doodledood
- 64 skills
- 0 followers
- 78 repo stars
- 11 hours ago last updated
- ▌ Audit State Machines · doodledoodFind every implicit and explicit state machine in a codebase, model each one formally, and report every bug the model shows and the code confirms — a bad state that can be reached, a forbidden transition, a state with no way out — with its fix and an offer to turn the findings into Tickets. Changes no code. Use when the user asks to audit state machines, find implicit state machines, check status or lifecycle logic across an app, or find status or lifecycle bugs that span several files.
- ▌ Create Principles Skill · doodledoodCreate or refresh a project skill that holds one area's principles — how the project's people want design, product, prompts, architecture or other work done, and why — drawn from what they already said, so agents with or without manifest-dev start that work from it. Use when the user asks to create a principles skill, capture how the team does design, product or architecture work, or refresh an area's principles; with no area named, it offers the areas worth one.
- ▌ Orchestrate · doodledood bundleCoordinate an assigned project outcome or run ready Tickets from one effort, or the whole store, in parallel — each through run-ticket in its own session — land finished work one Ticket at a time, ticket up the debt runs leave, and keep a status page and one list of what waits on the person. By default it proposes each plan and waits for approval; with --autonomous it executes successive plans within the assignment without asking for plan approval. Use when pursuing a project outcome, choosing useful work from evidence, or when the user wants to work through the queue, run many Tickets at once, or start unattended work from a scheduler.
- ▌ Setup Project · doodledood bundleSet a project up with the surfaces manifest-dev works from — a North Star, a glossary, ADR conventions, a recommended verification harness the user may opt out of, principles skills for its high-signal areas, and the context-file wiring that makes every session use them — seeding them from the project's own history where there is any, and keep a set-up project sound by auditing it against the setup the references describe and offering each gap, marking what changed since the surfaces version it records. Use when a repository has no CONTEXT.md or decision records, when adopting manifest-dev in an existing codebase, when starting a new project, when a set-up project records no surfaces version or an older one, or when the user asks to set up the project, re-run the setup to check it is sound, bootstrap ADRs, or reconstruct decisions from history.
- ▌ Hillclimb · doodledoodImprove an existing artifact round after round toward a goal — a page, a prompt, a document, code whose speed matters, a simulation — keeping a change only when it measures better, until rounds bring no confirmed gain. Runs figure-out, define and do; quick by default, thorough when asked or when the stakes call for it. Use when the user asks to hill-climb, optimize, keep improving or make something as good as it can be for its goal, or to continue an earlier climb.
- ▌ Write Goal · doodledoodWrite one standalone goal defining what done means, in at most 4,000 characters, from a Manifest, a figure-out read, a Ticket, a handoff, a plain request or several of them. Use when the user wants to turn this work into a goal, or paste it into a goal field with no file reference behind it.
- ▌ Manifest Dev Help · doodledood bundleAnswer any question a person has about manifest-dev, with the why behind it: what it is for, its workflow and the autonomy ladder, each term a user meets (Manifest, Acceptance Criterion, Global Invariant, verification harness, recipe, ask-first, Lock, Debt, Ticket and the rest), how the parts relate, why each part exists, the practices it encodes, and what a Manifest, a run report, a pull request section or a file the workflow wrote means. Use when the user asks what something in manifest-dev is, why it works that way, how its skills relate, or where to start. Not for help with the user's own task.
- ▌ Babysit Pr 2 · doodledoodAuthor-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.
- ▌
- ▌ Example 2 · doodledoodAnalyzes the current project structure and tech stack. Use when asked to explore, understand, or summarize a project. Trigger terms: project overview, analyze codebase, what is this project.
- ▌ Telegram · doodledood bundleSend the user a one-way Telegram message or phone notification through their configured bot, including requested alerts, work completion, blockers, and decisions needing attention. Also set up the bot connection.
- ▌ Deletion Pass · doodledoodAudit a plan, design, architecture, or process for whether every requirement and mechanism earns its keep — an ordered deletion pass (question requirements, delete or absorb parts, simplify only what survives, accelerate/automate last) that reports what to cut and what to question without rewriting the artifact. Use before finalizing a design or plan, when a proposal feels over-built or accreted, or when the user asks for a deletion pass, a simplicity audit, a Musk-algorithm pass, or "what can we remove."
- ▌ Sync Pi Setup · doodledoodSyncs the current local Pi setup back into this repo's portable setup templates. Use when the user says to sync, refresh, or update this repo from their installed Pi config, extensions, models, MCP template, or agent instructions.
- ▌ Sync Tools · doodledoodRegenerate the Codex distribution copy of the plugin skills and check it for drift. Run after changing anything under claude-plugins/*/skills. OpenCode and Pi read the source tree directly and need no sync.
- ▌ Harden Task File · doodledoodHarden 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 · doodledoodAnalyze 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.
- ▌ Do · doodledood bundleManifest 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.
- ▌ Sync Claude Code Plugins · doodledoodSync 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.
- ▌ Auto · doodledoodEnd-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, or asks to tend or babysit a PR.
- ▌ Done · doodledoodCompletion 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.
- ▌ Define · doodledood bundleManifest 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.
- ▌ Design · doodledood bundleDesign and build digital artifacts: interfaces, documents, workbooks, presentations, charts, media, games, conversational tools and spatial experiences. Model the user’s work and delivery context, choose a coherent creative direction, preserve functional and accessibility requirements, and verify the delivered experience. Visual artifacts should be striking and memorable within their purpose and existing design system. Use for creating or restyling artifacts, including disposable prototypes at reduced fidelity. Finished-artifact evaluation belongs to review-design.
- ▌ Just Do · doodledoodGoal-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.
- ▌ Check Pr · doodledoodRead-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.
- ▌ Escalate · doodledoodTerminal escalation for do or just-do when unresolved blockers require outside intervention and no useful independent work remains. Reports the evidence, recovery attempts, completed work, and intervention needed.
- ▌ Just Auto · doodledoodGoal-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.
- ▌ Ticket Up · doodledood bundleAuthor 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.
- ▌ Eli5 · doodledoodExplain a topic like I'm a 5 year old. Use when the user types /eli5 <topic> or asks for a dead-simple picture explainer of how something works.
- ▌ Figure Out · doodledood bundleFigure 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.
- ▌ Poll Slack · doodledoodNarrate 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.
- ▌ Run Ticket · doodledoodRun 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.
- ▌ Example · doodledoodAnalyzes the current project structure and tech stack. Use when asked to explore, understand, or summarize a project. Trigger terms: project overview, analyze codebase, what is this project.
- ▌ Just Define · doodledood bundleGoal-based Manifest builder. Encodes shared understanding into a verifiable Manifest — Deliverables, Acceptance Criteria, Global Invariants — deciding for itself how to interview. Use when the user asks to just define it, spec it lean, or make a manifest with minimal process.
- ▌ Next Ticket · doodledoodRead 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.
- ▌ Review Code · doodledood bundleReview a change along one specific quality dimension — bugs, design, simplicity, maintainability, testability, test quality, type safety, contracts, operational readiness, docs, prose value, change intent, defect-class completeness after a fix, or context-file 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.
- ▌ Init Context · doodledood bundleSet a project up with the surfaces manifest-dev works from — a North Star, 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.
- ▌ Handoff · doodledoodProduce 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 delegation flows where a focused side-session returns context to the parent.
- ▌ Walk Pr · doodledood bundleWalk 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.
- ▌ Review Design · doodledoodReview digital artifacts against the user’s task, creative direction, functional and accessibility requirements, and actual delivery medium. Inspect renders, native files, playback or interaction as appropriate; exercise relevant failure and recovery paths and report evidence-backed findings. Use for design review or a manifest gate. Building and restyling belong to design.
- ▌ Sweep Tickets · doodledoodRecover 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.
- ▌ Teach Me · doodledoodTeach 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".
- ▌ Review Writing · doodledoodReview any prose against this project's writing standards — a README, a spec, a design doc, a blog post, marketing copy, or a draft you paste in. Detects whether the text is documentation or human-voiced writing, applies that register's rules plus the rules holding in both, and reports graded findings with the fix. Use when checking a document's style, asking whether a draft reads as AI-written, reviewing writing before publishing, or asking for a writing review outside a manifest run.
- ▌ Review Pr · doodledood bundleAutonomous 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.
- ▌ Figure Out Team · doodledoodDrive 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.
- ▌ Just Figure Out · doodledood bundleGoal-based investigation partner. Presses a topic until understanding is shared and names a read — conclusion, confidence, evidence, what would overturn it — deciding for itself how to get there. Use when the user asks to just figure something out, think it through lean, or investigate with minimal process.
- ▌ Review Prompt · doodledoodReview 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.
- ▌ Prompt Engineering · doodledood bundleCreate, 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 Holistic · doodledoodCalled by review-pr after its reviewer fleet and judgment pass return: consolidates their findings against the PR's history into the set of comments worth posting — pruning what the PR already covers, merging duplicates, subordinating defects under premise questions, bounding to the reviewed range, and rewriting every body in the caller's voice. Not for direct use.
- ▌ Review Pr Judgment · doodledoodCalled by review-pr in both of its modes: the whole-PR premise check that asks whether a change earns its keep against the pain it solves, firing only on concrete evidence and returning non-blocking author-facing questions, one per root, with no severity. Not for direct use.
- ▌ Review Pr Thread Verify · doodledoodCalled by review-pr for each unresolved review thread it authored: judges from the thread, the author's replies, and the current code whether the original concern is addressed, stale, or still standing, and returns exactly one disposition with a drafted reply where one is needed. Not for direct use.
- ▌ Human Writing · doodledood bundleResearch-backed principles for writing prose that avoids AI tells. Apply when writing articles, blog posts, emails, marketing copy, social media, or any prose content. Covers vocabulary, structure, tone, rhythm, and craft techniques that make writing feel authentically human. Not for code, commit messages, or technical documentation.
- ▌ Promote On X · doodledood bundlePromote a product by finding high-signal posts on X and crafting value-first replies. Uses Claude in Chrome for browser interaction and writing plugin for human-quality prose. Triggers: promote on twitter, promote on x, post replies on x, social media promotion.
- ▌ Babysit Pr · doodledoodBabysit a PR until merge-ready, then ask before merging. Runs pr-merge-prep on a 10-minute loop, monitors readiness (CI, reviews, conflicts), auto-stops when ready, and requires explicit user confirmation to merge. Never merges autonomously. Use when: "babysit this pr", "watch pr until ready", "keep fixing pr until mergeable".
- ▌ Research Web · doodledoodDeep web research with parallel investigators, multi-wave exploration, and structured synthesis. Spawns multiple web-researcher agents to explore different facets of a topic simultaneously, launches additional waves when gaps are identified, then synthesizes findings. Use when asked to research, investigate, compare options, find best practices, or gather comprehensive information from the web.\n\nThoroughness: quick for factual lookups | medium for focused topics | thorough for comparisons/evaluations (waves continue while critical gaps remain) | very-thorough for comprehensive research (waves continue until satisficed). Auto-selects if not specified.
- ▌ Pr Merge Prep · doodledood bundleAutonomously bring a PR to mergeable state. Resolves merge conflicts, fixes CI failures, addresses review comments, syncs PR description, and requests re-review. Designed for unattended cron execution via loop skill. Use when: "prep pr for merge", "make pr mergeable", "fix pr blockers", "autonomous pr maintenance".
- ▌ Explore Codebase · doodledoodFind all files relevant to a query with orthogonal exploration for comprehensive coverage. Returns topic-specific overview + file list with line ranges. Uses parallel agents for thorough+ levels to ensure nothing is missed.
- ▌ Address Pr Comments · doodledoodTriage and fix PR review comments. Reads comments, filters false positives (outdated, misread, wrong context, style preference), validates relevance against current diff, and fixes valid ones with confirmation. Use when: "fix pr comments", "address review feedback", "handle pr feedback".
- ▌ Build Review Persona · doodledoodBuild a personalized PR review skill by mining GitHub review history. Extracts review patterns, communication style, priorities, and blind spots — generates a calibrated review-as-me skill that posts inline comments on PRs. Use for onboarding, cloning review style, or creating a reviewer persona.
- ▌ Tend Pr · doodledood bundleTend a PR through review to merge-readiness. Classifies comments (bot/human, actionable/FP/uncertain), fixes issues via manifest amendment + scoped /do (or directly in babysit mode), tends CI, syncs PR description, and asks before merging. Use when a PR needs tending through review, or to babysit a PR. Triggers: tend pr, babysit pr, review loop, get this merged, tend this PR.
- ▌ Tend Pr Tick · doodledoodSingle iteration of PR tending. Reads PR state, classifies new events, routes fixes, reports status. Called by /loop via /tend-pr setup. Can be invoked manually to run a single tick.
- ▌ Write · doodledoodWrite prose that avoids AI tells through an iterative workflow. Gathers your context, writes using research-backed principles, reviews via writing-reviewer agent, auto-fixes HIGH+ issues, loops until clean. Use for articles, blog posts, emails, marketing copy, social media. Triggers: write content, draft article, write blog post, write email, write copy.
- ▌ Decide · doodledoodPersonal decision advisor for QUALITY over speed. Exhaustive discovery, option finding, sequential elimination, structured analysis. Use for investments, purchases, career, life decisions. Surfaces hidden factors, tracks eliminations with reasons, confident recommendations. Triggers: help me decide, should I, which should I choose, compare options, what should I do, weighing options.
- ▌ Review · doodledoodProduction-level PR review using consultant agent. 10-category framework focused on correctness.
- ▌ Consultant · doodledood bundleConsults external AI models (100+ via LiteLLM) for complex analysis. Use for architectural review, security audit, deep code understanding, or when extended reasoning is needed. Runs async with session management.