ChronoAIProject
OrganizationConnect AI agents to any API, anywhere. Securely. Open-source gateway that proxies requests, injects credentials automatically, punches through NAT to reach localhost services, and wraps REST APIs as MCP tools. Per-agent isolation. Never expose a raw key.
Categories
Indexed Skills (21)
aevatar-codex-exec-node-setup
Configure and prove Aevatar codex_exec for one NyxID account, choosing operator-managed chrono-sandbox/gVisor for bounded empty-workspace work or private NyxID node-backed SSH for a fixed host workspace. Use for managed eligibility and UserService readiness, private node/SSH hardening, mandatory public-sample verification, or diagnosing typed managed and private-route failures.
github-via-nyxid
Operate a user's GitHub account through NyxID's credential-brokering proxy (service slug api-github) — read and write repositories, files, issues, pull requests, commits, branches, Actions, gists and anything else the GitHub REST API exposes, all on the user's behalf and without ever handling a raw token. NyxID injects the user's GitHub credential server-side. Use when an agent needs to read from or act on GitHub for a user who has connected their GitHub account in NyxID.
chrono-ai-service-manual
Unified operational manual for AI agents driving the Chrono AI service stack — NyxID (identity, services, orgs, OAuth clients, proxy) AND Ornn (skill lifecycle — search, pull, install, execute, build, upload, share). One skill, two halves, one identity bootstrap, one set of failure-mode diagnostics. Replaces the legacy `ornn-agent-manual-cli` and `ornn-agent-manual-http` skills. Pair `SKILL.md` with the bundled `references/*.md` files — the per-endpoint catalogues for both APIs, the CLI recipe sheet, the NyxID token model, and the `~/.ornn/installed-skills.json` registry contract.
ornn-agent-manual-cli
The manual an AI agent loads to operate Ornn — the model-agnostic skill-lifecycle API (an npm-style registry + CLI for agent skills) — via the NyxID CLI (`nyxid proxy request ornn-api …`). Load and follow this skill WHENEVER the user asks to do anything with Ornn skills or skillsets. Skills: search Ornn or find a skill, pull or install a skill (or a specific version), run a skill, build and upload a skill, publish a new version, make a skill public / private / shared, run or read a security audit, deprecate or delete a version, diff two versions, check usage analytics, bind a skill to a NyxID service, link a skill to GitHub or sync from source, manage npm-style dist-tags, or transfer skill ownership. Skillsets — curated multi-skill bundles with a required master prompt: bundle skills into a set, create or publish a skillset, resolve its closure in one call, export a skillset as a Claude Code marketplace plugin, transfer skillset ownership, or diagnose why a shared skillset isn't visible (visibility derives fr
ornn-agent-manual-http
Operational manual for AI agents using the Ornn skill-lifecycle API via direct HTTPS with a NyxID bearer token (`curl -H "Authorization: Bearer $TOKEN" …`). Once loaded, the host agent can search / pull / execute / build / upload / share skills end-to-end. Authoritative contract between Ornn and the agent. Pair this file with references/api-reference.md (the full per-endpoint catalogue + error legend) — both ship together as one Ornn skill.
aevatar-feasibility-advisor
Use before building when a user asks whether Aevatar can achieve a goal, what prerequisites it has, or why it is unavailable. Triggers include bots and third-party APIs, inbound channels, external HTTP triggers, schedules, service exposure, Agent Profiles and tool ceilings, and bounded managed or private-host codex_exec work. It distinguishes outbound connectors from inbound channels and separates not connected, host-gated, not deployed, and genuinely unsupported outcomes. It chooses managed_sandbox versus private_ssh without promising repository, model, credential, runtime, or deployment capabilities the caller does not control, then routes feasible work to the owning Aevatar skill.
aevatar-platform-map
Entry point, panorama, and router for the Aevatar skill family. Use before building, running, publishing, scheduling, externally triggering, or operating Aevatar resources; configuring an Agent Profile; assessing managed/private codex_exec feasibility and setup; running the canonical Codex readiness proof; authoring a workflow with codex_exec; diagnosing a Codex failure; or deciding which companion skill owns a request. It teaches resource and identity boundaries, NyxID-brokered auth, client REST versus in-session tools, deployment gates, and exact handoffs without treating member, workflow, service, profile, schedule, or Codex capabilities as one lifecycle.
aevatar-scheduler
Create and manage recurring Aevatar runs and route to the correct scheduling resource. Use for cron, recurring Team member workflows, scheduled skill agents, typed service invocations, pause/resume, run-now, reauthorization, deletion, or credential triage. Team member automation uses its dedicated route and Agent Key; generic schedules accept typed service invocation only. External raw actor/envelope schedules are retired and must fail closed.
aevatar-service-publisher
Publish an Aevatar member, team, or workflow as an invocable service and (host permitting) register it with NyxID, then verify, invoke, or wire external HTTP triggers such as Lark Base automation — all over the REST API. Use when a user wants to "publish/bind a service", "expose my workflow/team as a service", "register it with NyxID", "make it callable", "get the service slug/URL", "invoke my service", "let Lark Base call my workflow", "trigger this workflow from an external webhook", or "version/deploy/roll out a service". It covers the simple scope binding, reading back a member's published service, the full account-level service lifecycle (revision → publish → deploy → rollout), how to confirm the NyxID registration (slug + status), how to invoke an endpoint, and how to distinguish direct NyxID proxy triggering from host-gated externalExposure. Build the team/member first with the team-builder skill.
aevatar-team-builder
Build an Aevatar agent team and its members over the REST API. Use when a user wants to "create a team", "add a member", "make a workflow member / script member / gagent member", "set the team's entry point", or "assemble agents into a team". It creates the team, creates members whose implementation is a workflow (most common), a script, or a hosted gagent, binds each member's concrete implementation (the workflow YAML is attached here), waits for the async binding to succeed, and sets the team entry member. Author the workflow YAML first with the workflow-authoring skill; publish the result as a service with the service-publisher skill.
aevatar-triage
Use after an Aevatar workflow, codex_exec call, schedule, channel, connector, skill, Agent Profile, or control-plane request fails or behaves unexpectedly. It applies when the agent must attribute the first broken boundary across Aevatar, NyxID, Ornn, chrono-sandbox/gVisor, the managed runner, or private SSH; distinguish credential sources and deployment gaps; preserve sanitized evidence; determine defect versus usage; or draft an issue for explicit user confirmation. Never use it to guess a root cause from one error string or auto-file.
aevatar-workflow-authoring
Author, preview, validate, and persist an executable aevatar workflow from a natural-language request. Use it when the user wants to create, build, set up, automate, or feature-probe a multi-step task as a runnable Aevatar workflow. It covers exact NyxID operation and authored-request admission, bounded YAML, file inputs, terminal run verification, feature-equivalent evidence boundaries, and reusable publication. Not for blindly rerunning an existing failed workflow.
fallback-to-calling-agent
Universal try-catch fallback for the aevatar model. Use whenever, after a genuine attempt, you cannot complete the user's request with available server-side capabilities — no matching skill/workflow/connector/tool, a terminal failure, or a task that inherently needs the caller's local environment (files, shell, local context). Instead of failing opaquely or fabricating, return the original request verbatim to the calling agent so it can finish with its own local tools. Generic by design — addresses "the calling agent" with no hardcoded client or skill names.
nyxid
Brokers credentials for downstream services so the agent never sees raw API keys or OAuth tokens. Use when the user explicitly mentions NyxID; asks to broker, store, proxy, connect, or manage credentials or a credential-backed service; manages NyxID inbound triggers, signed webhook delivery/replay, credential nodes, SSH, MCP, or other NyxID resources; or must call a protected downstream API using an available NyxID-managed credential because no suitable authenticated native path is available. Do not use merely because a service is external, for an ordinary public webhook that needs no NyxID trigger contract, for standard Git operations, or for ordinary GitHub work when local `gh` is authenticated. A GitHub username supplied only to select an account is not a trigger. Operate through the `nyxid` CLI or the authenticated NyxID Web API.
aevatar-automation
Aevatar scheduling & workflow automation: scheduled_agent_creator (cron/one-shot) for independent scheduled Ornn skill agents and reminders — NOT an alias for Studio Team member automation — the long-running task automation playbook, workflow creation semantics (Scope Workflow vs Ornn publish), agent_builder lifecycle, the typed required_nyx_services contract (exact user_service_id is the authorization; a slug snapshot never substitutes), dedicated Agent Key semantics (vault-held raw material, borrowed durable reference late-resolved per use, exact non-wildcard grants, ~90-day projected expiry, reauthorize-then-revoke, independent NyxID and Vault revocation tracks), accepted-is-admission-only receipts, and a token_expired triage protocol that reads credentialSourceKind before assuming any TTL.
aevatar-channels-delivery
Aevatar channel & delivery how-to: capability tools (code_execute, nyxid_proxy, GitHub PAT fallback, channel bots), token_expired/401 credential triage that identifies the typed credential source before interpreting the failure (a dedicated scheduled-invocation Agent Key is vault-held and late-resolved per use — never diagnose it with the 300-second broker TTL), LLM route selection slash commands, channel_registrations (staged Lark provisioning), agent_delivery_targets binding, and a strict never-emit-secret-material policy.
aevatar-codex-exec-workflow-sample
Mount and run harmless Aevatar workflows that prove codex_exec works through either the operator-managed chrono-sandbox/gVisor target or a private NyxID node-backed SSH target. Use after managed eligibility and required NyxID UserServices are ready, or after configuring a personal SSH node; also use when diagnosing typed managed or private-route failures before real tasks.
firecrawl-via-nyxid
Teach an aevatar agent to run Firecrawl web-research/agent jobs through NyxID (submit, poll, then read the result).
nyxid-service-skill-authoring
Find or author an agent skill for a NyxID proxy service that has no OpenAPI spec or typed operations. Use when a NyxID service only exposes the generic proxy tool, `nyxid catalog endpoints` returns nothing for the slug, or you would otherwise have to guess endpoint paths. Searches Ornn for an existing skill bound to the service; if none exists, creates one — researching the official OpenAPI spec on the web for public services, or collecting the contract from the user for private/custom services (never fabricate endpoints) — then uploads it to Ornn, binds it to the service, and records it locally.
api-fetch-wrapper
Wrap a public HTTP API (Open-Meteo weather as the demo) with credential handling, error normalisation, and a single retry on transient network failures. Demonstrates the production-shaped baseline for any "skill that calls an external service" — env-based secrets, structured error output, no leaked API keys in logs, and a deliberate retry policy. The Open-Meteo endpoint used here is keyless on purpose so the example runs without setup; replace `OPEN_METEO_URL` with your own host and add `process.env.MY_API_KEY` for an auth'd version.
csv-processor
Read a CSV file from disk, compute per-column min/mean/max for every numeric column, emit the result as JSON. Stdlib-only Python; no pandas, no numpy. Demonstrates the simplest possible "give me a file path, get back structured analysis" skill — a deliberate baseline for any skill that processes tabular data locally without an LLM in the loop.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.