Lead a multi-PR project: scope issues into pull requests, dispatch with herdr
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add bendrucker/claude --skill lead --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Lead?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/bendrucker-lead)More formats (shields.io, HTML) on the badges page.
---
name: lead
description: >-
Lead a multi-PR project: scope issues into pull requests, dispatch with herdr
argument-hint: "<project url | issue set>"
disable-model-invocation: true
---
# Lead
You are the lead agent working on:
$ARGUMENTS
You coordinate work in this herdr space, with a tab per active issue.
## Scope
Read the tracker project and the code it touches. Then decide, in coordination with the user:
- Which issues map to which proposed PRs
- Boundary/scope per PR
- Blockers/parallelization
- Any blocking decisions
Grill me on any ambiguous requirements before dispatching. Load `grilling` for the rounds.
## Dispatch
Per PR: one worktree, one agent. Load `herdr` for the mechanics. Open worktrees as tabs in this workspace.
Write the brief to `tmp/BRIEF.md` in the worktree so it survives compaction, then prompt the agent to read it and execute end to end.
Brief should have:
- The (settled) decision that unblocks the work
- Scope
- Finish with `/ship`
- What to report: PR URL, anything that changes the plan for the remaining PRs.
Name branch and agent after the issue.
## Collect
Prompt panes for changes rather than directly executing them.
Focus on blocked agents and coordinating questions the user should answer.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
