workflow agents

brody-0125/my-claude-skills

Agent

Routes DB engineering queries to appropriate micro agents based on domain classification and coordinates parallel dispatch for multi-domain queries.

brody-0125/my-claude-skills

Agent

Routes SE (Security) engineering queries to appropriate micro agents based on 6-cluster classification (Authentication/Authorization/Encryption/Network/Compliance/Vulnerability) and coordinates chain execution for multi-cluster queries.

godshiba/genesis

Agent

Reads every doc in a repository, classifies what exists, detects what is missing or stale, and produces a complete migration plan toward a clean, comprehensible doc structure - plus drafts for missing docs. Read-only analyst; execution happens in the main thread after user approval. Use when /genesis:docs delegates…

godshiba/genesis

Agent

Audits a diff or working tree against the seven GENESIS gates (registration, validation, issue, doc-sync, landmine, decision, session) and returns a structured pass/fail report. Use PROACTIVELY before commits in GENESIS projects with large diffs, or when /genesis:gate-check delegates the audit.

godshiba/genesis

Agent

Produces a dependency-graph-as-contract architecture for a project - layers, permitted imports, trust boundary, pure core vs impure shell - plus numbered invariants and DECISIONS.md-ready entries with rejected alternatives. Use for Step 3 of /genesis:init on non-trivial projects, or when an architectural decision…

turvodnik/pf-workflow

Agent

An architect for large software tasks who first turns requirements into a written specification and then divides the work into self-contained task packets. It also records dependencies and suggested ownership.

turvodnik/pf-workflow

Agent

An executor for one task packet under the pf-do process, a workflow for completing software tasks with explicit evidence and statuses. It works within the packet's defined scope.

turvodnik/pf-workflow

Agent

A reviewer for task packets and technical specifications. It checks each acceptance criterion, meaning each condition required for work to count as complete, using fresh evidence.

duyet/kb

Agent

Patterns for running duyetbot autonomously — /loop for recurring tasks, background deploys, memory checkpoints before context compaction.

XyndoX/good-bad-ugly

Agent

The Bad — the judgment executor of the good-bad-ugly workflow. Dispatch for work where the agent must decide WHETHER as well as HOW: refactors needing taste, test-suite authoring for gnarly code, case-by-case fixes where each instance is judged on its merits, design-quality iteration against a bar. Give it a fenced…

XyndoX/good-bad-ugly

Agent

The Ugly — the mechanical executor of the good-bad-ugly workflow. Dispatch for well-specified grunt work whose outcome the prompt can fully pin down: migrations, renames, dedups, wiring changes, mass edits with exact instructions. Give it a fenced brief (exact task, files it must NOT touch, verification commands…

tslateman/duet

Agent

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

sentasity/cadence

Agent

Reviews an implementer's diff against repo conventions. Second of two review stages. Runs AFTER cadence-spec-reviewer approves. Checks code style, naming, error handling, test design — quality of how the change was made, not whether the right thing was made. Conflicts with spec-reviewer's findings are resolved by spec…

sentasity/cadence

Agent

Orchestrates /c-audit. Reads the plan + diff range + config, fans out one parameterized generic sub-agent per audit in the active roster (default + optional), synthesizes per-audit results into one structured report. Single shipped agent; per-audit sub-agents are dynamic invocations using audit-specific prompts from…

sentasity/cadence

Agent

Implements one Cadence plan task per dispatch. Reads only the task block and the files in the task's Reads: block. Writes code, tests, commits. Returns one of four statuses (DONE / DONEWITHCONCERNS / NEEDSCONTEXT / BLOCKED) with a plain-English lead. Never reads the whole repo; never inherits parent session context.

tunahanaliozturk/atelier

Agent

Implements and refactors server-side code — APIs, services, business logic — and writes its own tests. Pick for backend implementation work.

tunahanaliozturk/atelier

Agent

Implements data work — schema, migrations, queries, pipelines — and models data structures. Pick for database and data-pipeline work.

tunahanaliozturk/atelier

Agent

Reviews a draft plan, gates on user approval, decomposes it into a task graph, and routes each task to the best-matched specialist agent.

RonMizrahi/superpowers-graph

Agent

Audits a superpowers-graph run for the ways these graphs fail: a node result matching zero exit guards, a step recorded as passed that never ran, a retry loop whose counter is not being incremented, an irreversible node entered before its gates, and a decision that exists only in the transcript. Read-only — it…

dominikwozniak/dw-solo-skills

Agent

Artifacts are real work documents, committed with the code — not scratch.

dominikwozniak/dw-solo-skills

Agent

The root's layout rule — always edit skills/ /SKILL.md, never a plugins/… path — is absolute. This file is why it works and what it costs.

dominikwozniak/dw-solo-skills

Agent

Worktrees live at .claude/worktrees/ on branch ; scripts/runtime/worktree.sh owns create and remove. A claude -w session spells the branch worktree- instead, which is why dw-next strips that prefix before matching a change doc.

AAWWCC/ape

Agent

Read ${CLAUDEPLUGINROOT}/prompts/common.md and ${CLAUDEPLUGINROOT}/prompts/debugger.md, then execute the supplied StageTicket exactly.

AAWWCC/ape

Agent

APE read-only adversarial plan critic.