felipemelendez
UserDeploy a coordinated team of AI engineers to any codebase. A Claude Code plugin with structured workflow, two-stage code review, autonomous BLOCKED recovery, and a research gate that verifies external APIs against current docs before specs get written.
Categories
Indexed Skills (17)
brainstorming
Use when starting creative work — a new feature, added functionality, a system design, or a behavior change — before any code is written. Not for one-line fixes, mechanical chores, or when an approved spec already exists.
dispatching-parallel-agents
Use when 3+ tasks are independent — no shared files, no order dependency — and can run concurrently. Fan-out only; per-task review happens after all return.
dispatching-subagents
Use when running plan tasks sequentially with per-task two-stage review — the default for tasks with dependencies, sensitive code, or shared files another task changed.
executing-plans
Use when you have a written plan and need to drive it task-by-task to completion. Top-level orchestrator that routes each task to sequential or parallel dispatch and tracks state.
finishing-a-branch
Use when implementation is complete and tests pass. Decides between merge, PR, keep, or discard — without destructive actions unless the user confirms.
managing-memory
Use when the user says "remember", "save this", "I told you before", or "forget that". Classifies notes into Claude Code's native CLAUDE.md and research-gate state.
receiving-code-review
Use when responding to code review feedback — from a human, from another agent, or from the two-stage review flow. Resists performative agreement and blind implementation.
requesting-code-review
Use when a diff is complete and about to be merged, opened as a PR, or called done. Runs the two-stage review plus an optional security pass. Not for mid-task or incomplete diffs.
research-classifier
Use when about to invoke brainstorming or writing-plans, before a spec or plan is committed. Decides whether to verify API surfaces against current docs first.
test-driven-development
Use when implementing a feature or bugfix where tests are practical, before writing implementation code. Enforces red-green-refactor with a verified red phase. Not for docs-only or config-only changes with no testable behavior, and not before systematic-debugging when the trigger was a failure rather than new work.
using-git-worktrees
Use when work needs isolation from the current branch — long-running feature, risky refactor, parallel attempt. Creates and tracks a worktree without touching unrelated state.
using-orchestrator
Use when starting any session in an LLM Orchestrator project. Establishes the Concise Agent Protocol response shapes and mandates skill invocation before any response or action.
using-workflows
Use when deciding whether an already-chosen fan-out (multi-dimension review, parallel implementation, multi-source research) runs on the Workflow tool or inline. Do not use to decide whether to parallelize at all — that is dispatching-parallel-agents.
verification-before-completion
Use when about to claim work is done, fixed, passing, or ready to merge — it forces a real run of the verifying command first. Not for reporting a failure honestly, which needs no gate. Runs last, after any review skill.
writing-plans
Use when a spec is approved and implementation has not started. Produces a dated, checklist-shaped plan file that another agent (or you) can execute task-by-task. Not for work already covered by an existing plan, and not before brainstorming has produced the spec.
writing-skills
Use when adding a new skill or editing an existing one. Keeps the catalog short, the frontmatter correct, and the body free of coercion and padding.
handing-off-to-fresh-context
Use when context is filling on a long task and you should leave a short note so work resumes cleanly after the conversation is compacted.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.