gaia-research
OrganizationMulti-harness token-usage cost reporter for AI agent sessions (pi, Claude Code, Codex, opencode). Reads JSONL logs, prices from LiteLLM catalog, auto-refresh built-in. One file, zero deps.
Categories
Indexed Skills (18)
cost
Report token usage and USD cost for AI agent sessions by parsing logs from pi, Claude Code, OpenAI Codex, opencode, and Hermes Agent. Prices are auto-refreshed weekly from the LiteLLM catalog. Use when the user asks about cost, spend, token usage, "how much did this session cost", or invokes /cost.
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
wayfinder
Chart a too-big effort as a shared map of decision tickets on the Gaia headquarters issue tracker, then resolve them one at a time until the way to the destination is clear. Use when someone says: "this is too big for one session", "chart a map", "wayfinder map", "plan this effort", "what do we need to decide first", "open a wayfinder", "work the map", "what's on the frontier", or /wayfinder. Covers any gaia-research org repo — gaia-skill-tree, gaia-research, gaia-skill-heaven and beyond — but every map and every ticket lives on ONE tracker: gaia-research/gaia-skill-tree. This is cartography (planning an effort as decisions), NOT triage of an existing backlog — for that use /gaia-triage.
summon
Explicitly summon the best-matching skill for a concrete capability gap into this session without installing it.
lucy-image-production
One-shot Lucy asset generation and deterministic export for Skill Heaven.
skill-heaven
Arm the human-led converge band at low or med. User-invoked orchestrator for explicit Skill Heaven routing.
skill-hell
Arm the model-led explore band at high, xhigh, or max. User-invoked orchestrator for automatic Skill Hell routing.
skill-ultra
Arm the ultra crown rung, choosing human-led convergence or model-led exploration and depth per capability gap.
skill-zero
Arm the zero rung: cut temporary automatic skills while manual summon remains available, or cut all skills.
gaia-issue-resolver
End-to-end plan → implement → review pipeline that takes one triaged Gaia issue to a merged-ready PR, with Kill Criteria on the issue and zero follow-up debt. Use when someone says: "resolve this issue", "take #N end-to-end", "work the P0 queue", "fix and ship this issue", "run the resolver", "close out this issue properly", or /gaia-issue-resolver. Works any gaia-research org repo — gaia-skill-tree, gaia-research, gaia-skill-heaven — while the issue itself lives on the headquarters tracker, gaia-research/gaia-skill-tree. Assumes the issue is already triaged and carries a P0–P4 label; if it does not, run /gaia-triage first.
gaia-triage
Triage the Gaia issue backlog and skill-batch intake queue. Use this skill when someone asks to: "triage issues", "clean up the issue tracker", "review the backlog", "close stale issues", "process the intake queue", "review skill-batches", "evaluate draft skill proposals", "approve or reject pending skills", "is this issue still valid?", "what's clogging the backlog?", "run a triage pass", or /gaia-triage. Covers two workstreams: (1) GitHub issue lifecycle — identifying resolved, stale, or need-more-info issues and acting on them via gh CLI; (2) skill-batch intake — evaluating draft proposals in registry-for-review/skill-batches/ and routing them toward promotion or rejection. This is the gatekeeping step before new skills enter the canonical registry; and (3) a cross-repo triage sweep — sizing, P0-P4 prioritization, umbrella/epic synthesis, and assignment across every gaia-research org repo, on the one headquarters tracker.
lucy-tuner
Launch, inspect, and use the interactive Lucy position and zoom tuner HUD in Skill Heaven Hero A.
codex-playbook
Drive the Codex CLI as a benchmark target or dispatched worker. Use when running codex probes, comparing codex postures, building codex-zero, or handing work to a codex agent. Covers non-interactive exec, sandbox and config isolation, model and reasoning-effort selection, and the per-session skills toggle.
cost-measurement
Measure token usage and USD cost for any Skill Heaven benchmark arm, dispatched worker, or session. Use whenever reporting spend, comparing the cost of two postures, or logging session token spend. Wraps gaia-research/skill-cost, the canonical cost basis for the whole ecosystem.
harness-door-pattern
Build a Skill Heaven door for a new AI coding harness. Use when adding support for any harness (claude, pi, codex, hermes, grok, or a new one) — covers the four suppression-mechanism classes, how to probe without being lied to, the door package shape, and the traps that have already cost time.
herdr-benchmark-pane
Run Skill Heaven benchmark probes and side-by-side posture comparisons in visible Herdr panes. Use whenever comparing postures (floor, product-floor, curated, native), doors (claude-zero, pi-zero, codex-zero), or harnesses, and the operator must be able to watch every arm run.
herdr-dispatch
Dispatch coding workers into visible Herdr panes instead of hidden in-harness subagents. Use whenever you need to hand work to another agent (Claude, pi, codex, hermes, grok) and the operator must be able to watch it happen. Covers pane layout, agent start, prompting, waiting, reading results, and teardown.
pi-playbook
Drive the pi CLI as a benchmark target or dispatched worker. Use when running pi probes, comparing pi postures, launching pi-zero, or handing work to a pi agent. Covers the flag surface that maps onto Skill Heaven mechanisms, model selection, and non-interactive invocation.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.