Use when you have a small PR or feature and want an agent to repeatedly fix review feedback until tests pass and the PR is merge-ready.
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero…
Coordinate automated or manual multi-agent development through scoped authority, single-writer ownership, fixed baselines, explicit tests…
Structured multi-provider AI debates between Claude and available advisors — use for critical decisions
苏格拉底式创意探索技能,融合 gstack 的 brainstorm 和 superpowers 的 aside 模式。 在不同方案之间做发散-收敛循环,用分块展示降低认知负荷,帮助团队找到最佳路线。
PR code review that surfaces decay risks, design smells, and maintainability issues with concrete Symptom → Source → Consequence → Remedy…
Use when receiving code review feedback before implementing suggestions, especially when feedback is unclear, risky, disputed, or…
Load the AgentOps language and Triggers: "define this domain term", "check the bounded context".
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term…
Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage
Prepare PR commits and body.
Research an upstream repo.
Use when requesting independent code review, after implementation slices, before merging high-risk work, or when verification exposes…
Use before merge, after subagents, or for spec/plan review.
Use when a PR or feature needs both specification and code-quality review
Query the authoritative global Herdr Review and Work Manager inventory, recommend actionable PR work, and explicitly materialize confirmed…
Review a teammate's pull request. The reviewer role (multi-lens analysis, severity calibration, suggestion writing) lives in the…
Manages enterprise notification dispatch, confirmation requests, and strict approval tracking across authorized MCP connectors.
Sends IM notifications, tracks approval workflows, and manages status records across enterprise communication channels.
Honest analysis of what went wrong. Use after a failed launch, missed quarter, or bad hire to run a blameless 5-Whys retrospective with a…
Review a PR across multiple dimensions — description, code changes, code scan, unit tests — using parallel subagents.