beyondeye
Useran agentic IDE in your terminal, markdown tasks with YAML frontmatter, git-native, zero infrastructure. Works with Claude Code, OpenCode, and Codex CLI.
Categories
Indexed Skills (27)
task-workflow
Shared implementation workflow for task-based skills, with profile-check sites wrapped in Jinja conditionals.
ait-git
Git commands for aitasks/aiplans directories — use ./ait git instead of plain git
aitask-pickrem-remote
Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.
aitask-pickweb-remote
Pick and implement a task on Claude Code Web. Zero interactive prompts. No cross-branch operations — stores task data locally in .aitask-data-updated/.
aitask-contribute
Contribute local aitasks framework changes back to the upstream repository by opening structured GitHub issues.
aitask-contribution-review
Analyze a contribution issue, find related issues, and import as grouped or single task.
aitask-add-model
Register a known code-agent model in models_<agent>.json, optionally promote it to default across config/seed/DEFAULT_AGENT_STRING.
aitask-changelog
Generate a changelog entry by analyzing commits and archived plans since the last release.
aitask-create
Create a new AI task file with automatic numbering and proper metadata.
aitask-explain
Explain files in the project: functionality, usage examples, and code evolution history traced through aitasks.
aitask-refresh-code-models
Research latest AI code agent models via web and update models_*.json configuration files.
aitask-reviewguide-classify
Classify a review guide file by assigning metadata and finding similar existing guides.
aitask-reviewguide-import
Import external content (file, URL, or repository directory) as a reviewguide with proper metadata.
aitask-reviewguide-merge
Compare two similar review guide files and merge, split, or keep separate.
aitask-stats
Calculate and display statistics of AI task completions (daily, global, per-label).
aitask-explore
Explore the codebase interactively, then create a task for implementation.
aitask-fold
Identify and merge related tasks into a single task, then optionally execute it.
aitask-pick
Select the next AI task for implementation from the `aitasks/` directory.
aitask-pickrem
Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.
aitask-pickweb
Pick and implement a task on Claude Code Web. Zero interactive prompts. No cross-branch operations — stores task data locally in .aitask-data-updated/.
aitask-pr-import
Create an aitask from a pull request by analyzing PR data and generating a structured task with implementation plan.
aitask-qa
Run QA analysis on any task — analyze changes, discover test gaps, run tests, and create follow-up test tasks
aitask-revert
Revert changes associated with completed tasks — fully or partially
aitask-review
Review code using configurable review guides, then create tasks from findings.
aitask-web-merge
Merge completed Claude Web branches to main and archive task data.
aitask-wrap
Wrap uncommitted changes into an aitask with retroactive documentation and traceability.
aitask-audit-wrappers
Audit and port aitask skill wrappers across code-agent trees, plus helper-script whitelist coverage.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.