71 skills · sorted by relevance
Run one iteration of a BMad unattended development loop, with optional route and review selections. The skill follows a generated workflow and reports a halt reason or command failure when execution cannot continue.
Configure permission checks for unattended Antigravity CLI runs. The setup combines blocking rules, automatic approval for scoped operations, AI classification for ambiguous calls, and single-use approval tokens to control tool access within a verified workspace.
Resume pending deliberation saved by unattended acc runs. The skill guides the agent through reading each queued item and its context, submitting a proposal, and reporting resolution identifiers and supporting references until the queue is cleared.
Manage tasks on an OpenViking kanban board, where each Markdown file contains the task and its handoff notes. Record decisions, verified progress, and next steps so another agent or person can resume the work.
Add error handling to n8n workflows with connected error outputs, retries, and failure notifications. Return HTTP status codes that explain what went wrong, distinguish invalid requests from service failures, and keep internal error details out of public responses.
Build failure handling into n8n workflows with separate error paths, retries, alerts, and clear API responses. Use it for webhooks and unattended jobs to make failures visible and return status codes that explain what went wrong.
Independent re-derivation gate for proposed changes during autonomous execution. Evaluates a change (code diff, config edit, engine evolution, schema change) against the work's authority matrix and a 4-check protocol: invariant compliance, scope authorization, detection narrowness, and regression risk. Returns structured JSON with pass/fail per check, an overall verdict (APPROVE / REQUEST_CHANGES / REJECT), and blockers. Profile-driven thresholds (strict for unattended runs, lenient for desk supervision). Use when an autonomous agent proposes an engine change, when reviewing a Claude Code-authored modification before merge, or when an unattended profile requires independent re-derivation. Trigger on: "review/approve this proposed change," "critic-gate this," "is this change safe," "is this safe to merge," "should I let this land," "run the critic." Do NOT use for handoff-readiness checks (use rootnode-handoff-trigger-check), general code review, or design-time correctness. Authority matrix required.
The English summary is being prepared. Showing the original description.
Select and confirm an overnight or long-running unattended collaboration topology. Use only for a requested unattended run, not ordinary questions or short tasks.
The English summary is being prepared. Showing the original description.
Author and run unattended autonomous workflows — "workflow", "unattended", "run on a schedule", "automate this overnight", "set up an autonomous", "dry-run". Mandatory budget guards, a separate verification gate, idempotency, and dry-run on by default.
The English summary is being prepared. Showing the original description.
Set up and use gstack in Capy or Claude Code for planning, code review, debugging, and release work. It checks the local environment, handles installation or repairs when needed, and selects the workflow instructions for the task.
Use a real browser to verify web pages and apps through short, supervised interactions. Capture screenshots, inspect errors and network requests, and document reproducible steps for UI bugs or expected behavior checks.
Set up OmniRoute and manage its command-line configuration. Inspect and validate tool settings, manage environment variables, check for updates, and control automatic startup using commands that support both interactive and unattended setup.
Run a ruflo agent on your ruOS cloud desktop through an authenticated connection. Follow its output as it runs, record execution status in ruflo, and release the task claim when the run finishes.
Review records across OMC sessions to find recurring obstacles in the agent's working environment. It turns evidence from timelines, logs, and notes into ranked proposals for checks, guidance, tools, or information access, with changes requiring user approval.
Test the pages affected by a branch or pull request in a browser. The skill checks rendered pages and key interactions, then reports passes, failures, skipped checks with reasons, and steps to reproduce problems.
Delegate coding, analysis, refactoring, or reviews from Claude Code to Codex CLI. The skill explains unattended execution, permission settings, output capture, parallel tasks, and independent checks of changed files and test results.
Design and implement command-line tools with subcommands, options, interactive prompts, and progress indicators. Get command structures, configuration handling, clear error messages, and shell completion scripts, with guidance for automated use and testing across operating systems.
Set up Loop Engineering through a single command-line tool, choosing a workflow pattern and agent tool. Start in report-only mode, check setup health and readiness, and provide next actions and first-run instructions.
Define a consistent process for unattended AI research using public sources. Limit clarification questions, show a search plan, distinguish facts from interpretations and assumptions, and keep reports structured so repeated investigations can be compared.
Compare current competitor evidence with a previous research snapshot and report only meaningful changes, with sources and dates. Flag sales comparison materials, positioning, pricing analysis, or roadmap assumptions that need updating during recurring monitoring.
Find a valuable gap in test coverage by checking code, existing tests, and QA priorities. The skill creates at most one locked GitHub issue with concrete test cases, ready for later implementation.
Develop user-visible improvements for cc-wf-studio, verify their basis in the code, and assess their value. Record qualifying proposals as locked GitHub issues, creating a queue of concrete ideas for later implementation without changing code.
Advance one development task by managing an existing pull request, fixing a build failure or bug, or implementing a queued idea. Record the work and integrate changes into auto-dev only after automated checks pass.
Advance one queued QA task by adding tests or test tooling, recording the work, and opening a pull request. The skill also manages its in-flight QA requests and merges into auto-qa after CI passes.