sshlg-skills 1.76.0 → 1.76.2

package/CHANGELOG.md

@@ -1,3 +1,26 @@
+## v1.76.2 (2026-10-24): seo-aeo-audit pinned to 0.32.0
+
+- **seo-aeo-audit 0.32.0** (was 0.31.3), commit `51dba19`: `references/playbooks.md`, ten
+  procedures run on a live property (an indexing push with a held-out control, IndexNow on every
+  verified release, Baidu for Chinese pages, Request indexing, a full showcase over a dynamic
+  catalog, problem-intent pages, an unmeasured-claims sweep, localizing for a non-Google engine,
+  grammatical case in templates, a network of satellite sites), each with when to use it, the
+  steps, how to verify the result, what to measure next and the traps a run hit. `skills.json` and
+  `claude-plugin-pins.json` regenerated by `scripts/sync-member-pins.js --write` and
+  `scripts/sync-claude-pins.js --write` from the staged gitlink; README table updated; the
+  ctx-04.06 acceptance receipt re-emitted because the pins moved under it.
+
+## v1.76.1 (2026-10-23): two issues closed in the members
+
+- **Pins:** agent-stack 0.31.2 (0.31.0 closed issue agent-stack#56: `agent-evals/references/support-quality.md`,
+  a product-neutral support quality standard for agents that answer people, routed from
+  `agent-evals` and `agent-orchestrator`); seo-aeo-audit 0.31.3 (0.31.1 closed issue seo-aeo-audit#56:
+  `url_inspection.py` re-mints its ADC token before 50 minutes and once on HTTP 401, so a long
+  run no longer answers 401 after an hour). Both patches carry `test/family_gate.py` with
+  `# shared-mechanism: family-gate` and `# diverges: none`, the two lines this repository's
+  cross-repository check requires of every copy; the canonical `member-gate/family_gate.py` carries it too, and all
+  eleven members' copies were refreshed.
+
 ## v1.76.0 (2026-10-23): M3 waves 2 and 3, the operator's decisions and one member gate
 
 - **Pin:** task-pipeline 1.101.1 (B-153: the release gate's python3-failure fallback reads

package/README.md

@@ -51,9 +51,9 @@ scripts. No services, no telemetry, no API keys.
 | **[agent-sync](https://github.com/ssheleg/agent-sync)** | 1.23.0 | Several agents, one repository, no collisions. Leases with a TTL so two agents cannot claim the same work, race-free id reservation, a run journal and a generated board — over a pluggable knowledge cloud. The answer to "two sessions just committed over each other". |
 | **[make-skill](https://github.com/ssheleg/make-skill)** | 0.33.0 | A skill that builds skills. Create, retrofit, audit and publish agent skills and Claude Code plugins: conformance to the [Agent Skills](https://agentskills.io/specification) open standard, [Anthropic's platform rules](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) (per-surface runtime limits, the Skills API, evals) and the [Claude Code plugin reference](https://code.claude.com/docs/en/plugins-reference), marketplace layout, version sync, validator + CI, every distribution channel, the review checklist for third-party skills, and what a *skill author* must know about MCP and A2A — the protocols themselves live in `agent-stack`. |
 | **[sheleg-design](https://github.com/ssheleg/sheleg-design-skill)** | 1.66.2 | The taste layer. Cinematic scroll-driven landing pages — one scroll clock, motion that degrades to calm, WebGL particle formations — plus product-UI style packs each shipping a ready token layer, and the Figma border: tokens as variables, design to code without hand-copied values. |
-| **[seo-aeo-audit](https://github.com/ssheleg/seo-aeo-audit)** | 0.31.0 | Evidence-first website audit for search **and** answer engines. Ten tracks from crawl access to AI citation mechanics; every finding carries an observation, every recommendation an evidence tier, and the output is a prioritized change plan plus a link-building brief, not a score. Before a site is built, `/seo-aeo-audit brief` writes the build-time brief that the audit later verifies. |
+| **[seo-aeo-audit](https://github.com/ssheleg/seo-aeo-audit)** | 0.32.0 | Evidence-first website audit for search **and** answer engines. Ten tracks from crawl access to AI citation mechanics; every finding carries an observation, every recommendation an evidence tier, and the output is a prioritized change plan plus a link-building brief, not a score. Before a site is built, `/seo-aeo-audit brief` writes the build-time brief that the audit later verifies. |
 | **[sheleg-dev](https://github.com/ssheleg/sheleg-dev)** | 0.16.0 | The integration layer a product reaches once it has users: **money in, tracking, sign-in, speed**. Stripe subscription billing reconciled into your own database — webhook idempotency, renewals, seats and proration, refunds, price drift, and the coupon offered at the cancel step, where a `duration=once` discount leaves `subscription.discounts` the moment its invoice finalizes and the offer can be taken every cycle; crypto payments that survive under-payment, duplicate webhooks and rate drift; GA4, Google Ads, Meta and LinkedIn under Consent Mode v2; Google sign-in with the account pre-hijacking guard, and the server-side auth surface behind it; Core Web Vitals work that moves the score rather than the report; and Sentry error tracking wired so it does not forward your own credentials to a third party and so a stack trace names the commit that caused it. |
-| **[agent-stack](https://github.com/ssheleg/agent-stack)** | 0.30.2 | Production patterns for agent systems, in four skills. **The orchestrator** — tool-calling loops that survive their own context pressure, pipelines with human checkpoints and resume, provider routing with fallback and health checks, memory architecture — form, function and dynamics, the four-stage retrieval pipeline, and what a layer table alone cannot say, and **the shape of the work decided before the work**: an edge that carries no data is no edge, a plan that declares its dependencies is executed in layers rather than in list order, and a parallel layer gets a checker before the node that consumes it. **The harness** — what the agent is *told*: system prompts at the right altitude, tool descriptions the model can act on, technique choice with a verdict each, workflow versus agent and static versus dynamic, plus a seven-track audit of an agent somebody else built and a scanner for the defects that are mechanically visible. **The evals** — suites that measure whether it actually works: judging trajectories, regression fixtures grown from production, judges calibrated before they are trusted. **The interop layer** — MCP at revision 2026-07-28 and the four features it deprecated, running many servers at once, the registry, A2A 1.0, and the gateway, every reference carrying the spec revision it was read against. Plus the wallet side of reselling LLM access: tiered balances, one markup boundary, two-phase commit against a provider API. |
+| **[agent-stack](https://github.com/ssheleg/agent-stack)** | 0.31.2 | Production patterns for agent systems, in four skills. **The orchestrator** — tool-calling loops that survive their own context pressure, pipelines with human checkpoints and resume, provider routing with fallback and health checks, memory architecture — form, function and dynamics, the four-stage retrieval pipeline, and what a layer table alone cannot say, and **the shape of the work decided before the work**: an edge that carries no data is no edge, a plan that declares its dependencies is executed in layers rather than in list order, and a parallel layer gets a checker before the node that consumes it. **The harness** — what the agent is *told*: system prompts at the right altitude, tool descriptions the model can act on, technique choice with a verdict each, workflow versus agent and static versus dynamic, plus a seven-track audit of an agent somebody else built and a scanner for the defects that are mechanically visible. **The evals** — suites that measure whether it actually works: judging trajectories, regression fixtures grown from production, judges calibrated before they are trusted. **The interop layer** — MCP at revision 2026-07-28 and the four features it deprecated, running many servers at once, the registry, A2A 1.0, and the gateway, every reference carrying the spec revision it was read against. Plus the wallet side of reselling LLM access: tiered balances, one markup boundary, two-phase commit against a provider API. |
 | **[telegram-dev](https://github.com/ssheleg/telegram-dev)** | 0.4.0 | Telegram, split by the API each surface actually speaks. **`telegram-bots`** — the official HTTP Bot API: `update_id` as the only idempotency key an update carries, the `allowed_updates` default that subscribes you to everything *except* `chat_member` and the two reaction types while answering `ok: true`, the webhook secret header that is the real check, rate limits as a design constraint (1/sec per chat, 20/min per group, ~30/sec bulk), and Telegram Stars with a **ten-second** pre-checkout window and a grant that belongs to `successful_payment`. **`telegram-userbots`** — MTProto and Telethon: the session file as a credential equal to the password, `FloodWaitError` as the API telling you exactly how long to wait, pinning across minor releases that move session and entity-cache behaviour, and the account-ban risk a bot token does not carry — the skill opens with whether a user account is needed at all. **`telegram-miniapps`** — the web layer, whose entire security model is one signed query string: verifying `initData` server-side, the `auth_date` window, the Ed25519 path for a third party, and the SDK package whose name moved while the organisation's own page still fronts the old one. Both the verifier and the delivery invariants ship as runnable fixtures with their mutants. |
 | **[xr-dev](https://github.com/ssheleg/xr-dev)** | 0.4.2 | **`quest-lifecycle`** maps the product from platform choice through design, build, testing, Store, monetization, launch and operation. The existing owners cover native OpenXR, Kotlin Spatial/hybrid apps, measured rendering optimization, current-source/tool discovery, commercial and asset readiness, and WebXR/PWA. Every stage names evidence and a next action; Meta engine companions and official Godot XR documentation supply implementation detail. |
 | **[web3d-dev](https://github.com/ssheleg/web3d-dev)** | 0.2.2 | Realtime 3D on the web with three.js and React Three Fiber, split by the question. **`web3d-runtime`** — how the scene runs: WebGPURenderer and its WebGL2 fallback, TSL and compute, post-processing, device loss and profiling, led by the failures r186 keeps silent: `render()` before `init()` throws, `positionNode` collapses every instance to a point, `computeAsync` does not wait for the GPU, and about twenty drei components do not run on WebGPU. **`web3d-assets`** — the glTF pipeline from a source to the frame within a written budget: gltf-transform and gltfpack, KTX2 and meshopt, the loader that reads the result, sourcing and the four licence questions; it delegates orders to the asset service when the machine runs one and works by the same principles when not. **`web3d-animation`** — a two-sided animation protocol with a shared clip canon: rig, clips, blending, retargeting, root motion, crowds and vertex-animation textures. Every fact is pinned to three@0.186.1, and the gate checks each code block against that release's exports. |

package/claude-plugin-pins.json

@@ -2682,8 +2682,8 @@
     {
       "name": "seo-aeo-audit",
       "repo": "ssheleg/seo-aeo-audit",
-      "commit": "1cbb3610b484dfc700086c8470377944c0e405da",
-      "version": "0.31.0",
+      "commit": "51dba1913c967e606b773786f091302771d242ed",
+      "version": "0.32.0",
       "pluginInstall": "seo-aeo-audit@seo-aeo-audit",
       "pluginPath": "plugins/seo-aeo-audit",
       "entry": {
@@ -2691,7 +2691,7 @@
         "displayName": "SEO + AEO Audit",
         "source": "./plugins/seo-aeo-audit",
         "description": "Audits a website across ten evidence-based tracks (access & indexation, canonicalization, architecture & link equity, intent, content value, extractability/AEO, entity consensus, experience signals, risk, measurement) and outputs a findings report plus a prioritized change plan with verification steps. Includes a stdlib-only page auditor with answer-engine read-budget analysis.",
-        "version": "0.31.0",
+        "version": "0.32.0",
         "author": {
           "name": "ssheleg",
           "url": "https://x.com/sshlg93"
@@ -2716,7 +2716,7 @@
       "files": [
         {
           "path": ".claude-plugin/plugin.json",
-          "sha256": "45c983161bfb449a821f3fe0f4d600f137e843abb3bb41a00973a94c9ca4906e",
+          "sha256": "54524e31122d383215eeac1c800d636b7e0f23a9394430774cb55b0e1be3a045",
           "bytes": 766
         },
         {
@@ -2726,8 +2726,8 @@
         },
         {
           "path": "skills/seo-aeo-audit/REFERENCE_INDEX.md",
-          "sha256": "eebda02b35ac9e6e2a44a3b5b4d6fa3b9c33ed3623cb47e7d9dfabe02f438f3d",
-          "bytes": 1991
+          "sha256": "9c4686a64d623f7ee72e63dbdaf41608eacbec858334b13332a0119662ae0af1",
+          "bytes": 2122
         },
         {
           "path": "skills/seo-aeo-audit/references/aeo-geo.md",
@@ -2824,6 +2824,11 @@
           "sha256": "f3dc1ec6f9f2b5245c809a203b658d4ad730c390fc8ba988107f5540b91c8e52",
           "bytes": 14766
         },
+        {
+          "path": "skills/seo-aeo-audit/references/playbooks.md",
+          "sha256": "d2ff12f4ddc127b9829934e9dcfae05bad85fe981b2a911e5251d3a2c26591eb",
+          "bytes": 20903
+        },
         {
           "path": "skills/seo-aeo-audit/references/preflight.md",
           "sha256": "8c7366d11bada4908b6469ee4516bd5d8665475dd4fa7fafb375869fc379d284",
@@ -2841,8 +2846,8 @@
         },
         {
           "path": "skills/seo-aeo-audit/references/scripts.md",
-          "sha256": "4eb2ec3b55276ed4e6bdc20b6e4d683db04e0c5a8266ddceccbe5789b9499de0",
-          "bytes": 26137
+          "sha256": "cb26823aeb51f7cc8660dae71474dc59fd50ded161f106b350dfd427a1df0d76",
+          "bytes": 26377
         },
         {
           "path": "skills/seo-aeo-audit/references/technical-checks.md",
@@ -2856,53 +2861,53 @@
         },
         {
           "path": "skills/seo-aeo-audit/references/tooling.md",
-          "sha256": "692d232dcdc6a52f4c8d40785b2a320387df48f4630ffd3b246345f1caaa4677",
-          "bytes": 41865
+          "sha256": "3ba76e042093159e289cbb47a4e542861aa5df5e2dd93a51f047c5f2df82dcd2",
+          "bytes": 42026
         },
         {
           "path": "skills/seo-aeo-audit/scripts/agent_surface.py",
-          "sha256": "bc5d2d01a482d84a0630ec842ca418698f1c32912f89f6a7cb556d16666fb1ef",
+          "sha256": "874833e978d6ccc58e6d1f16a3bd98b72e6fec814e0deef67c2edd7be17dcb9f",
           "bytes": 97372
         },
         {
           "path": "skills/seo-aeo-audit/scripts/ai_panel.py",
-          "sha256": "2c7231e84d8528c04e2b6431d3585e9c44c9a28b8ddc7d663f6000500830d7c2",
+          "sha256": "dfe0ff50123836d758fb1d5f74b795d46c3f28f6121eee5a20b117565e8e2f3b",
           "bytes": 25268
         },
         {
           "path": "skills/seo-aeo-audit/scripts/bwt_pull.py",
-          "sha256": "b8dece8c1755ab0f0a2e71080a87ebd90f241ce60ba7e5b9affac612d0b8c562",
+          "sha256": "b9dca38dd80acdfe71e740f0d26f7deb33cc6a4b9cfe778bc6e9bb694748559c",
           "bytes": 25409
         },
         {
           "path": "skills/seo-aeo-audit/scripts/gsc_pull.py",
-          "sha256": "bcf4c84b57cee199fe72950bd7f05e0a02132d9bd6fcc00feed1af5e6f49dabe",
+          "sha256": "3298592db0e593514a28aa31d0e512ab5b6f0b8fcc7f95e73364d9066b70a873",
           "bytes": 61132
         },
         {
           "path": "skills/seo-aeo-audit/scripts/page_audit.py",
-          "sha256": "492ae9dac4f32158db50def808f7f9b0952d188dafdb47984df01c02b2c5e965",
+          "sha256": "6694279f96ea90bc2797adeb430b800bf04c674a625e37e64bc464a118237efc",
           "bytes": 80703
         },
         {
           "path": "skills/seo-aeo-audit/scripts/preflight.py",
-          "sha256": "5497598d14dfcfada90e41ec2684e32d56b786e6314c16c1d84c65ea6d5d5047",
+          "sha256": "23f5fe8db6d7f219c8f43eced4d995239abf6d49b7996e937964f88bcfab4139",
           "bytes": 65317
         },
         {
           "path": "skills/seo-aeo-audit/scripts/psi_pull.py",
-          "sha256": "38fde119ac40aeec72c0f8dca88f31ac730382f2b9272a3d10993ea83848f848",
+          "sha256": "aaabbc25be17217ed1cbda2a9d7f1dfbe6873885d48bfad907384312adf7080b",
           "bytes": 28522
         },
         {
           "path": "skills/seo-aeo-audit/scripts/sitemap_audit.py",
-          "sha256": "c17da63f913fe256879b02dd3da978b36f45959818f153efec256878e51eeeba",
+          "sha256": "0c4580b14ab26d1cc033cbd786b829328eba4c75ef67881e1a93e5ba79b878ee",
           "bytes": 44650
         },
         {
           "path": "skills/seo-aeo-audit/scripts/url_inspection.py",
-          "sha256": "31e10819459f89246ce55d3fc5b678c20e2177c5faedb3bdbbdd22bfbf9243ee",
-          "bytes": 34553
+          "sha256": "e531e03d7d7e9eac1b4b8f34d37b91232a13dbe2a17b3b4ea628195449b5e7a7",
+          "bytes": 36543
         },
         {
           "path": "skills/seo-aeo-audit/SKILL.md",
@@ -3265,8 +3270,8 @@
     {
       "name": "agent-stack",
       "repo": "ssheleg/agent-stack",
-      "commit": "4a15f7c26f41c95ce300be131d5d6f33491f4f88",
-      "version": "0.30.2",
+      "commit": "27be243b737e50cb1198207ba07e8704076853bb",
+      "version": "0.31.2",
       "pluginInstall": "agent-stack@agent-stack",
       "pluginPath": "plugins/agent-stack",
       "entry": {
@@ -3274,7 +3279,7 @@
         "displayName": "Agent Stack",
         "source": "./plugins/agent-stack",
         "description": "Four skills: agent-orchestrator — tool-calling loops, pipelines with checkpoints, provider routing with fallback, memory architecture, plus the wallet side of reselling LLM access; agent-evals — run/trace/thread evals, LLM judges, and fixtures grown from production; agent-interop — MCP servers and clients, A2A agent cards, the MCP Registry, and gateways; agent-harness — system prompts, tool shaping, workflow-vs-agent, and auditing an agent system.",
-        "version": "0.30.2",
+        "version": "0.31.2",
         "author": {
           "name": "ssheleg",
           "url": "https://x.com/sshlg93"
@@ -3299,7 +3304,7 @@
       "files": [
         {
           "path": ".claude-plugin/plugin.json",
-          "sha256": "dcede6fd908154045471766784f2de2ba7bcb205a38761d2335a1cec907edc13",
+          "sha256": "9f3c5b3a06538e3a5dfdffd47f1cf531d943d3f40816bd18ae3961480241d643",
           "bytes": 1081
         },
         {
@@ -3317,10 +3322,15 @@
           "sha256": "77cd03cc4f258a097888f81b817e8c9487b4d777d9ac092f76fe48de8de692ca",
           "bytes": 13853
         },
+        {
+          "path": "skills/agent-evals/references/support-quality.md",
+          "sha256": "a39fb4a9b68d9d90c9a2ccf1a32252535328b582b487a0196e7b321fb4a44dbd",
+          "bytes": 12410
+        },
         {
           "path": "skills/agent-evals/SKILL.md",
-          "sha256": "221d4487a1775f8b9c1fc30ac49251a14d08e248def29afdfc66aa677db417b3",
-          "bytes": 21197
+          "sha256": "6c17dff16c45711cd3ca550585e23fb77b2d1f59fbc26c7042625f423ac46b6d",
+          "bytes": 21472
         },
         {
           "path": "skills/agent-harness/references/audit.md",
@@ -3484,8 +3494,8 @@
         },
         {
           "path": "skills/agent-orchestrator/SKILL.md",
-          "sha256": "7d0e36de35cf002c2959aba394f9ed89d264473b049695d2e54dabfe191480e1",
-          "bytes": 20571
+          "sha256": "e933867fb85610efd76e7bc8b1d0ec186cfe26cefbbe6c43afb5d8062a8e232e",
+          "bytes": 20723
         }
       ]
     },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sshlg-skills",
-  "version": "1.76.0",
+  "version": "1.76.2",
   "skillsCli": "skills@1.7.2",
   "description": "The ssheleg harness skill layer: routing, delivery gates, specialist skills and durable handoffs for coding agents.",
   "bin": {

package/skills.json

@@ -160,13 +160,13 @@
       "skillNames": [
         "seo-aeo-audit"
       ],
-      "version": "0.31.0",
+      "version": "0.32.0",
       "entry": "/seo-aeo-audit",
       "role": "whether a machine will find it",
       "npm": "@ssheleg/seo-aeo-audit",
       "shape": "static, with a bounded discovery",
       "shapeWhy": "The ten tracks are fixed; **which** are in scope is decided per site at step 0 and written into the report, so the executed set is recoverable. An eleventh pass (Discover) is added by a stated condition, never by taste.",
-      "commit": "1cbb3610b484dfc700086c8470377944c0e405da"
+      "commit": "51dba1913c967e606b773786f091302771d242ed"
     },
     {
       "name": "sheleg-dev",
@@ -205,13 +205,13 @@
         "agent-interop",
         "agent-harness"
       ],
-      "version": "0.30.2",
+      "version": "0.31.2",
       "entry": null,
       "role": "orchestration, prompts, evals, protocols, and the LLM wallet",
       "npm": "@ssheleg/agent-stack",
       "shape": "static",
       "shapeWhy": "Reference material, not a run. What varies is which reference a task loads, which the SKILL.md table decides in advance.",
-      "commit": "4a15f7c26f41c95ce300be131d5d6f33491f4f88"
+      "commit": "27be243b737e50cb1198207ba07e8704076853bb"
     },
     {
       "name": "telegram-dev",