Independently verify one Gaia Steward Class B build: read only the rendered verifier prompt and the sensor evidence, check the diff and proof, and record accept, reject or escalate. Use when a full Steward run emits an agent.verify action, for "/gaia-steward-full --verify", or "verify the steward dispatch". The verifier must be a different agent from the builder.
中文简介正在准备中。当前显示原文说明。
Produce the Gaia Steward coverage retrospective: the 17-routine table of registered detectors, what each actually observed in the latest receipt, the remaining gaps, and the no-op versus closure record. Use for "/gaia-steward-full --retro", "steward coverage report", "which routines are covered", or "how is steward doing".
中文简介正在准备中。当前显示原文说明。
Observe the repository with every registered Gaia Steward detector and report what each one actually saw, without changing anything. Use for "/gaia-steward-full --observe", "what is Steward seeing", "scan the repo for maintenance debt", or as the first phase of a full Steward run. Distinguishes actively observed, unknown/unavailable and not-evaluated detectors; never treats an unexecuted probe as healthy.
中文简介正在准备中。当前显示原文说明。
Sort open Gaia Steward debt into Class A (deterministic repair), Class B (bounded dispatch) and Class C (founder decision) with priorities, optionally narrowed to one routine or one debt id, without acting on any of it. Use for "/gaia-steward-full --triage", "--routine N", "--debt ID", "what should Steward do next", or "triage the maintenance debt".
中文简介正在准备中。当前显示原文说明。
Land a Gaia Steward Class A repair (agent-skill mirror or bundled-schema mirror) as a deterministic commit on a steward/a/* branch, open a draft PR to the integration branch, and record the outcome. Use when a full Steward run emits a forge.open_pr action, for "land the class A repair", or "open the steward PR". Never targets main and never merges.
中文简介正在准备中。当前显示原文说明。
Run Gaia Steward end to end: observe every routine's detectors, triage debt by authority, land Class A repairs on the integration branch, drive one bounded Class B dispatch through an independent verifier, re-observe, and leave a quiet founder desk or a precise list of decisions. Use for "/gaia-steward-full", "run the steward", "full maintenance pass", "what does the repo need", "resume the steward run", or a scheduled maintenance wake. Thin entrypoint: each phase is an atomic gaia-steward-* skill.
中文简介正在准备中。当前显示原文说明。
Render the Gaia Steward founder desk: the Class C decisions that need the founder, each with decision, why it matters, evidence, recommendation, alternative, what it unblocks and a link, plus operational failures shown separately. Use for "/gaia-steward-full --status", "what needs my decision", "founder desk", or at the end of every full Steward run.
中文简介正在准备中。当前显示原文说明。
Procedure for controlled, human-gated outbound README badge provisioning PRs (Issue #1817). Preflights upstream repositories, ensures single-badge placement with deep links, and records campaign outcomes without automated retries or multi-badge noise.
中文简介正在准备中。当前显示原文说明。
Broad, pre-curation evidence reconnaissance for a declared Gaia skill, intake batch, upstream repository, or proposed generic capability. Run before choosing a discovery strategy or mapping topology, to give the curator independent research leads and counterevidence. Context only: never scores, grades, ratifies, ingests, or mutates the registry. Later ev-discovery and ev-pipeline phases validate/promote any selected leads.
中文简介正在准备中。当前显示原文说明。
Publish a new post (announcement, link, or LaTeX-style meta report) to the Gaia site. Use when you want to add any update to the registry's public feed and landing page.
中文简介正在准备中。当前显示原文说明。
Toggle the badges-page Honesty Mode build-time flag on or off. ON makes the README badge generator emit direct /badges/_assets/<handle>/<file>.svg URLs (no Cloudflare Worker, no ?repo= validation). OFF restores worker-validated URLs. Use when the user says "/honesty-mode on", "/honesty-mode off", "turn honesty mode on/off", or asks for the current honesty-mode state.
中文简介正在准备中。当前显示原文说明。
Use this skill when the user wants to turn code graph analysis into tracked GitHub issues — "audit the architecture", "find god nodes", "triage architectural debt", "run graphify and log issues", "what's over-coupled in this codebase", "create issues from graphify findings", "check for structural problems", "scan for architectural smells", or any request that combines codebase topology analysis with issue tracking. This skill runs graphify to build a dependency graph, parses GRAPH_REPORT.md for god nodes and structural patterns, converts findings into GitHub issue payloads, and optionally pushes them to the repo. It bridges static analysis and project management in a single automated pass. Requires graphify and gh CLI.
中文简介正在准备中。当前显示原文说明。
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
A relentless interview to sharpen a plan or design.
中文简介正在准备中。当前显示原文说明。
Push committed changes and create a draft PR on GitHub. Use when you have staged changes ready to push and want to open a draft PR for early feedback or documentation.
中文简介正在准备中。当前显示原文说明。
Generate interactive, animated, responsive HTML-based terminal simulators to showcase CLI commands, scripts, pipelines, or interactive workflows. Use this whenever you need to visually showcase a command line sequence, mock interactive CLI tools, or simulate code executions.
中文简介正在准备中。当前显示原文说明。
Calculate and display the token usage, turns, and estimated cost for the active session and subagent runs by parsing the harness session logs. Use when the user asks for token usage, session cost, or types `/pi-cost`.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
Append a session/state snapshot to MEMORY.md (regardless of where it lives — for this repo it's `founder/MEMORY.md`). Use when the user says "snapshot memory", "save state to memory", "/memory-snapshot", "log what happened in MEMORY", or otherwise asks to record the current session's outcomes for the next orchestrator. Locates the project's MEMORY.md, prepends a dated entry above the previous snapshot (newest first), preserves every existing entry (NEVER overwrites or truncates), and reports back the file path + byte delta. Not for one-off feedback memories (use the user-level memory system at ~/.claude/.../memory/ for those). Not for trimming or deleting old entries.
中文简介正在准备中。当前显示原文说明。
Run bounded, read-only semantic advisory sidecar passes for candidate mapping, issue triage, upstream diffs, evidence verification triage, and meta audit hints. Enforces monthly spend limits with explicit fallback to worker-luna.
中文简介正在准备中。当前显示原文说明。
This repo is indexed by graft/. For ANY task here, whether understanding how something works, finding where code lives, tracing what calls a symbol or what a change breaks, or scoping an edit, get your context from graft before grepping or reading source files.
中文简介正在准备中。当前显示原文说明。
Manually trigger artifact regeneration, versioning, and chore commit. Use when you need fine-grained control over when registry artifacts sync (outside the automated sync-artifacts.yml workflow).
中文简介正在准备中。当前显示原文说明。
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
中文简介正在准备中。当前显示原文说明。