, available API costs, completion time, and consistency across repeated trials.
- Comparing coding agents on real development tasks
- Evaluating a new tool or model before adoption
- Checking performance after agent updates
affaan-m/ECC☆ 285.5KUpdated Oct 21, 2026
Control a running iOS Simulator on macOS from Orca’s live device pane. Perform taps, gestures, typing, button presses, and rotation, and inspect the interface element hierarchy to check app changes in the simulator.
- Check iOS app changes in the simulator
- Reproduce gestures and text entry
- Check the display after rotating the device
stablyai/orca☆ 101KUpdated Oct 21, 2026
Extract business areas, workflows, and process steps from a codebase and display them as an interactive horizontal flow graph. Use an existing knowledge graph, a map of project components, or run a lightweight scan of project files.
- Understanding business workflows from code
- Mapping business areas and process steps
- Creating a business view from an existing knowledge graph
Egonex-AI/Understand-Anything☆ 87.5KUpdated Oct 12, 2026
Analyze project code, configuration, and documentation to build a graph for interactive architecture exploration. It maps components and dependencies, supports Japanese descriptions, and can update the analysis based on changes since the previous analyzed commit.
- Understand the structure of an unfamiliar project
- Explore dependencies between components
- Generate architecture descriptions in Japanese
Egonex-AI/Understand-Anything☆ 87.5KUpdated Oct 12, 2026
Run or inspect local Release-Green checks for a specific code revision or combined pull request candidate. Report blocking failures, diagnostic differences, and missing evidence, compare against the base revision, and identify remaining CI checks.
- Checking a pull request candidate before maintainer review
- Comparing failures against the exact base revision
- Separating blocking failures from diagnostic differences
cheaper-inference/OmniRoute☆ 79.4KUpdated Oct 22, 2026
Run or inspect local Release-Green checks for a specific code revision or combined pull request candidate. Report blocking failures, diagnostic differences, and missing evidence, compare against the base revision, and identify remaining CI checks.
- Checking a pull request candidate before maintainer review
- Comparing failures against the exact base revision
- Separating blocking failures from diagnostic differences
diegosouzapw/OmniRoute☆ 79.4KUpdated Oct 21, 2026
Set up a coordinated team of three or more AI agents for development tasks spanning multiple files. Configure the team structure, assign specialized roles, and prepare parallel work with named agents and messaging.
- Implementing a feature across multiple files
- Refactoring across modules with coordinated agents
- Sharing a security audit across an agent team
ruvnet/ruflo☆ 78.2KUpdated Oct 21, 2026
Reviews completed changes through hands-on checks and one reviewer agent. It compares the implementation and recorded evidence with the original goal, constraints, code quality, and security requirements, then reports approval, specific blockers, or an inconclusive result.
- Reviewing completed changes before a pull request handoff
- Checking whether an implementation meets the original request
- Organizing failed checks and required fixes
code-yeongyu/oh-my-openagent☆ 70.2KUpdated Oct 21, 2026
Coordinates a named team of Codex workers with concrete responsibilities and shared progress records. It selects available collaboration tools, manages communication and separate working copies when needed, and handles integration, team archival, and cleanup after the work ends.
- Splitting related implementation work across cooperating agents
- Investigating several aspects of a clearly defined problem
- Inspecting team progress and member responsibilities
code-yeongyu/oh-my-openagent☆ 70.2KUpdated Oct 21, 2026
Official · RemotionFreeSummary Upload preview images and videos for a Remotion Element to remotion.media, then update the corresponding URLs. The skill also handles local asset cleanup according to whether previews come from fresh renders or committed submissions.
- Publish freshly rendered Element previews
- Upload preview assets from committed submissions
- Replace local image and video URLs
remotion-dev/remotion☆ 66KUpdated Oct 21, 2026
Official · RemotionFreeSummary Update Remotion’s FFmpeg dependency to a published rust-ffmpeg commit, refresh the dependency lockfile, and rebuild compositor binaries for all supported platforms. Validate the changes and open a draft pull request with source revisions and build results.
- Apply a published rust-ffmpeg revision to Remotion
- Rebuild compositor binaries for all supported platforms
- Verify Windows runtime library dependencies
remotion-dev/remotion☆ 66KUpdated Oct 21, 2026
Organize open pull requests before a release, classify what to merge or defer, and track decisions in a resumable document. Guide review, merging, follow-up fixes, and closing requests already covered by other changes.
- Sort a backlog of pull requests before a release
- Prioritize bug fixes for the next version
- Resume interrupted reviews from a progress document
jamiepine/voicebox☆ 58.2KUpdated Oct 7, 2026
Manage Hindsight memory for coding sessions: retrieve past decisions, store documents and initiative plans, correct outdated information, and configure memory by project. It also explains automatic conversation capture and helps investigate memory configuration problems.
- Retrieving past project decisions and conventions
- Saving external notes and initiative plans
- Correcting outdated or inaccurate memory
vectorize-io/hindsight☆ 52.3KUpdated Oct 21, 2026
Move reusable code and its tests from OpenHuman into the appropriate tiny* submodule. Separate host responsibilities, update module interfaces, verify the migration, and align release versions and integrity hashes when a loadable module changes.
- Extract reusable logic from the OpenHuman core
- Move implementation tests into the owning submodule
- Update TinyBus contracts and host adapters
tinyhumansai/openhuman☆ 42.2KUpdated Oct 21, 2026
Control interactive command-line tools through tmux by sending keystrokes, capturing terminal output, and waiting for prompts. Supports session management and running multiple coding agents in parallel, with helper scripts for finding sessions and detecting text.
- Operating an interactive Python session
- Waiting for prompts and reading terminal output
- Running Codex or Claude Code sessions in parallel
volcengine/OpenViking☆ 40.5KUpdated Oct 20, 2026
Turn a feature idea into a design document through focused dialogue. The skill clarifies goals and constraints, compares two or three approaches, and reviews the design in sections before documenting architecture, data flow, errors, and testing.
- Clarifying requirements for a new feature
- Comparing alternative implementation approaches
- Reviewing a design section by section
davila7/claude-code-templates☆ 32.8KUpdated Oct 21, 2026
Review open GitHub issues, proposals, and pull requests to identify useful maintainer work. Get ranked candidates with evidence, dependencies, and validation needs, then begin work only on an item you explicitly select.
- Choose the next maintenance task
- Prioritize a backlog for the available work window
- Find pull requests that need review
trycua/cua☆ 30.6KUpdated Oct 21, 2026
Review FastGPT pull requests in stages, starting with the intended change and key execution paths. Check security, performance, tests, and compatibility, then organize findings by severity into a review report and line-level comments.
- Checking a pull request before merging
- Reasoning through normal, edge, and error cases
- Assessing API and database compatibility risks
labring/FastGPT☆ 29.9KUpdated Oct 21, 2026