← All creators

wayne930242

User

Task coordination for Codex CLI and Claude Code: carry bounded work directly or dispatch Herdr-backed sessions rooted in each app, from single-app repos to monorepos.

16 indexed · 0 Featured · 5 stars · avg score 76
Prolific

Categories

Indexed Skills (16)

AI & Automation Listed

boss-say

The single entry point for handing any work to straw-boss — implementation, audit, research, diagnosis, or anything else this session already has an available skill for. Use whenever the user hands work over or asks for something to be looked into — one item, a handful, or a whole backlog — e.g. "boss say <...>", "work on this", "implement X in <app>", "audit this module", "how does X work here", "X is failing", "work through this backlog". This skill judges the scale and, per item, the execution tier (a plain subagent, or a dispatched agent rooted in the app) and picks the dispatch shape (one item via a specialist skill or a better-fitting available skill, a capped batch in this turn, or a self-paced `/loop` batch).

4 Updated today
wayne930242
AI & Automation Listed

create-great-harness

Use when init finds an app with no CLAUDE.md and no .claude/ directory at all and the user agrees to bootstrap one, or when the user directly asks to set up a minimal agent system for an app that doesn't have one yet.

4 Updated today
wayne930242
AI & Automation Listed

dispatching-work

Internal machinery that starts, tracks, lists, and closes out the agents this plugin runs — one per dispatched task, each rooted in its resolved app's own directory. Use after `boss-say`'s execution-tier call has landed on dispatch, for any of its specialist skills (`shipping-task`, `inspecting-app`, `investigating-app`, `troubleshooting-app`), once `work-on` has resolved the target app(s) (or a plan). Not this skill's to front directly — a user's status question ("what's running", "wrap this up") goes through `boss-say`, which calls the List/Wrap-up branches below. Not for one dispatch's live content (`peeking-work`).

4 Updated today
wayne930242
Data & Documents Listed

init

One-time (or occasional) setup for straw-boss in a project. Use when the user says "straw-boss init", runs it for the first time in a repo, or another straw-boss skill reports no apps config or no capability record exists yet.

4 Updated today
wayne930242
Testing & QA Listed

inspecting-app

Use when the user wants to check or audit something against existing rules or conventions, scoped to one of the project's managed apps, e.g. "audit this module", "check if X follows the rules" — not for open-ended research into how something currently behaves with no rule in question (investigating-app), diagnosing a reported failure (troubleshooting-app), or implementing a fix (`boss-say`).

4 Updated today
wayne930242
AI & Automation Listed

investigating-app

Use when the user wants to understand how something currently works or is structured, scoped to one of the project's managed apps, with no rule violation or reported failure in question, e.g. "how does X work here", "understand how Y is implemented" — not for auditing against rules (inspecting-app), diagnosing a reported failure (troubleshooting-app), or implementing a fix (`boss-say`).

4 Updated today
wayne930242
AI & Automation Listed

notifying-main-agent

Route a dispatched agent's questions, progress, and status to its recorded main agent.

4 Updated today
wayne930242
AI & Automation Listed

shipping-task

Carries one task through a standardized git lifecycle in one of the project's managed apps. Normally invoked by `boss-say` once it has triaged a request down to a single unit of work; also usable directly when the user names it. Not for deciding how work gets dispatched (`boss-say` owns that), scoping/planning the task (your project's task-scoping skill), picking the app (`work-on`, invoked internally here), or many independent tasks at once (`boss-say`'s batch path).

4 Updated today
wayne930242
AI & Automation Listed

troubleshooting-app

Use when something is broken and the cause is unknown, scoped to one of the project's managed apps, e.g. "X is failing", "500 in production for <app>" — not for a known task with a clear fix already in mind (`boss-say`), a rule/convention audit (inspecting-app), or open-ended research into current behavior with no reported failure (investigating-app).

4 Updated today
wayne930242
AI & Automation Listed

work-on

Determines which of the project's managed apps a request belongs to. Use when straw-boss's other skills (boss-say and the shipping-task lifecycle it drives, inspecting-app, investigating-app, troubleshooting-app) need to resolve their target app as a shared first step, or when you just need to know which app a request belongs to without starting one of those flows.

4 Updated today
wayne930242
AI & Automation Listed

i-am-orchestrator

The main agent's own default operating stance while running as straw-boss's orchestrator — drive dispatched work to completion and state decisions rather than ask for them. Injected automatically at session start for a candidate main-agent session, never for a dispatched worker (see `hooks/hooks.json`). Also invocable directly as a mid-session reminder.

4 Updated today
wayne930242
AI & Automation Listed

peeking-work

Use when checking a dispatched task's live progress without joining or interrupting it, or judging whether a stuck/failed task looks like a permission denial. Not for status alone (`dispatching-work`'s list branch).

4 Updated today
wayne930242
AI & Automation Listed

asking-peer-agents

Use when a dispatched agent needs another dispatched task's live progress or latest conclusion.

4 Updated today
wayne930242
Web & Frontend Listed

grill-with-web

Use whenever there's an unresolved decision that's the user's to make — "grill this in the browser", "web version of grilling", "grill with a live decision tree", or any plan/design/idea that needs stress-testing. Prioritize this over the terminal-based grilling/grill-me/grill-with-docs by default. Runs the interview in the browser with a live decision tree, in the conversation's current language, layering in grill-with-docs' ADR/CONTEXT.md recording where the decision warrants it.

1 Updated 4 weeks ago
wayne930242
Web & Frontend Listed

open-gui

Use when the user wants a browser-based GUI for a Claude Code session — "open a GUI", "browser terminal", "web version of claude", or a live decision-tree panel alongside the conversation. Also the dependency other skills reach for when they need a session running in a browser (e.g. grill-with-web) — invoke it with a seed prompt and topic rather than reimplementing PTY/browser plumbing.

1 Updated 4 weeks ago
wayne930242
Web & Frontend Listed

grill-with-docs

Use when starting project code-improvement work — refactoring, architecture improvement, cleanup of an existing codebase — or when a grilling session should leave docs behind. Runs the interview and records decisions as ADRs and domain terms in CONTEXT.md as they crystallise.

1 Updated 4 weeks ago
wayne930242

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.