> ## Documentation Index > Fetch the complete documentation index at: https://docs.livepeer.org/llms.txt > Use this file to discover all available pages before exploring further. # AI Features > AI assistants, agent adapters, skills, public AI artifacts, and automated AI-facing pipelines in the docs repo. # AI Features This repo ships two AI products from one codebase. **Outward-facing:** any MCP-compatible client (Claude, Cursor, Copilot, ChatGPT plugins) can query Livepeer documentation as freshness-stamped authoritative source instead of inferring from training data. Public surfaces are the hosted MCP endpoint, `llms.txt`, an AI-enriched sitemap, and the Mintlify chat assistant on the live site. **Inward-facing:** every supported AI coding tool has a thin native adapter rooted in one `AGENTS.md` baseline. 34 canonical AI skills cover session lifecycle (`thread`, `pm`, `research`, `design`, `build`, `iterate`, `close`), content pipelines, repo audits, and governance creation. The same governance gates apply to humans and agents – adapters surface canonical truth for specific consumers but hold no authority of their own (per locked D-DG-11). The third strand – the **automation belt that keeps both honest** – was partially broken until 2026-05-25: `llms.txt` and `sitemap-ai.xml` had drifted 47 days stale, root-caused by the [cron-is-dry-run bug](./automations.mdx#cron-is-dry-run-by-default-bug-fixed-2026-05-25) in the dispatch workflows. Fix shipped 2026-05-25 in commit `e42946cdf` on `docs-v2-dev-draft`; the next scheduled cron after merge to `docs-v2` should regenerate both files. See [Known gaps](#known-gaps). *** ## Public AI surfaces | Surface | Where | What it serves | Status (2026-05-23) | | ----------------------- | ------------------------------------------ | ---------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `llms.txt` | repo root | LLM-readable site index per [llms.txt standard](https://llmstxt.org/) – 371 lines, 35 KB, 188 entries | Production. **47 days stale** (mtime 2026-04-15; `docs.json` last touched today). | | `sitemap-ai.xml` | repo root | AI-enriched sitemap with `ai:section` / `ai:wordCount` / `ai:lastVerified` / `ai:tags` per URL – 181 URLs, 71 KB | Production. **47 days stale**. Covers only 6 of 10 tabs; `developers`/`orchestrators`/`delegators`/`internal`/`ai-tools` entirely absent. | | `robots.txt` | repo root | AI crawler allowlist | Production. **Does not advertise `sitemap-ai.xml`** – only the Mintlify-generated `sitemap.xml`. Per SLICE-12, AI-enriched metadata is not crawler-discoverable. | | Hosted MCP | `docs.livepeer.org/mcp` | Public no-auth Model Context Protocol endpoint, hosted by Mintlify | Production. One tool documented (`search_livepeer_docs`); no live tool-list drift check. | | Mintlify chat assistant | live site widget | Reader-facing chat grounded on published docs | Production. Configured by [`.mintlify/Assistant.md`](https://github.com/livepeer/docs/blob/docs-v2-dev/.mintlify/Assistant.md) (113 lines: mission + source-of-truth order + IA routing map + fallback behaviour + high-risk topic guardrails). | | `skill.md` (root) | advertised at `docs.livepeer.org/skill.md` | AI-readable summary of Livepeer's developer platform for direct agent injection | **Documented in `v2/resources/documentation-guide/ai-automations/ai-features.mdx`; the repo has no `skill.md` at root.** Either Mintlify generates from another input, or the doc is aspirational. Resolve or strike. | | `docs-index.json` | repo root | Structured docs index for AI consumption – 532 entries | Production. `generated` field says 2026-04-07 but mtime is 2026-05-18 – generator failed to update its own provenance field. | **Three AI artefacts publish three different counts:** `llms.txt` = 188 entries, `sitemap-ai.xml` = 181 URLs, `docs-index.json` = 532. Different pipelines, no reconciliation. *** ## Agent adapters (6 + the cross-agent baseline) All adapters point UP into `AGENTS.md` per locked [D-DG-11](../decisions/docs-guide-structure.md). Adapters surface canonical truth for specific consumers but hold no authority. Any rule stated only in an adapter file is invalid and must canonicalise into a T0–T3 source in `docs-guide/`. | Agent | Path(s) | Lines | Thin-adapter compliance | | ------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------: | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **`AGENTS.md`** (root baseline) | `AGENTS.md` | 119 | Reference – every adapter points here. | | Claude Code | `.claude/CLAUDE.md`, `.claude/GOVERNANCE.md`, `.claude/settings.json`, `.claude/skills/` (12 SKILL.md pointers), `.claude/references/` (25 files, \~2,860 lines, 13 categories) | **326** | ⚠️ **2.74× AGENTS.md – material D-DG-11 violation**. CLAUDE.md grew via project-state inserts (e.g. "Repo Features Documentation Audit" row added 2026-05-22). Drift widening. | | Codex | `.codex/README.md`, `.codex/task-contract.yaml`, `.codex/GOVERNANCE.md` + `.github/AGENTS.md` (Codex extension, 153 lines) | 3 + 153 | `task-contract.yaml` `scope_in` covers 20 entries (most of repo) – branch isolation is nominal. `locks-shared/`, `skills/`, `scripts/` subdirs do not exist (assumed by brief). | | Cursor | `.cursor/rules/repo-governance.mdc`, `.cursor/rules/no-deletions.mdc` + `.cursor/GOVERNANCE.md` | 24 + 30 | Reference implementation for thin adapters. | | Windsurf | `.windsurf/rules/repo-governance.md` + `.windsurf/GOVERNANCE.md` | 13 | Reference implementation. | | Augment | `.augment/rules/` (3 files: `repo-governance.md`, `git-safety.md`, `no-deletions.md`) + `.augment/GOVERNANCE.md` | \~120 combined | Plus **phantom-retired duplicate** at `ai-tools/ai-rules/.augment/` (165 lines, 4 files) – at active path; invisible to freshness validator. | | GitHub Copilot | `.github/copilot-instructions.md` | 31 | Thin per D-DG-11. | | Mintlify chat | `.mintlify/Assistant.md` + `.mintlify/GOVERNANCE.md` | 113 | IA routing-map drifts against `docs.json` with no CI alignment check. | | **Retired (active path)** | `.github/augment-instructions.md` (206 lines, archived-header) | 206 | **Heaviest adapter** at active path with archived-header only. Directory-walking agents still read it. Cleanup required. | **Validator:** `operations/scripts/validators/governance/compliance/check-agent-docs-freshness.js` – proves every adapter exists, is non-empty, matches the approved set. **Validator path drift:** [`docs-guide/policies/agent-governance-framework.mdx`](../policies/agent-governance-framework.mdx) lines 137 + 228 reference `operations/scripts/validators/governance/check-agent-docs-freshness.js` (missing `/compliance/` subfolder). `AGENTS.md` line 98 has the correct path. Cleanup required. *** ## AI skills (34 local + 53 portable + 53 templates) The skill catalogue covers session lifecycle, content pipelines, audits, governance creation, and agent packaging. Live counts (2026-05-23): * **34 active local `SKILL.md`** under `ai-tools/ai-skills//SKILL.md` (+ 1 archived in `x-archive/`) * **53 portable skill exports** under `ai-tools/agent-packs/skills/` * **53 templates** under `ai-tools/ai-skills/templates/*.template.md` * **9 entries** in `skill-catalog.json` (26% of 34 skills catalogued) * **1 entry** in `agent-packs/skills/manifest.json` (the `browser` skill) – 52 portable skills exist next to it unregistered * **317 entries** in `ai-tools-registry.json` ### Skills by group (live, 2026-05-23) | Group | Skills (verified present) | | ------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Session lifecycle** | `thread`, `pm`, `research`, `design`, `build`, `iterate`, `dispatch`, `agent-brief`, `diagnose`, `close`, `propagate` | | **Content pipelines** | `page-authoring`, `content-pipeline-pass-a`, `content-pipeline-pass-b`, `content-pipeline-tab-map`, `docs-copy`, `source-content` | | **Audit & review** | `repo-audit-orchestrator`, `docs-coverage-and-route-integrity-audit`, `docs-quality-and-freshness-audit`, `rubric-static-review`, `docs-review-packet-generation`, `docs-review-fix-execution`, `script-footprint-and-usage-audit` | | **Governance creation** | `create-action`, `create-component`, `create-script`, `skill-docs`, `generated-mdx-banners-governance` | | **Component governance** | `component-layout-governance` | | **Style & language** | `style-and-language-homogenizer-en-gb` | | **Cleanup** | `cleanup-quarantine-manager` | | **Packaging & support** | `cross-agent-packager`, `browser`, `product-thinking` | **Maturity:** per SLICE-02, **18 of 34 local skills still carry `status: draft` with empty test logs** – including most of the session lifecycle backbone (`thread`, `research`, `design`, `build`, `iterate`, `close`). The primary scaffold has never been validated in production despite daily use. ### Templates and portable skills * **53 `.template.md` files** at `ai-tools/ai-skills/templates/` – canonical authoring templates. * **53 portable `SKILL.md`** at `ai-tools/agent-packs/skills/` – generated exports for distribution to per-agent packs. * **15 portable wrappers are stale v1.0** pointing to local canonical bodies at v1.3/v1.4 – needs regeneration. * **38 portable-only skills have NO local canonical body** – referenced by dispatchers like `page-ship.mdx` but the dispatcher graph is partly fictional. * **Templates 32/37/38 each appear twice with different content;** 41/42 duplicate the content of 37/38 (renumbered without deleting originals). ### Generators that keep the skill system honest | Generator | What it produces | | --------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------- | | `operations/scripts/generators/governance/catalogs/generate-ai-skills-indexes.js` | Skill indexes; replaces hand-maintained counts | | `operations/scripts/integrators/ai/agents/cross-agent-packager.js` | Per-agent generated packs (codex/claude/cursor/windsurf) from canonical templates | | `operations/scripts/integrators/ai/codex/sync-codex-skills.js` | Lands managed skills in `~/.codex/skills` | | `operations/scripts/validators/governance/ai/validate-ai-tools-registry.js` | Validates `ai-tools-registry.json` schema + lane assignments | | `operations/scripts/validators/governance/ai/check-companion-manifest.js` | Verifies every skill's optional companion bundle (`references/`, `scripts/`, `assets/`) is declared before sync | *** ## AI tools registry `ai-tools/registry/ai-tools-registry.json` is the canonical 344 KB inventory of every `ai-tools/**` artefact. 317 entries. 7-lane model with lifecycle states. | Surface | What it is | | ------------------------------------------------- | -------------------------------------------------------------------------------- | | `ai-tools/registry/ai-tools-registry.json` | Canonical inventory (317 entries) | | `ai-tools/registry/ai-tools-registry.schema.json` | Schema for the registry | | `ai-tools/registry/ai-tools-inventory.md` | Generated inventory report (mtime 2026-04-05 – older than registry; needs regen) | | `ai-tools/registry/dispatchers/*.mdx` | 6 dispatcher pages | | `ai-tools/registry/workflows/*.mdx` | \~50 workflow pages | **Coverage gap:** 9 of 34 skills are in `skill-catalog.json` (26%); the rest are in the registry but absent from the catalogue. Two separate inventory systems (`skill-catalog.json` vs `ai-tools-registry.json`) with no automated cross-check. *** ## ai-rules (`ai-tools/ai-rules/`) Pre-governance rule docs flagged for retirement by the governance framework: | File | State | | -------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------- | | `best-practices.md`, `HUMAN-OVERRIDE-POLICY.md`, `ROLLBACK-GUIDE.md` | Advisory-only | | `_retired/` (8 files) | Retired archive | | `.augment/` (4 files, 165 lines) | **Phantom-retired duplicate subtree at active path** – invisible to freshness validator. Should move to `_retired/` or canonical `.augment/rules/`. | Two `AI_GUIDELINES.md` files give **contradictory `--no-verify` policy** – the `.augment/` shadow forbids it; the live + `_retired` versions allow it with metadata. Reconciliation required. *** ## AI governance contracts Documented in [`docs-guide/policies/agent-governance-framework.mdx`](../policies/agent-governance-framework.mdx) and [`docs-guide/frameworks/ai-tools-governance.mdx`](../frameworks/ai-tools-governance.mdx). | Contract | What it enforces | Validator | | ------------------------- | ------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Agent baseline freshness | All AI adapters reflect the same core repo rules; thin-adapter compliance per D-DG-11 | [`check-agent-docs-freshness.js`](https://github.com/livepeer/docs/blob/docs-v2-dev/operations/scripts/validators/governance/compliance/check-agent-docs-freshness.js) | | Codex task isolation | AI task branches declare scope + avoid overlapping or hidden work | `.codex/task-contract.yaml`, `operations/scripts/validators/ai/codex/validate-locks.js` | | Skill registry parity | Skills and generated agent packs remain synchronised | `ai-tools/registry/`, `generate-ai-skills-indexes.js`, `validate-ai-tools-registry.js` | | Companion manifest parity | Every skill's optional companion bundle is declared before sync | `operations/scripts/validators/governance/ai/check-companion-manifest.js` | | Public AI artefacts | AI-facing root files generated and validated from current nav/content | `lpd ai-sitemap --check`, llms-file validators | *** ## Contributor rules * Do not edit generated AI artefacts (`llms.txt`, `sitemap-ai.xml`, `docs-index.json`, generated skill catalogs, generated agent packs) by hand. Run the named generator. * Do not add a new skill without a `SKILL.md`, registry entry, and validation story. * Do not treat AI-generated reports as source of truth unless their generator and source inputs are named. * Do not bypass branch or deletion rules for AI work. The Codex task-contract scope is checked at preflight. * Native adapters must be thin per D-DG-11. New rules go in `AGENTS.md` or the relevant docs-guide policy – not adapter files. *** ## Known gaps ### `llms.txt` + `sitemap-ai.xml` 47 days stale (P0) – root cause FIXED 2026-05-25 Both root artefacts last regenerated 2026-04-15 vs `docs.json` last touched 2026-05-22. Root cause: the cron-is-dry-run bug in `dispatch-discoverability.yml` + 5 sibling dispatchers. **Fix shipped** in commit `e42946cdf` on `docs-v2-dev-draft` (inverted FLAGS in all 6 scheduled jobs). Pending merge to `docs-v2`, after which the next 04:00 UTC cron should regenerate both files. See [Cron-is-dry-run bug FIXED](./automations.mdx#cron-is-dry-run-by-default-bug-fixed-2026-05-25). ### Veracity pipeline now has dispatchers (was: Phase 6 blocker) Three new dispatchers under `operations/scripts/dispatch/content/veracity/` (May 2026) close the long-standing "veracity-pass DRAFT blocks Phase 6" gap: `docs-research-packet.js` (engine), `orchestrator-guides-research-review.js` (scope wrapper), `docs-page-research-pr-report.js` (advisory PR artefact, experimental, non-blocking). All manual-pipeline; not yet on cron. See [Automations § Recently shipped](./automations.mdx#recently-shipped-may-2026). ### `skill.md` is documented but has no source `v2/resources/documentation-guide/ai-automations/ai-features.mdx` advertises `https://docs.livepeer.org/skill.md` as a published AI artefact. **The repo has no `skill.md` at root.** Either Mintlify generates from another input, or the doc is aspirational. Resolve or strike from the public page. ### `docs-guide/tooling/ai-tools.mdx` skill/template counts are stale The page claims "42 templates" and "42 skills". Live is 53 templates and 34 local skills (53 portable). **Both numbers wrong.** Replace with generator-emitted blocks from `generate-ai-skills-indexes.js` + CI assertion on drift. ### `.claude/CLAUDE.md` violates D-DG-11 thin-adapter rule 326 lines vs `AGENTS.md` 119 lines (2.74×). Most of the bulk is a project-state table that belongs elsewhere. Trim to ≤200 lines; no policy duplicated from `AGENTS.md`. ### 18 of 34 local skills are `status: draft` with empty test logs The entire session-lifecycle backbone (`thread`, `research`, `design`, `build`, `iterate`, `close`) has never been validated in production despite being the primary scaffold for AI-assisted work in this repo. Promote one at a time: pick a draft skill, run 3 production passes, record results, flip to `status: current`. ### Local skills (34) vs portable skills (53) divergence is undocumented `agent-packs/skills/manifest.json` registers ONLY ONE skill (`browser`) while 53 portable SKILLs live next to it. 38 portable-only skills have no local canonical body – referenced by dispatchers but the graph is partly fictional. Reconcile or document why portable-only skills exist. ### Template numbering drift Templates 32/37/38 each appear twice with different content; 41/42 duplicate the content of 37/38 (renumbered without deletion). Cleanup queue. ### `docs-copy/` has both `reference/` and `references/` Two ref directories under `ai-tools/ai-skills/docs-copy/` (singular + plural) containing different files. Never reconciled. Pick one. ### Validator path drift in `agent-governance-framework.mdx` Lines 137 + 228 reference `validators/governance/check-agent-docs-freshness.js`; actual path is `validators/governance/compliance/check-agent-docs-freshness.js`. `AGENTS.md` line 98 has the right path. Cleanup required. ### `.github/augment-instructions.md` at active path with archived-header 206 lines – the heaviest single adapter in the repo. Header says archived; path is active. Directory-walking agents still read it. Either move to `_retired/` or actually delete. ### `ai-tools/ai-rules/.augment/` phantom-retired subtree 165 lines, 4 files, at active path. Should be in `_retired/` per the governance framework. Currently invisible to the freshness validator. ### `ai-tools/registry/ai-tools-inventory.md` lags the registry Inventory mtime 2026-04-05; registry mtime 2026-04-08 (later). Regenerate the inventory. ### `codex/skills-manifest.json` provenance drift Claims `generated_at: 2026-03-22` but file mtime is 2026-04-08. Either manual edit OR generator bug (failed to update its own `generated_at` field, same pattern as `docs-index.json` SLICE-12 finding). ### `robots.txt` doesn't advertise `sitemap-ai.xml` Only Mintlify's auto-generated `sitemap.xml` is listed. AI-enriched metadata in `sitemap-ai.xml` is undiscoverable by crawlers via robots.txt. Add the entry. ### Three AI artefacts publish three different counts `llms.txt` = 188 entries, `sitemap-ai.xml` = 181 URLs, `docs-index.json` = 532. No automated reconciliation check. Either pick one source-of-truth or document why three. ### Mintlify chat assistant has no `docs.json` alignment check `.mintlify/Assistant.md` carries an IA routing map that's hand-maintained against `docs.json`. No validator confirms they agree. Wire one or commit to manual sync on every `docs.json` change. *** ## Related * **[AI Tools Governance Framework](../frameworks/ai-tools-governance.mdx)** – architecture: 7-lane model, lifecycle states, skill/dispatcher/workflow taxonomy * **[Agent Governance Framework](../policies/agent-governance-framework.mdx)** – adapter rules + retired-legacy table + migration map * **[AI Tools Registry](../tooling/ai-tools.mdx)** – registry schema + per-skill detail (currently has stale counts – needs refresh per [Known gaps](#known-gaps)) * **[Automations](./automations.mdx)** – the cron-is-dry-run bug + dispatch architecture that drives AI artefact regeneration * **[Content Writing Pipeline](../frameworks/content-writing.mdx)** + **[Checks Framework](../frameworks/checks-framework.mdx)** – how the content-pipeline skills (pass-a, pass-b, tab-map) operationalise per-page review * **[Ownerless Governance Policy](../policies/ownerless-governance.mdx)** – the 4-part contract for governed surfaces (4 of 5 unified surfaces formally ownerless-ready post-D-ACT-10; legacy 8-entry file superseded) * **`AGENTS.md`** (root) – cross-agent baseline (119 lines); every adapter points here * **`.mintlify/Assistant.md`** – the Mintlify chat assistant configuration * **`ai-tools/registry/ai-tools-registry.json`** – canonical 317-entry inventory * **`workspace/thread-outputs/repo-consolidation-deep/SLICE-02-ai-tools.md`** – full 324-file ai-tools/ inventory with maturity per skill * **`workspace/thread-outputs/repo-consolidation-deep/SLICE-06-agent-adapters.md`** – full 49-file adapter inventory with thin-adapter compliance per adapter