sshlg-skills 0.77.0 → 0.78.0

package/CHANGELOG.md

@@ -1,5 +1,34 @@
 # Changelog
 
+## v0.78.0 — an unqualified landing page reaches both crafts
+
+**B-57: `сделай лендинг` reached no route at all — and neither did `build a landing page`,
+which the row never mentioned.** A landing is the canonical two-craft surface, so the ask
+for one arriving at nothing was the gap; both phrases now reach **`sheleg-design` ∥
+`copywriting`** together, which is the composition this family prescribes for a landing.
+
+**Verb phrases, not the bare noun, and the difference was measured rather than argued.**
+
+| prompt | bare `лендинг` | verb phrase |
+|---|---|---|
+| `сделай лендинг` | both | **both** |
+| `build a landing page` | both | **both** |
+| `напиши текст для лендинга` | both — a copy task handed a visual route | **copywriting alone** |
+| `почини баг на лендинге` | three routes | **task-pipeline alone** |
+
+The bare noun fixes one case and damages two. Cycle 5 refused it for a reason that no
+longer held — it said the bare noun would *take* the route from `copywriting`, and with
+both crafts firing that is no longer true — but measuring found a different reason that
+does hold, so the refusal stands on new evidence rather than old.
+
+**A premise of the row had expired.** It said both descriptions were at or near the
+1024-character limit; `copywriting` is at **536**, with 488 free. Only `sheleg-design` was
+tight, and there the room was **made rather than found** — `scrubbed sections` and one
+`implemented` came out of the prose, 30 characters that were not carrying their weight
+beside a phrase an operator actually types.
+
+**Pins: `sheleg-design` 1.37.4 → 1.37.5, `super-ux` 0.41.4 → 0.41.5.**
+
 ## v0.77.0 — closing a false positive found the bypass it was hiding
 
 **B-59: the hygiene guard could not tell a command being run from one being written

package/README.md

@@ -33,11 +33,11 @@ scripts. No services, no telemetry, no API keys.
 
 | Skill | Version | What it does |
 |---|---|---|
-| **[super-ux](https://github.com/ssheleg/super-ux)** | 0.41.4 | Scenario-driven UI development. A versioned design chain in `docs/ux/` — the product vision → personas and jobs → user flows → a screens-and-states map with Figma frames → traced scenarios → evidence-backed audits → fix plans, plus `docs/brand/` for how the product speaks. One `/ux` entry point that reaches every skill, two doc-drift linters and a contract doctor. |
+| **[super-ux](https://github.com/ssheleg/super-ux)** | 0.41.5 | Scenario-driven UI development. A versioned design chain in `docs/ux/` — the product vision → personas and jobs → user flows → a screens-and-states map with Figma frames → traced scenarios → evidence-backed audits → fix plans, plus `docs/brand/` for how the product speaks. One `/ux` entry point that reaches every skill, two doc-drift linters and a contract doctor. |
 | **[task-pipeline](https://github.com/ssheleg/task-pipeline)** | 1.67.0 | Full-cycle delivery orchestrator. An intake grill interrogates the request into a complete brief, then **ten gated stages** carry it — docs, brainstorm and decompose, spec, plan, build, tests, deploy, post-deploy, wiki, acceptance — refusing to advance until each gate passes. Documentation is a deliverable with its own portable gate, and the retrospective it leaves behind is traceable to the commit that earned each lesson. |
 | **[agent-sync](https://github.com/ssheleg/agent-sync)** | 1.11.1 | 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)** | 0.19.1 | 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)** | 1.37.4 | 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. |
+| **[sheleg-design](https://github.com/ssheleg/sheleg-design-skill)** | 1.37.5 | 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)** | 0.20.2 | 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. |
 | **[sheleg-dev](https://github.com/ssheleg/sheleg-dev)** | 0.5.2 | 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; 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. |
 | **[agent-stack](https://github.com/ssheleg/agent-stack)** | 0.11.1 | 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, four memory layers with confidence decay and conflict resolution, 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. |

package/lib/triggers.js

@@ -112,6 +112,7 @@ const ROUTES = {
       'палитра', 'palette', 'цвета', 'colors', 'типографика', 'typography',
       'шрифт', 'font', 'выглядит', 'how it looks', 'красивее', 'красиво',
       'make it prettier', 'анимация', 'hero',
+      'сделай лендинг', 'build a landing page',
       // Both forms of the same adjective, because the stemmer cannot bridge them:
       // `красивее` cuts to `красиве`, which is not a prefix of `красиво`. The skill
       // advertises both for that reason — a stem in this list instead of a word
@@ -159,6 +160,7 @@ const ROUTES = {
       'write copy', 'напиши текст', 'rewrite this', 'перепиши',
       'store listing', 'описание в сторе', 'microcopy', 'микрокопия',
       'звучит как нейросеть',
+      'сделай лендинг', 'build a landing page',
     ],
     line: 'is text a user of the product will read → `/copy` writes it in the recorded voice',
   },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sshlg-skills",
-  "version": "0.77.0",
+  "version": "0.78.0",
   "description": "One launcher/updater for the ssheleg skill family (super-ux, task-pipeline, agent-sync, make-skill, sheleg-design, seo-aeo-audit, sheleg-dev, agent-stack) across every agent — Claude Code, Cursor, OpenCode, Kilo, Kimi, Hermes, OpenClaw, Codex, and more.",
   "bin": {
     "sshlg-skills": "bin/sshlg-skills.js"

package/skills.json

@@ -31,7 +31,7 @@
       "pluginMarketplace": "ssheleg/super-ux",
       "pluginInstall": "super-ux@super-ux",
       "desc": "Scenario-driven UI development: a versioned design chain in docs/ux/ — the product vision, personas and jobs, user flows, a screens-and-states map with Figma frames, traced scenarios, evidence-backed audits, fix plans — plus docs/brand/, the verbal identity: one voice, per-surface registers, a string registry and a 35-check copy linter. /ux and /brand entry points, two doc-drift linters and a contract doctor.",
-      "version": "0.41.4",
+      "version": "0.41.5",
       "entry": "/ux",
       "role": "what the interface must do and how it sounds",
       "npm": "super-ux",
@@ -100,7 +100,7 @@
       "skillNames": [
         "sheleg-design"
       ],
-      "version": "1.37.4",
+      "version": "1.37.5",
       "entry": "/sheleg-design",
       "role": "how it looks and moves",
       "npm": "sheleg-design-skill",