Communitygithub.com

ChronoAIProject/nyx-skills

Verify-first promotion intelligence for ANY repo or org. Pulls live GitHub state, runs sshx multi-perspective consensus over it, and returns an evidence-backed board of what is genuinely promotable, how items connect, and what is unverifiable. Use when an agent or operator asks "what's worth promoting / what connects / what's real" for a target repo or org.

What is nyx-skills?

nyx-skills is a Codex agent skill that verify-first promotion intelligence for ANY repo or org. Pulls live GitHub state, runs sshx multi-perspective consensus over it, and returns an evidence-backed board of what is genuinely promotable, how items connect, and what is unverifiable. Use when an agent or operator asks "what's worth promoting / what connects / what's real" for a target repo or org.

Works with~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/ChronoAIProject/nyx-skills/tree/HEAD/promo-scout

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

promo-scout

Generic, verify-first promotion intelligence. It is the opposite of a hype scraper: nothing reaches the board unless live GitHub state backs it, and the judgment is made by sshx consensus (isolated perspectives + truth table), not by one model's say-so.

Requires: gh authenticated with your existing GitHub auth, either via gh auth login or GH_TOKEN, and the sshx skill available to the caller.

When to use

An agent or operator wants, for a target repo/org: what is genuinely promotable right now, how the pieces connect across repos, and what tempting claims are NOT verifiable.

Step 0 — confirm explicit scope WITH THE USER

There is no broad account-wide default. Require the user to name:

  • a whole org (public repos only by default),
  • one or more specific repos (owner/repo), or
  • a mixed list. Also confirm REPO_LIMIT for org targets (default 12 most-recently-active public repos). Private repo collection requires explicit opt-in with --include-private; do not use that flag unless the user has confirmed it.

Step 1 — fetch live state (deterministic; runs from anywhere)

Run the bundled fetcher with an explicit target:

python3 scripts/promo_scout_fetch.py <org | owner/repo> [more...]   # public/default scope
python3 scripts/promo_scout_fetch.py --include-private <org | owner/repo> [more...]   # only after explicit confirmation

It writes /tmp/promo_scout_bundle.json: per-repo README head, recent commits, releases, open PRs, recent issues. This is the ONLY evidence the consensus step may use.

Step 2 — run real sshx consensus over the bundle

Invoke the sshx skill (worker-delegated, isolated perspectives, codex-cli workers) with this decision, feeding the bundle as the fixed input:

Given ONLY this live GitHub state bundle, produce three lists. (1) Promotable: items genuinely worth promoting now — each MUST cite concrete bundle evidence (a release tag, a dated commit, a README capability). (2) Connections: cross-repo links where one repo's work composes with another's, each backed by a real signal in the bundle (shared PRs, dependency mentions, complementary capability). (3) Dropped: tempting claims that the bundle does NOT support, with the missing evidence. No overclaim; if evidence is absent, it goes to Dropped, not Promotable.

Use distinct sshx thinking-perspectives, e.g.: a promotability lens, a cross-repo connection lens, and a skeptic / overclaim-hunter lens. Require convergence per the sshx truth table; honor abstain when workers can't establish a claim.

Step 3 — emit the board

Write the agreed result as a board (markdown + optional JSON): ## Promotable now, ## Connections, ## Dropped (unverifiable). Each promotable/connection item carries its bundle evidence inline. The Dropped list is mandatory — it is the credibility of the board.

Guardrails

  • Evidence or it doesn't ship. Live bundle is the only source; no outside memory, no inflated numbers.
  • The connections/synthesis must EMERGE from the consensus over live state — do not inject a pre-written narrative.
  • Honest by construction: unverifiable → Dropped; when consensus can't be reached, report abstain, not a guess.

Individual skills in this repo

This repo contains 9 individual skills — each has its own dedicated page.

ChronoAIProject/aevatar-attachment-probe

Boundary test for inbound Lark attachments — the user sends an image or file alongside this command and the bot reports exactly what it can observe on the chat path (text only, attachment refs, or nothing), without guessing. Detects when the platform wires chat-path attachment visibility so dependent skills can be upgraded.

ChronoAIProject/aevatar-vision-probe

Verify the read-image (vision) path end to end — the user sends an image plus the trigger, a workflow vision step describes it, and the run output proves the model actually saw the image (a real description, not "no image received"). Run it before any image-dependent workflow (petty-cash receipt, invoice OCR).

ChronoAIProject/codex-formal-answer

Use when answering mathematical, conceptual, philosophical, or metaphysical questions through repository-first scientific reasoning, a clause-complete formal bridge, retained exact Lean specializations, reusable library growth, and an ordinary conversational answer; the formal work stays internal and is shown only when the user asks for it.

ChronoAIProject/lark-im-ops

Send, reply to, react to, read, and find Lark messages and chats through the bot's NyxID-brokered im/v1 APIs — proactively post to a chat or DM, thread-reply, add or remove emoji reactions, read a single message or pull a chat's history over a time window, search or list the chats the bot is in, and download an image/file from a message. Handles the "content must be a JSON string" footgun and receive_id_type selection, and doubles as the im-scope probe — on a scope 403 it reports the exact missing permission instead of failing silently.

ChronoAIProject/nyx-skills

Method for producing short vertical videos from ChatGPT image generation through a fixed browser tab, local TTS narration, timed subtitle burn-in, cover exports, and a manifest. Use when an operator needs a reproducible image-to-short workflow with pinned session consistency, per-beat visual prompts, 1080x1920 safe-area rules, local ffmpeg/PIL assembly, and private access kept outside the skill.

ChronoAIProject/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

ChronoAIProject/petty-cash-approval-payload-builder

Runs the petty-cash approval flow end to end yourself — collect Lark DM/sheet/image context, extract receipt details, build the exact approval body, then SUBMIT the Lark approval instance.

ChronoAIProject/public-copy-release-guard

Portable checklist for gating public-facing copy before release. Use when captions, posts, manifests, topics, titles, or launch copy must be checked for generic AI wording, leaked internal labels, forbidden experiment or tool names, platform topic allowlists, CTA spam, and unsupported overclaims.

ChronoAIProject/research-claim-fidelity-reviewer

Severity-weighted BLOCK, WARN, OK reviewer method for technical and research posts. Use when reviewing X threads, announcements, captions, or launch copy for hook strength, thread arc, generic AI vocabulary, source fidelity, claim support, numeric-claim verification, and thread format before recommending publish.

Related Skills