440 skills · sorted by relevance
Switches the Kilo JetBrains plugin between a pinned released CLI and a freshly built local CLI. Includes commands to clear old build artifacts, regenerate the local executable, and verify the selected setup with Gradle.
Use the Archon CLI to launch AI workflows on projects, inspect their results, and approve, reject, cancel, or resume runs. The skill also guides setup, configuration changes, workflow creation, and improvements to workflow prompts.
Delegate coding, analysis, planning, and reviews from Codex to Claude Code through its command-line interface. Capture responses, resume sessions, or run independent tasks in parallel, then verify changed files and test results independently.
Read and change Superset desktop preferences through its command-line tool, without opening settings. Adjust fonts, terminals, notifications, and Git options, or create and install custom color themes from JSON files, with local operation and no login required.
Test polly's coordination of coding agents using a scripted mock language model and live command-line tools. Check startup, task dispatch, safety rules, parallel delegation, and whether real agents make appropriate orchestration decisions.
Test Omnigent’s setup, help, and terminal interactions by driving the real CLI in an isolated environment. Capture rendered screens and compare checks before and after a change to establish whether a reported interface problem was fixed.
Guide CI work for Worktrunk, a Rust tool for managing Git worktrees. Adds project rules for running tests, checking Codecov coverage, diagnosing failures, reviewing pull requests, and maintaining toolchain and CI versions.
Turn development requirements into an implementation plan with specific files, function signatures, tests, and verification commands. Use it before coding to document decisions and divide the work into independently testable tasks.
Audit groups of bug reports to find shared root causes, checking claims against current code and tests. Produce a cause map, prioritize fixes that remove faulty mechanisms, and document which issues have enough evidence to close.
Guide an approved defect fix from reproduction on current main through testing and independent validation. Record evidence for each operator workflow, track change size and rollback scope, and apply review records when receipt-driven development is enabled.
Set up Ouroboros inside Claude Code with a guided wizard. Check runtime requirements, configure the Claude runtime, optionally add project instructions to CLAUDE.md, and register existing repositories as context for future interviews.
Manage terminal work across panes: open jobs, run commands, read output, and wait for completion. Report agent status, exchange messages, and request human decisions through tuios, a terminal window manager with a background service.
Review concrete code changes for defects, compatibility problems, repository-rule violations, and unnecessary code. Produce evidence-based findings and, when explicitly requested, make minimal cleanup changes while checking that existing behavior is preserved.
An experimental workflow for delivering software changes through configured checks, pull requests, review updates, and merge verification. It follows project permissions and release conditions, and reports missing evidence or checks before treating delivery as complete.
Inspect BB storage across machines, identify cleanup candidates, and remove archived files or unused development data. Configure automatic thread archiving and deletion, with previews showing how many threads would be affected before saving retention settings.
Publish saved skill and global AGENTS.md changes to a private repository, then check the automated public mirror. The workflow isolates intended edits, preserves unrelated work, and verifies the actual published content.
Prepare an APM release by assessing changes since the last tag, choosing a version increment, cleaning the changelog, updating version files, and running CI-equivalent checks before opening a release pull request.
Carry out an implementation plan by assigning independent tasks to separate agents. The workflow includes specification checks, code quality reviews, fixes, a persistent progress record, and a final review of the entire branch.
Organize mixed Git changes into focused commits and pull requests that reviewers can follow. It preserves unrelated work, checks proposed changes for private information, runs relevant validation, and pushes or opens pull requests when authorized.
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.
Convert requirements into a detailed implementation plan before coding begins. Break work into small actions with exact file paths, code examples, test commands, expected results, and commit steps so another developer can follow the plan.
Execute an existing implementation plan in the current session by assigning each task to a fresh subagent, a separate agent handling delegated work. Each task receives a specification review followed by a code quality review, with fixes rechecked.
Investigate past agent runs using recorded tool calls, exit codes, and file changes. Replay failures, distinguish observed evidence from inferred causes, and compare models from the same saved point when requested.
Use when launching, monitoring, or controlling AI coding agents (Claude Code, Codex, OpenCode, etc.) in tmux via Agent of Empires (aoe). Covers creating sessions, capturing agent output, running parallel worktree agents, and organizing work into groups and profiles. Prefer aoe over raw tmux for agent management.
The English summary is being prepared. Showing the original description.