cleanexpo

@cleanexpo source repo

365 skills
0 followers
16 hours ago last updated

▌
Skybridge · cleanexpo bundle
Guide developers through creating and updating ChatGPT and MCP apps. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools/views, debugging, running dev servers, deploying and connecting apps to ChatGPT. Use when a user wants to create or update a ChatGPT app, MCP app, MCP server or use the Skybridge framework.

0
installs
▌
Tao Judge · cleanexpo
Single-scalar termination gate for the TAO judge-gated loop. Wraps a Sonnet evaluator call that scores a goal-state pair and returns a structured JudgeVerdict (done, reason, score 0..1, next_action_hint). The autoresearch principle — autonomy mandate gives intent, judge() gives a measurable termination condition.

0
installs
▌
Visual QA · cleanexpo
Playwright-powered visual testing skill. Captures screenshots at multiple breakpoints and colour schemes, runs visual regression tests, validates design implementation against DESIGN.md, and generates baseline snapshots for CI.

0
installs
▌
Wayfinder · cleanexpo
Chart a foggy, bigger-than-one-session effort as a shared map of decision tickets on Linear, then work the map one decision per session until the way is clear.

0
installs
▌
Wiki Lint · cleanexpo
Weekly health check for the Brain-1 wiki. Finds orphan pages, missing cross-refs, stale claims, and contradictions. Fixes orphans and cross-refs automatically; flags stale/contradictions for founder review. Run every Saturday or manually with "lint the wiki".

0
installs
▌
Audit Emit · cleanexpo
Centralised audit emitter sitting in front of every Dispatcher step + every Scribe send + every CoS routing decision. Writes to .harness/swarm/swarm.jsonl (existing immutable append) and optionally fires Langfuse webhooks for off-Pi-CEO observability. Closes Hermes Sprint 1 SWARM-006 + the audit-immutable safety control.

0
installs
▌
Cmo Growth · cleanexpo
Daily marketing visibility across the 11 Unite-Group businesses. Computes LTV:CAC, blended CPA, channel concentration (HHI), attribution decay from ad-platform feeds. Drafts a 1-page CMO snippet into the daily 6-pager. Gates ad-spend over $5,000/day through draft_review HITL. Closes Wave 4 A2 of the senior-agent slate (RA-1860).

0
installs
▌
Deployment · cleanexpo
Deployment constraints and runtime behaviour for Railway (backend) and Vercel (frontend) — proxy config, redirects, Telegram, SSE limits, and model routing.

0
installs
▌
Merge Gate · cleanexpo bundle
Use before opening any PR, pushing to a shared branch, or merging in this estate — where automation force-readies draft PRs and squash-merges them on green within minutes, so opening a PR is authorising its merge. Fires when about to run gh pr create / gh pr ready / gh pr merge, or push to a deploy-on-push branch.

0
installs
▌
Ship Chain · cleanexpo
Ship Chain orchestrator. Routes /spec /plan /build /test /review /ship commands to the correct pipeline phase, enforces gate requirements between phases, and validates artifact completeness before allowing progression.

0
installs
▌
Tao Skills · cleanexpo
Master index of all 31 TAO skills.

0
installs
▌
Wiki Query · cleanexpo
Query the Brain-1 wiki before hitting external research. Returns an answer grounded in accumulated founder context plus a confidence score and go_external flag. Use on every Margot research request before firing deep_research or realtime calls — cache hit rate target 60-70% for repeat topics.

0
installs
▌
Artlist MCP · cleanexpo bundle
Use when a task needs AI image or video generation — campaign visuals, hero shots, product or social video, thumbnails, ad creative, localized variants — through the official Artlist MCP (mcp.artlist.io, 100+ models incl. Nano Banana Pro, Seedance 2.0, Kling 3.0, Veo 3.1, Sora 2). The model catalog is discovered live from the server every session, never a stored or cached list. Use also before any autonomous run that could touch media generation, because it carries the credit-spend gate. Covers connection per surface, live model selection, the iterate-in-conversation loop, and failure handling.

0
installs
▌
Define Spec · cleanexpo
Spec writer. Converts a raw idea into a structured specification with PITER classification, goals/non-goals, Given/When/Then acceptance criteria, and explicit constraints. Output is a spec.md ready for the /plan phase.

0
installs
▌
Propose Fix · cleanexpo
Produce the repair as a diff plus a regression test, never applied directly. Bounded to three attempts, each materially different, then it stops and reports the diagnosis rather than the error. Use only after `classify` returns proceed.

0
installs
▌
Tier Worker · cleanexpo
Workers execute discrete, well-scoped tasks quickly.

0
installs
▌
Verify Test · cleanexpo
Test verifier. Interprets smoke test and CI results, classifies pass/fail, detects flaky tests and coverage regressions, and produces a structured verdict with a recommendation for the /review gate.

0
installs
▌
Wiki Growth · cleanexpo bundle
Senior-review-board audit of the 2nd Brain vault — challenge shortlisted ideas, assign dispositions, route survivors to storm/spm/skill-authoring. Writes only inside its _system/wiki-growth/ sandbox.

0
installs
▌
Wiki Ingest · cleanexpo
Write a research finding, Board session output, or Margot insight back into the Brain-1 wiki. Updates existing pages in place, creates new pages if warranted, appends to log.md, and re-uploads changed files to the Gemini corpus. Use after any research session, Board deliberation, or when the operator says "save this to the wiki".

0
installs
▌
Agent Expert · cleanexpo
Act-Learn-Reuse cycle for agent improvement over time.

0
installs
▌
Agentic Loop · cleanexpo
Infinite self-correcting iteration until completion criteria met.

0
installs
▌
Architecture · cleanexpo
Architectural conventions and anti-patterns specific to Pi-Dev-Ops — companion model, sandbox isolation, ZTE leverage, CLAUDE.md hygiene, parallel dispatch, topology-first autonomy.

0
installs
▌
Design Audit · cleanexpo
DEPRECATED (RA-7057) — superseded by the installed pbakaus/impeccable skill v3.9.1. Use `impeccable` (`/impeccable audit`, `/impeccable critique`, `/impeccable polish`, `/impeccable bolder`) instead. Kept for the archaeological record; do not route new work here.

0
installs
▌
Design Board · cleanexpo bundle
Five-persona deliberation skill for brand design — 15+ years of typography, layout, colour, motion, and 3D expertise. Five subagents (Art Director, Brand Systems Architect, Motion Designer, WebGL/3D Specialist, Critic) propose, cross-examine, and synthesise N concrete variants of a brand visual identity. Each variant is a complete `.design.md` + `.motion.md` (+ optional `.scene.md`) that the design-iterate loop hands back to the client (the user) for review. Triggered by `design-iterate`, or directly when the user says "convene the design board for {brand/brief}".

0
installs
▌
Hooks System · cleanexpo
Use when adding lifecycle hooks or safety guardrails to a project — the 6 hook types plus the starter guardrail hookset (danger-word block, scope-lock, draft-only).

0
installs
▌
Meta Curator · cleanexpo
Skill self-authoring agent. Reads .harness/lessons.jsonl (weekly) and merged-PR diffs (daily), proposes new SKILL.md drafts via the existing skill-creator skill, and surfaces them through Scribe → telegram-draft-for-review for user 👍 before adding to the registry.

0
installs
▌
Model Router · cleanexpo bundle
Use before substantive work when choosing whether to work inline, delegate, fan out, or escalate based on ambiguity, stakes, scope, repetition, privacy, and prior failure.

0
installs
▌
Orchestrator · cleanexpo
Continuity spine from idea to ship. Runs an OUTER loop that pushes work hub-to-spoke out to estate projects, and an INNER loop that audits itself against the constitution — trimming cache, flagging hallucinations, tightening code generation. Does NOT do the work; it routes, gates and carries state. Pulls a skill only when a stage needs it and releases it immediately, to protect context. The constitution is a hard gate checked before every self-modifying action. Stops for exactly two things — spending money and touching production. A denied action is terminal. Use when running a project end-to-end, resuming a stalled build, or dispatching work across multiple estate repos.

0
installs
▌
Pii Redactor · cleanexpo
Detect and redact personally identifiable information from any payload before it enters logs, prompts, or outbound messages. ≥95% precision, ≤5% false-positive rate. Non-negotiable in front of every Scribe send and every email-listener intake. Closes Hermes Sprint 1 SWARM-005 requirement.

0
installs
▌
Ship Release · cleanexpo
Release gatekeeper. Validates all pipeline phases are complete, enforces the review score ≥ 8/10 hard gate, documents the ship event, and updates the Linear ticket to Done. Produces a ship-log.json.

0
installs
▌
Zte Maturity · cleanexpo
Zero Touch Engineering maturity model — 4-level assessment with explicit scoring criteria per dimension.

0
installs
▌
Agent Browser · cleanexpo
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers.

0
installs
▌
Agentic Layer · cleanexpo
Design products with agent-native architecture.

0
installs
▌
Control Scope · cleanexpo bundle
Use when a check has RUN and you are about to say what it proved, or when choosing where to plant a canary, narrow a search, or enumerate the surface a guard covers. Answers ONE question, what did the instrument actually look at and what sentence am I permitted to write. Catches searches aimed at the wrong name, checks that enumerate a fixed set and go stale, canaries planted where the instrument was already known to reach, and claims upgraded from "within targeted scope" to "by discovery". Triggers on "confirmed", "nothing found", "scanned clean", "no matches", "I searched for", "-maxdepth", "--include", "sampled", "the broad search timed out", "we use discovery now".

0
installs
▌
Daily 6 Pager · cleanexpo
Stripe-style daily executive brief assembled from CFO + CMO + CTO + CS snippets, the latest Margot deep-async insight, and RA-1842 (iOS release) status. Cron-fired at user-local 06:00. Routes through pii-redactor + draft_review HITL gate. Closes Wave 4 A5 of the senior-agent slate (RA-1863).

0
installs
▌
Design System · cleanexpo
Design stack orchestrator for Pi-CEO. Routes UI work to the correct specialist skill (design-intelligence, ui-component-builder, impeccable, visual-qa). Start here for any design task.

0
installs
▌
Intent Parser · cleanexpo bundle
Classify an inbound Telegram message into one of six intent types so the Chief of Staff can route to the right role. Use this on every Telegram message that lands in Pi-CEO before any routing decision.

0
installs
▌
Launch Review · cleanexpo
Aggregate the repo's existing audit skills into ONE prioritized launch-readiness report through four lenses — PM journey, growth/SEO, engineering, design — adding only the two lenses nothing else covers (end-to-end PM journey + growth/SEO conversion) and fanning out to security-audit, impeccable, agentic-review, and leverage-audit for the rest. Review only; never fixes. Use on "is this ready to launch" or as the review step of /ship-it.

0
installs
▌
Margot Bridge · cleanexpo
Bridge from Pi-CEO orchestrator to Margot's standalone Gemini-powered research MCP server at ~/.margot/. Use when intent is research-shaped (deep_research / deep_research_max) or image-gen, or when corpus diagnostic is needed. Margot is owned separately; this skill never modifies her source.

0
installs
▌
Tao Boomerang · cleanexpo
Token-efficient one-shot dispatch with summary-only return. Caller asks a question, the worker replies with ONLY the answer — no preamble, no chain-of-thought, no markdown unless the answer requires it. Composes on `_run_claude_via_sdk`. Use when you need the answer, not the conversation.

0
installs
▌
UI UX Pro Max · cleanexpo
Full-stack design workflow skill. Orchestrates all four design layers (intelligence, build, audit, visual-qa) end-to-end with maximum quality settings. Use for ambitious UI work — new pages, design system extensions, and design sprints.

0
installs
▌
Agent Workflow · cleanexpo
Use when defining, scoping, promoting, or debugging an agent or ADW — the 5-part agent contract, scoping formula, promotion ladder, and 4-way break diagnostic.

0
installs
▌
Agentic Review · cleanexpo
Review agent output for quality, not just correctness.

0
installs
▌
Auto Generator · cleanexpo
Generate tier configs from project briefs automatically.

0
installs
▌
Chrome Browser · cleanexpo
Use when the user asks to browse, click, navigate, fill a form, screenshot, or read content from a live website via the claude-in-chrome MCP tools — or whenever a task needs to drive an actual Chrome tab rather than fetch static HTML.

0
installs
▌
Claim Verifier · cleanexpo
The runnable cite-or-cut gate for FINISHED Nexus copy — walks every checkable factual claim in a completed asset, resolves each to a substantiation record or cuts it, runs the Australian Consumer Law excluded-tactics deny-list, and freezes the Substantiation Ledger before publish. Use as the last gate before any copy asset ships — landing page, service page, ad, email, franchise-recruitment copy. Triggers on "cite-or-cut", "substantiate this copy", "claim check", "can we publish this", "freeze the ledger", "is every claim proven", "ACL check the copy". NOT research (that is `storm`), NOT trust scoring (that is `eeat`).

0
installs
▌
Claude Runtime · cleanexpo
Rules for invoking Claude correctly — subprocess vs SDK mode, stream-json parsing, MCP SDK imports, Railway vs local environment differences.

0
installs
▌
Control Design · cleanexpo
Use BEFORE writing or changing any check, test, gate, guard, assertion, exclusion, fixture or startup config branch — while the control is being built, not when its result is read. Catches controls that cannot fail, exclusions whose premise has expired, checks that know a fixed set and go stale, verifications that require handling the thing they protect, and missing-config branches that invent a credential instead of refusing to start. Triggers on "add a check", "write a test for", "gate this", "skip/exclude this path", "assert that", "guard against", or any first run of a new control.

0
installs
▌
Design Approve · cleanexpo
Labelling + cache step. Once the user approves a variant in design-iterate, this skill writes the canonical brand spec files (`{slug}.design.md`, `{slug}.motion.md`, optional `{slug}.scene.md`), generates the standalone `{slug}.html` preview file, snapshots the iteration to the approved-variant cache, and triggers `remotion-brand-codify` to write the BrandConfig.ts runtime fields. Treats approval as a commit point.

0
installs
▌
Design Iterate · cleanexpo
Iteration loop driver for brand design. Calls design-board to generate N variants, renders each at three breakpoints (mobile/tablet/desktop) via the preview-canvas + Claude Preview MCP, presents screenshots to the client (the user) via AskUserQuestion, captures feedback, refines, and repeats until the user approves a variant. The visible canvas the client uses to actually SEE designs.

0
installs
▌
Email Listener · cleanexpo
Convert inbound Gmail messages into Pi-CEO sessions via webhook → intent-parser → orchestrator. Closes the "no email-triggered session creation" gap. Use this when Phill wants Pi-CEO to act on emails — replies, ticket creation, research dispatch — without him CC-ing it manually.

0
installs
▌
Launch Charter · cleanexpo
The immutable governance charter every autonomous launch agent loads FIRST. Defines what agents may improve freely vs. what they may never touch (permissions, spend caps, safety, irreversible actions). Binds the generic self-improvement rails to Pi-Dev-Ops's real AGENTS.md boundary matrix. Use at the top of /ship-it, every cron run, and before any builder agent starts.

0
installs
▌
Leverage Audit · cleanexpo
12 Leverage Points diagnostic for agent autonomy — with explicit scoring rubrics and ROI guidance.

0
installs
▌
Margot Routing · cleanexpo
Linear routing checklist for Margot — place broad ideas in the parent project first, then copy to vertical projects only where scope belongs. Use when Margot creates tickets, triages founder ideas, or spans portfolio repos.

0
installs
▌
Pi Integration · cleanexpo
Bridge TAO to pi-mono runtime for multi-provider support.

0
installs
▌
Pi SEO Scanner · cleanexpo
Scan interpretation specialist for Pi-SEO findings. Applies blast-radius scoring to prioritise findings, detects false positives, classifies into fix-now/schedule/suppress/investigate buckets, and recommends scan config changes per project.

0
installs
▌
Review Command · cleanexpo
Review Command

0
installs
▌
Security Audit · cleanexpo
Senior Security Officer (15+ years white/black hat experience). Deep-audits codebases for OWASP Top 10, supply-chain risks, secrets exposure, auth flaws, injection vectors, CSP misconfigs, and weak crypto. Produces a prioritised CVE-style finding report with CVSS scores and remediation steps.

0
installs
▌
Senior Harness · cleanexpo bundle
Use before substantive project work that requires governed discovery, delegation, verification, or recovery from repeated failure.

0
installs
▌
Technical Plan · cleanexpo
Technical Plan Skill

0
installs
▌
Tier Architect · cleanexpo
Design tier configurations - which models for which roles.

0
installs
▌
Tier Evaluator · cleanexpo
QA agent that grades output against explicit acceptance criteria. Skeptical by default. Blocks on failure.

0
installs
▌
Token Budgeter · cleanexpo
Track and enforce token budgets per tier.

0
installs
▌
Autonomy Ladder · cleanexpo
Capability-tiered autonomy gating for all agent action — maps the DeepMind AGI→ASI continuum (arXiv:2606.12683) onto four autonomy tiers (L0 advise → L3 strategic/irreversible), each with an explicit gate. Use to decide "can this agent do this action un-gated, or must it stop for a human/Board?" before any autonomous or multi-move execution, and to design where the gate is ENFORCED. Triggers on "autonomy ladder", "autonomy gate", "can the agent do X autonomously", "gate this action", "should this escalate", multi-move executor design. The formal, capability-scaled version of the decision-rights matrix.

0
installs
▌
Browser Routing · cleanexpo
Use when a task needs a browser — automating a web flow, reviewing or improving UI, debugging a page, recording evidence, or QA-testing a deploy — before picking a browser tool or writing a browser-touching skill.

0
installs
▌
Context Cockpit · cleanexpo
Audit and reclaim a session's context/token budget in one pass — read /context, trim MCP tools, clear vs compact, CLI-over-MCP, model ladder, red-MCP triage.

0
installs
▌
Cross Tool Flow · cleanexpo
Declarative YAML/JSON authoring surface over dispatcher-core. Lets the user (or Margot, or Scribe) define multi-step cross-tool flows in plain text — chain Linear, Gmail, Calendar, Margot, Composio MCP tools — and run them via Dispatcher. Wave 2 surface; engine is dispatcher-core in Wave 1.

0
installs
▌
Dispatcher Core · cleanexpo bundle
Cross-tool workflow primitive. Executes a declared sequence of steps that chain Linear, Gmail, Calendar, Margot, Composio, or any registered MCP tool. State persisted to .harness/dispatcher_state.json so kill-switch + crashes don't lose progress.

0
installs
▌
Forward Planner · cleanexpo bundle
Research a project and plan 15+ moves ahead before building anything. Establishes the win condition (Definition of Done), reads the board (repo + PORTFOLIO registry + live external research), computes the gap, lays a roadmap spine of 15+ verifiable moves, forks branch points where outcomes are contingent, and red-teams the end-state to surface the "move-16 surprise" before it bites. Produces BOTH a human-readable foresight brief AND a machine-readable structured plan the swarm can execute. Use this FIRST whenever you (or the autonomous loop) are about to build, scope, or roadmap a project — and whenever someone asks "what's the full path to X", "what are we missing", "plan N moves ahead", "think this through", or talks about strategy, foresight, lookahead, sequencing, dependencies, or roadmaps. Use it even when the request just says "build project X" — map the whole path before executing the first step.

0
installs
▌
Heygen Director · cleanexpo
heygen-director — HeyGen / HyperFrames specialist

0
installs
▌
Incident Memory · cleanexpo
Write symptom, cause, fix, reviewer verdict and outcome to a searchable store — successes and failures alike. This is the store `classify` reads to decide known versus novel. Use as the final step of every self-healing chain, including chains that stopped early or gave up.

0
installs
▌
Piter Framework · cleanexpo
5-pillar AFK agent setup - Prompt, Intent, Trigger, Environment, Review.

0
installs
▌
Product Manager · cleanexpo
Senior Product Manager Engineer (15+ years SaaS delivery). Audits feature completeness vs advertised capabilities, identifies user journey gaps, evaluates documentation quality, and produces a prioritised product backlog aligned with business outcomes.

0
installs
▌
Remotion Script · cleanexpo
Use when a Remotion marketing video needs a timed script, scene narration, on-screen text, CTA, and voice pacing that fits a single ElevenLabs voice.

0
installs
▌
Scheduled Tasks · cleanexpo
Guidelines for writing reliable scheduled task prompts via the Claude scheduled-tasks MCP.

0
installs
▌
Session Handoff · cleanexpo
Durable session handoff (/session-handoff). Gates the tree green via scripts/handoff-loop.sh, classifies the session SHIPPED / READY-TO-SHIP / WIP-BLOCKED against a Definition-of-Done, then generates a precise handoff before stopping, switching terminals, opening a PR, handing work to another agent, or resuming later. Refuses to present unfinished work as a clean stop; for ready work hands off the exact merge-gate-guarded ship command. Writes a durable report + healthcheck log; the "1" of the 1-2 combo with /resume-from-handoff. Captures what was done, decisions locked, what shipped, key files, running state, verification, deferred/open questions, exact pickup point, risk notes, and a quality check.

0
installs
▌
Tao Context Vcc · cleanexpo
Deterministic, LLM-free conversation compactor for TAO sessions. Port of @sting8k/pi-vcc. Reduces transcript bytes via tool-output dedup, verbose-block head/tail truncation, repeat-pattern collapse, and whitespace normalisation. No model calls — runs in the hot path with zero token cost.

0
installs
▌
Brand Ambassador · cleanexpo
Generate brand-consistent content, copy, and messaging aligned with Pi-CEO tone and values.

0
installs
▌
Calendar Watcher · cleanexpo
Convert calendar event creation/modification/deletion into Pi-CEO actions. Use for time-anchored triggers — meeting prep 30min before, post-meeting summary, conflict detection, schedule reflow when an urgent block lands. Pairs with email-listener for the "calendar invite arrived in email" pattern.

0
installs
▌
Geo Optimization · cleanexpo
Generative + Answer Engine Optimization (GEO/AEO) standard for AI search visibility — the 2026 successor to SEO. Use when adding or auditing GEO infrastructure (llms.txt, JSON-LD schema, WebMCP, Lighthouse Agentic) OR AEO content-layer work (becoming the cited/quoted answer inside ChatGPT, Perplexity, Gemini, Google AI Overviews) on any portfolio site or via the Synthex client-audit module.

0
installs
▌
Northstar Shipit · cleanexpo
NorthStar add-on for /northstar and /ship-it. Removes noisy branches, picks the highest-value straight path to ShipIt, and hands only the approved launch-ready lane into the existing launch-charter → ship-it → ship-chain machinery.

0
installs
▌
Pi Ceo Docparser · cleanexpo
Parse PDF / DOCX / TXT into structured ParsedDoc (text + pages + tables + metadata). Pure deterministic extraction, no LLM call. Foundation for ICP-research workflows; consumed by marketing-icp-research.

0
installs
▌
Proof Discipline · cleanexpo
Use whenever about to mark a test, gate, verification or task as passing / GREEN / complete / fixed / shipped — the moment a CLAIM is made, not when a check is written. Catches vacuous verification, claims asserted but never checked against the live system, silent caps, deployed-vs-source drift, coverage gaps that hide non-functioning code, and green results whose control was aimed at the wrong target. Triggers on "tests pass", "it's green", "verified", "done", "complete", "fixed", "shipped".

0
installs
▌
Remotion Editing · cleanexpo
Use when a Remotion video has timing, sync, transition, caption, pacing, or audio-fit risk and needs editing discipline before render.

0
installs
▌
Tao Context Mode · cleanexpo
Summary-index + on-demand expansion. Walks a repo once, summarises every source file (~200B vs raw 5-50KB), and serves the FULL file only when callers `expand(path)`. Port of `context-mode`. No LLM calls — pure regex + first-comment synopsis. Deterministic; sha256-keyed for invalidation.

0
installs
▌
Tao Tdd Pipeline · cleanexpo
Test-first iteration pipeline. Composes on tao-loop + tao-judge to enforce red→green→refactor discipline. The judge is bound to "all tests pass + new test files modified". Without test files in the diff, GOAL_MET is rejected.

0
installs
▌
Creative Director · cleanexpo bundle
Use when someone asks to build, design, make, create, or generate any deliverable from a short prompt — a deck, web page, report, poster, campaign, brand look, prototype — especially when the prompt is underspecified. Resolves the subject and client persona, grills only the gaps with one checkbox screen, routes to the right specialist skills and MCPs, and runs a polish gate before handoff. Do not start generating for such requests without this skill.

0
installs
▌
Output Tournament · cleanexpo
Use when a creative brief has multiple plausible directions and picking wrong is costly — landing-page hero copy, taglines, headlines, hooks, video concepts, design directions. Generate several diverging variants, judge them independently, synthesise a winner. Not for high-stakes decisions or cross-domain review of one shared draft.

0
installs
▌
Prove The Failure · cleanexpo
Build a tight, red-capable feedback loop that drives the actual failure path and asserts the exact symptom, before any hypothesis is formed. One command, already run once, deterministic, fast, agent-runnable. Use at the start of any self-healing chain, or whenever something is broken/failing/slow and you are tempted to read the code and guess. First link in the self-healing chain; hands off to `contain`.

0
installs
▌
Remotion Designer · cleanexpo
Visual-design specialist for Remotion compositions. Sets layout grid, typography hierarchy, white-space, scene framing, and visual rhythm for a given composition + brand. Triggered after remotion-composition-builder for QA, or upfront when authoring a new composition type. Produces a layout spec consumed by remotion-composition-builder.

0
installs
▌
Sandcastle Runner · cleanexpo
The primitive. Wraps a single Sandcastle invocation (`npx sandcastle run`) so Pi-CEO orchestrator can spawn AFK code-executing agents in isolated Docker / Podman / Vercel-Firecracker / Daytona sandboxes. Pluggable agent (Claude Code / Codex / Pi / OpenCode) and pluggable sandbox provider. Stream stdout into session.logs. Pre-flight kill-switch + concurrency cap. Closes Wave 5

0
installs
▌
Skybridge Rollout · cleanexpo
Unite-Group rollout plan for Skybridge MCP-Apps framework — which businesses get an MCP App, in what order, with what auth, and how to productize it via Synthex. Invoke when planning, scoping, or building any MCP App across the portfolio.

0
installs
▌
Tao Codebase Wiki · cleanexpo
tao-codebase-wiki

0
installs
▌
Tier Orchestrator · cleanexpo
The orchestrator plans, decomposes briefs, and delegates to lower tiers.

0
installs
▌
Vercel Env Puller · cleanexpo
Per-project Vercel env-var manifests (NAMES + targets only — never values). At Sandcastle launch time, resolves the named vars in-memory via `vercel env pull`, injects into the sandbox via Sandcastle's `agent.env`+`sandbox.env`, and never writes a secret to disk inside Pi-CEO. Closes Wave 5

0
installs
▌
Adversarial Review · cleanexpo
Review a proposed fix with a different model in a fresh session that has no access to the builder's reasoning. Two axes, standards and spec, run as independent sub-agents. It flags; it never fixes. A fail returns to `propose-fix`. Use after `propose-fix`, before anything is applied.

0
installs
▌
Claude Max Runtime · cleanexpo
Execute TAO natively within Claude Max subscription.

0
installs
▌
Closed Loop Prompt · cleanexpo
Self-correcting prompts with embedded verification.

0
installs
▌
Context Compressor · cleanexpo
Compress context at tier boundaries to save tokens.

0
installs
▌
Design Canvas HTML · cleanexpo
Generates a self-contained `{slug}.html` preview file that demonstrates a brand's full design system (palette + WCAG contrast + typography scale + component recipes + motion samples + optional 3D scene) inline — no server, no build, opens directly in any browser. Used by design-approve to ship a portable canvas alongside the canonical spec files. Mirrors the routes in preview-canvas/app/brand/[slug] but flattened into one HTML file.

0
installs

365 published skills · page 2 of 4