eidos-marketplace

Use when the user asks about Eidos, Eidos AGI, platform status, `eidos do`, closeout, cleanup before done, docket-task orchestration, evidence verification, praxis learning, gateway routing, vault/secrets, plugins, or which Eidos AGI specialist system should handle a task. This skill tells Codex to call the installed `eidos` CLI first; MCP and plugins should only point to CLIs, while CLIs provide progressive reveal of the deeper tool graph.

Investigate current context before predicting likely futures, failures, user objections, and concrete changes. Use when Zoltar needs to research an app, plugin, architecture, workflow, plan, decision, or implementation and answer what is likely to go wrong, what evidence supports it, what complaint or failure is being prevented, and what should change today.

Answer a specific foresight decision question with researched evidence, a clear judgment, likely futures, user complaint prediction, and concrete changes. Use when Daniel asks whether an idea, implementation, plugin, architecture, or workflow is likely to be regretted, whether it is the right thing in the right place with the right authority, or what decision should be made given future effects.

Compatibility entrypoint for Zoltar foresight. Use when Daniel mentions Zoltar, asks to predict the future, asks for second-order effects, asks what he will complain about, or wants future-backed product/spec changes; route the work through researched evidence, judgment, structured output, doer/checker handoff, and self-improvement notes rather than generic prediction.

Maintain and check the Eidos marketplace when plugins must work in both Claude Code and Codex. Use when adding, refactoring, auditing, or debugging marketplace plugins, dual-host packaging, .claude-plugin and .codex-plugin manifests, root marketplace entries, source/store/cache drift, install proof, or host-neutral plugin payloads.

Challenge whether a Zoltar prediction, product idea, plugin, workflow, category framing, or architecture is overfit to existing market patterns. Use when Daniel asks for a Challenger Matrix, anti-consensus review, category redefinition, frontier user needs, non-consensus futures, Doubter voice, or whether an answer is too derivative, market-shaped, competitor-shaped, or copied from current agent/product patterns.

Convert Zoltar foresight findings into separate doer implementation instructions and checker validation instructions. Use when foresight needs to be handed to other agents, when Daniel asks for doer/checker splits, or when a future risk must become concrete acceptance criteria.

Predict the specific future user complaint, regret, or trust failure a change is likely to trigger, grounding each complaint in inspected evidence and converting the top complaint into concrete preventive changes. Use when Daniel asks what he will complain about, what future user objection is likely, or how to prevent a poor future before shipping.

Improve Zoltar by comparing prior foresight predictions against observed outcomes, user complaints, test results, implementation evidence, and checker feedback, then proposing concrete edits to Zoltar's research rules, prediction heuristics, output packet, doer/checker handoff, or plugin skills. Use when Daniel asks Zoltar to self-improve, learn from misses, audit its predictions, make itself better, or update its foresight behavior.

Audit and manage Cloudflare accounts, zones, DNS, SSL/TLS, cache, and Railway custom domains through the Clawdflare CLI and MCP server. Use for Cloudflare inspection, safe DNS dry-runs, authorized record changes, and zone troubleshooting.

Orientation map for the Eidos AGI ecosystem. Use when an agent needs to know where docs, skills, or code live for any Eidos pillar — Core brain, Storemetheus (plugin stores), Helios (browser), Omni (memory), Hancock (auth), Canon (standards), or the skills/contracts/transcoders hubs. The entry point before building anything inside Eidos.

Search, inspect, cache, compare, install, and update agent skills across Skills.sh, Eidos first-party hubs, installed/local Codex skills, trusted libraries, and GitHub. Use when the user wants to find a skill, compare candidates, inspect full skill files, access Eidos ecosystem skills, or install an approved skill for Codex.

Contract for proposing improvements to the Eidos Skills Hub ecosystem. Use when a search returns poor results, a hub is missing, a skill is stale, or the ranking policy should change. Produces a structured proposal that can be reviewed and applied.

Audit, update, and reconcile skills installed for Codex against provenance-tracked cached snapshots. Use when the user asks whether Codex has a skill, whether installed skills are current, to check drift, to review available updates, or to apply approved skill updates safely.

Search multiple agent-skill libraries concurrently across Skills.sh, Eidos first-party hubs, installed and personal Codex skills, trusted GitHub libraries, and GitHub-wide SKILL.md files. Use when the user wants broad discovery, alternatives beyond Skills.sh, parallelized search, explicit provider selection, or confirmation that a suitable skill is already installed locally.

Rank and compare agent-skill candidates with an explicit evidence-backed preference policy. Use when choosing between overlapping skills, explaining why one deserves preference, applying trusted, preferred, or blocked sources, favoring an installed equivalent, or preventing popularity from overriding task fit and provenance.

Use when the user asks to check, monitor, clean up, or keep a Mac healthy with apple-a-day or aad.

Use when a user wants to give an AI agent or Codex explicit software targets, measurable completion criteria, deterministic scoreboards, evidence audits, and repair loops.

Use when the user mentions Kai, @kai, kai CLI, founder ops, company-building workflows, Eidos internal operations, platform provisioning guardrails, Slack operations through Kai, deploy routing, idea capture, or Kai feedback.

Use when the user asks for Lever, leverage analysis, leverage AI, self-learning leverage reviews, agent-building decisions, bottleneck diagnosis, or whether work should become a reusable agent or system.

Use when the user asks about Pavo, Plaud recordings, Plaud CLI, Plaud MCP, real audio files, speaker identification, custom dictionaries, Pavo manifests, Google Drive sync planning, routing, or task creation from recordings.

Use when the user wants to ship, release, publish, deploy, package, list in a marketplace, or learn how a product ships over time.

Use when the user wants Microsoft SkillOpt, self-evolving agent skills, skill optimization from rollouts, validation-gated skill edits, token-cost reduction, thrashing detection, or Tokut/Token Cut remediation.

Use when work must be built, moved, verified, or run through Daniel's machine conduits; when distinguishing mac-mini-01 from rented remote Macs; or when deploying personal infrastructure plugins such as Tally to the right machine.

Delegate scoped coding tasks to AI workers through Foreman. Use when a coding task can be split into independent implementation slices that should run in isolated git worktrees while Codex remains architect and QA.

Use when building, auditing, or planning a private or public company plugin store, Codex marketplace, internal AI operating layer, plugin catalog, store governance model, or client-specific plugin distribution surface.

Use when the user asks for LinearPlus, Linear initiatives through API, Linear GraphQL initiative creation, attaching Linear projects to initiatives, or when the Linear connector cannot create/list initiatives.

Use when the user asks about Felix, agent scaffolding, agent standards, maintainer agents, repo health for an agent, pre-scaffold interviews, have/want/dont-want framing, AGENTS.md wakeup files, plugin setup placement, or whether a new agent should exist. This skill tells Codex to call the installed `felix` CLI first and use `felix-of-felix` only for maintaining public Felix itself.

Use when turning meeting artifacts from any source into grounded decisions, follow-ups, docs, CRM notes, or Linear tasks.

Use when a task involves browsing the web, opening or operating a website, using Browser or Chrome automation, logging in, working with username/password forms, handling account sessions, clicking through web UIs, inspecting pages, taking browser screenshots, or verifying web behavior. Prioritize doing the browser work directly instead of asking the user to do it.

Use when defining, enforcing, or reviewing agent operating standards after code, repo, plugin, workflow, or agent changes need proof gates, verification loops, AGENTS.md contracts, CI checks, or a durable definition of done.

Use when the user wants help shopping, comparing products, finding deals, building carts, choosing gifts, replacing items, checking compatibility, or deciding what to buy.

Use when the user asks about Eidos forges, forge discovery, creating a new forge, checking whether a forge exists, applying a forge pattern, registry.yaml, company-forge, or repo-local forge manifests. This skill tells Codex to use forge-forge's registry, CLI, and MCP tools as the source of truth.

Use Rhea when a task benefits from sovereign model routing, a Socratic debate, persistent Rhea sessions, remote server pairing, or Rhea image generation.

Use when the user asks Codex to discover, choose, install, add, bootstrap, or use Eidos plugins from the Eidos AGI catalog.