doodledood

compress-prompt

Compresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action space. Use when asked to compress, condense, or minimize a prompt.

Harden a manifest-dev task guidance file for one-shot quality — either /define's quality-gate/Default set or figure-out's probe set. Iterates: orthogonality gap analysis, user-approved additions, prompt review, fix, converge. Use when a task file needs comprehensive coverage or "harden task file".

learn-from-session

Analyze Claude Code sessions to learn what went right/wrong and suggest high-confidence improvements to skills. Use when asked to analyze a session, learn from a session, or review workflow effectiveness.

optimize-prompt-token-efficiency

Iteratively optimizes prompts for token efficiency by maximizing information density - reduces verbosity, removes redundancy, tightens phrasing while preserving semantic content. Use when asked to compress, shorten, reduce tokens, tighten, maximize density, increase information density, or make a prompt more concise.

sync-claude-code-plugins

Sync the prompt-engineering plugin from a local clone of claude-code-plugins into .claude/ so the repo is self-contained for isolated/web environments. Copies agents/skills, removes only previously-synced items that disappeared upstream. Other content in .claude/ is left alone. Use when asked to sync claude-code-plugins, pull prompt-engineering, refresh prompt-engineering plugin.

sync-tools

Generate multi-CLI distribution packages from the Claude Code plugin. Converts shared skills and package assets for OpenCode, Codex CLI, and Pi under dist/. Run after changing plugin components to keep distributions in sync.

babysit-pr

Author-side PR lifecycle babysitter and companion to review-pr. Use when the user wants to tend an existing GitHub PR through CI, review threads, description sync, mergeability, auto-fixes, or asks to babysit a PR with or without an existing manifest.

prompt-engineering

Create, update, review, or discuss an LLM prompt — a system prompt, a skill, or an agent. Use when writing or improving a prompt, discussing a skill or agent, diagnosing prompt failures, or when the user says a prompt needs work.

review-pr

Autonomous PR review that posts high-signal, human-voiced comments under your account. Use when reviewing someone else's PR or your own manifest-driven PR, when you want a precision-tuned review you can walk away from, or when the user asks to review a PR, post a PR review, autoreview, loop review, or watch a PR.

review-prompt

Review LLM prompts against the prompt-engineering skill's principles — leading with where each line came from — and report the findings without modifying files. Use when reviewing prompt quality, auditing a prompt, evaluating a system prompt, or checking whether prompt issues are high-confidence and fixable.

walk-pr

Walk through a PR or large diff together — your own or someone else's — one sub-changeset at a time and one review topic at a time within it. Use when reviewing a substantive PR collaboratively, walking a large refactor, or when the user asks to walk a PR, walk a diff, explain a PR, review collaboratively, or review a change together. Optional --canvas runs the walk in a live HTML artifact.

auto

End-to-end autonomous execution: figure-out → define → do, chained without manual approval gates. Use when you want to define and execute without intervention during planning, when the user asks for autonomous or end-to-end work, says just build it, or asks to tend or babysit a PR.

check-pr

Read-only inspection of a single GitHub PR lifecycle — checks CI, review threads, description sync, and mergeability, and returns PASS or FAIL with per-gate findings. Never invokes the merge button. Use when verifying a PR is ready to merge, polling lifecycle progress, checking mergeability, or babysitting a GitHub PR through CI and approvals.

define

Manifest builder. Turns shared understanding into a verifiable Manifest with Deliverables, Acceptance Criteria, Global Invariants, and an Initial Approach. Use when planning features, scoping refactors, debugging complex issues, or when the user asks to define, scope, plan, spec out, make a manifest, or break down a task.

do

Manifest executor. Works through Deliverables verifying every Acceptance Criterion and Global Invariant. Use when executing a manifest, running a plan, implementing a defined task, or when the user asks to run, execute, implement, or ship a manifest-backed plan.

figure-out

Figure things out together — any topic, problem, or idea. Presses relentlessly until shared understanding is reached. Use when understanding is the deliverable rather than a preamble to acting, when figuring it out is the goal, or when the user asks to think through a decision, dig deeper, press an assumption, investigate why something is happening, or work through a problem.

review-code

Review a change along one specific quality dimension — bugs, design, simplicity, maintainability, testability, test quality, type safety, contracts, operational readiness, docs, prose value, change intent, or CLAUDE.md adherence. Loads exactly one dimension reference and audits the diff against it, returning a structured PASS/FAIL report with severities. Use when verifying a change before merge, auditing a diff for a named concern, or running a manifest acceptance gate.

escalate

Structured escalation when /do hits an unrecoverable blocker. Surfaces what was tried, why it failed, and what the user can decide. Called by /do when work is blocked, cannot proceed, hits an unrecoverable failure, needs a user decision, or gets stuck.

run-ticket

Run one exact Ticket through recovery, autonomous work, and its required landing, then write DONE or ESCALATED evidence back to that same Ticket. Use when a hosted trigger, agent runner, or person supplies a specific issue, tracker item, or file Ticket to work end to end. This skill does not select backlog work or enforce Auto eligibility at dispatch.

sweep-tickets

Recover or start one unattended Ticket from a configured shared Ticket Store, then stop. Use from a scheduled agent trigger to resume one interrupted automation-owned Auto Ticket or select one ready Auto Ticket and invoke run-ticket. This is the low-frequency correctness path beside issue-event triggers, not a backlog batch runner.

auto-optimize-prompt

Iteratively auto-optimize a prompt until no issues remain. Uses review-prompt in a loop, asks user for ambiguities, applies fixes via prompt-engineering skill. Runs until converged.

handoff

Produce a self-contained context payload that lets a fresh agent continue without re-deriving what this session established. Use for cross-boundary transfer such as switching tools, starting a clean session, or handing off to another agent, and for DIY sub-agent flows where a focused side-session returns context to the parent.

teach-me

Teach the learner to deeply understand a body of work — the current session's changes, a PR, an ADR, or any topic they name — the problem and why it existed, the solution and why it was built that way, and why it matters, incrementally and confirming mastery at each stage before advancing. Use when the user wants to understand what was just built or changed, asks to be taught or walked through a change, or wants to learn the why behind the work — e.g. "teach me what we did", "teach me this PR", "explain this ADR".

done

Completion marker for the /do workflow. Outputs a plain-prose summary of what was built. Called by /do after every Acceptance Criterion and Global Invariant has fresh PASS evidence, when the manifest is complete, all criteria pass, or the workflow needs to wrap up with a completion summary.

poll-slack

Narrate new Slack messages in a channel or thread since a cursor. Returns a natural-language story of what was said, or a clear statement when there is nothing new. Use when a parent agent polls Slack and needs to know what changed, read a Slack delta, or understand a thread update without re-ingesting the whole thread.

re-pitch

Stop and re-pitch the last message — it didn't land. Re-explains with the context the reader was missing, in plain words, cutting every line that isn't value while keeping every fact that is. Use when the user says wait what, I'm lost, that didn't land, what do you mean, or asks for a re-explanation in plain English.

just-auto

Goal-based autonomous chain: figures out the task, encodes a Manifest, and pursues it end-to-end with full autonomy and minimal process. Use when the user asks to just build it, just auto it, run end-to-end goal-based, or go from idea to done without approval gates.

just-do

Goal-based Manifest executor. Reads a Manifest and pursues it with full autonomy: reach a state where every Acceptance Criterion and Global Invariant holds, deciding for itself how to get there. Use when the user asks to just do a manifest, run it goal-based, or execute with minimal process.

init-context

Set a project up with the surfaces manifest-dev works from — a glossary, ADR conventions, and the context-file wiring that makes every session use them — seeding them from the project's own history where there is any. Use when a repository has no CONTEXT.md or decision records, when adopting manifest-dev in an existing codebase, when starting a new project, or when the user asks to initialize project context, bootstrap ADRs, or reconstruct decisions from history.

Web & Frontend Solid

next-ticket

Read the project's Ticket store, choose the single best Ticket for the human-plus-AI session to work on now, claim it, and present it with the reason it leads. Use when asking what's next, what should I work on, or pulling the next Ticket from the backlog. Selection stops after presentation; execution belongs to run-ticket or the person holding the claim.

ticket-up

Author self-sufficient Tickets in the project's store from a finished Manifest, a direct work request, an open question, or follow-up findings from another Ticket. A Manifest becomes one coherent Shaped Ticket by default; split it by Deliverable only when the caller explicitly wants delegation or parallel pickup. Use when creating Tickets, ticketing up a plan, recording follow-up work, or handing work to a teammate, agent, or later session.

figure-out-team

Drive a multi-party deliberation in a Slack channel or thread. The agent is an involved orchestrator — presses rigorously, brings evidence, names trade-offs, surfaces disagreements, advances when answers cohere; owner-by-Slack-handle overrules. Use when the people involved cannot all sit in one chat, when deliberation has to happen in Slack, or when the user asks to figure out with the team, press a group asynchronously, or get the team aligned.