phase7
Execute Phase 7 Concurrency Hardening on a target file.
pr-loop
>-
ticket
Execute a single V12 refactoring ticket in a new isolated Bob session.
audit-and-add-project-skills
Audits project skills in .agent/skills/ and Codex skills for Cursor compatibility, then helps add compatible skills to .cursor/skills/. Use when the user wants to migrate project skills to Cursor, check if skills work with Cursor, or add existing skills to Cursor.
tavily-best-practices
Build production-ready Tavily integrations with best practices baked in. Reference documentation for developers using coding assistants (Claude Code, Cursor, etc.) to implement web search, content extraction, crawling, and research in agentic workflows, RAG systems, or autonomous agents.
crawl
Crawl any website and save pages as local markdown files. Use when you need to download documentation, knowledge bases, or web content for offline access or analysis. No code required - just provide a URL.
extract
Phase 6-style god-function extraction on a high-complexity method.
research
Comprehensive research grounded in web data with explicit citations. Use when you need multi-source synthesis—comparisons, current events, market analysis, detailed reports.
git-commit-analyzer
Analyze Git commits with deterministic metrics and contextual AI review, then produce a concise or playful contribution report. Use when asked to review recent commits, summarize engineering work, compare contribution patterns, inspect commit quality, or generate a 牛马鉴定报告 from a local repository, GitHub repository, or GitLab project.
baml
Learn how to use the BAML programming language for LLM structured outputs
Beancount Accounting
This skill should be used when the user asks to "add a transaction", "create a beancount entry", "record an expense", "balance my accounts", "query my finances", "check account balances", "categorize spending", "write beancount", "edit .beancount files", "run a BQL query", "reconcile accounts", or mentions beancount, double-entry accounting, or ledger files. Provides comprehensive beancount syntax, directives, and query language expertise.
edgartools
Learn the basics of the edgartools library - an SEC EDGAR API wrapper.
dart-python
DART Python: dartpy bindings, pybind11, wheels, and API patterns
dart-io
DART IO: URDF, SDF, MJCF, SKEL parsers, and dart::utils loading
dart-mechanical-refactor
DART Mechanical Refactor: perform a behavior-preserving mechanical refactor
dart-ultrawork
DART Ultrawork: kick off a large or autonomous DART task with project-home docs, an optional decision interview, and orchestrated execution
dart-contribute
DART Contribute: branching, PRs, and review workflow
dart-docs-update
DART Docs Update: update docs or AI instruction visibility without code changes
dart-retro
DART Retro: run a retrospective and capture durable lessons
dart-review-pr
DART Review PR: review a PR or address review feedback
dart-build
DART Build: CMake, pixi, dependencies, and build troubleshooting
dart-downstream-fix
DART Downstream Fix: fix a DART bug reported through gz-physics or Gazebo
dart-resume
DART Resume: continue unfinished work through its acceptance criteria, verification, and safe completion or documented blocker
dart-model-upgrade
DART Model Upgrade: audit and update DART 6 AI infrastructure for model or coding-agent upgrades, including named models, reasoning modes, migrations, compatibility reviews, and visual simulation-debugging evaluations
dart-verify-sim
DART Verify Sim: text-first and OSG visual debugging for DART 6 scenes, dynamics, collision, contacts, and GUI output
dart-manage-pr
DART Manage PR: manage an open DART pull request through CI, review, merge, and cleanup
dart-fix-ci
DART Fix CI: debug and fix failing CI checks
dart-ci
DART CI: GitHub Actions, cache debugging, and platform-specific failures
dart-release-ci-fix
DART Release CI Fix: debug and fix CI failures on the DART 6.20 release branch
dart-test
DART Test: unit tests, integration tests, CI validation, and debugging
dart-new-task
DART New Task: start a feature, bugfix, refactor, docs, build, or test task
dart-pr
DART PR: create a branch, commit, push, and open a DART pull request
dart-analyze
DART Analyze: analyze repository evidence without editing
dart-changelog
DART Changelog: decide, draft, finalize, or audit DART changelog entries
dart-branch-cleanup
DART Branch Cleanup: analyze or clean stale repository branches
dart-backport-pr
DART Backport PR: backport a merged release-6.20 PR to an older release branch
atlassian-cli
Use for installing, upgrading, authenticating, and using Atlassian Command Line Interface (ACLI, `acli`) for Atlassian Cloud. Triggers include Jira CLI tasks (work items, projects, boards, sprints), Atlassian Admin CLI tasks (user/org admin via API key), Rovo Dev CLI usage, enabling shell completion, scripting/CI usage, and troubleshooting `acli` errors or trace IDs.
replace-with-skill-name-using-hyphens
Use when [describe triggering conditions, symptoms, or specific errors].
authentication
Authentication and authorization including JWT, OAuth2, OIDC, sessions, RBAC, and security analysis. Activate for login, auth flows, security audits, threat modeling, access control, and identity management.
aws
AWS cloud services including EC2, EKS, S3, Lambda, RDS, and IAM. Activate for AWS infrastructure, cloud deployment, and Amazon Web Services integration.
batch-processing
Message Batches API for Claude with 50% cost savings on bulk processing. Activate for batch jobs, JSONL processing, bulk analysis, and cost optimization.
citations-retrieval
Document citations and RAG (Retrieval-Augmented Generation) patterns for Claude. Activate for source attribution, document grounding, citation extraction, and contextual retrieval.
complex-reasoning
Multi-step reasoning patterns and frameworks for systematic problem solving. Activate for Chain-of-Thought, Tree-of-Thought, hypothesis-driven debugging, and structured analytical approaches that leverage extended thinking.
confluence
Confluence documentation including pages, spaces, templates, and Atlassian integration. Activate for wiki pages, documentation, knowledge bases, and team collaboration.
database
Database design, SQL queries, migrations, and optimization. Activate for PostgreSQL, MySQL, SQLite, schema design, queries, indexes, and data modeling.
debugging
Debugging techniques for Python, JavaScript, and distributed systems. Activate for troubleshooting, error analysis, log investigation, and performance debugging. Includes extended thinking integration for complex debugging scenarios.
deep-analysis
Analytical thinking patterns for comprehensive evaluation, code audits, security analysis, and performance reviews. Provides structured templates for thorough investigation with extended thinking support.
deep-research
Comprehensive research on a topic using multiple sources and approaches. Spawns parallel research threads.
design-system
Apply and manage the AI-powered design system with 50+ curated styles
docker-build
Build Docker images with proper tagging, cache busting, and build tracking. Prevents stale image issues.
Page 559 of 1646 · 82253 results