sshlg-skills 1.3.2 → 1.3.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +44 -0
- package/README.md +16 -15
- package/package.json +2 -2
- package/skills.json +9 -9
package/CHANGELOG.md
CHANGED
|
@@ -1,3 +1,47 @@
|
|
|
1
|
+
## v1.3.4 — the public shelf becomes one system
|
|
2
|
+
|
|
3
|
+
- Every member now opens with one promise, one install command and one concrete
|
|
4
|
+
invocation; each also ships a root `SKILL-CARD.md`, schema-validated trigger
|
|
5
|
+
and scenario fixtures, and a committed 1200×630 social card.
|
|
6
|
+
- The umbrella owns a shared public voice pack and generates version-independent
|
|
7
|
+
social cards for all nine members. Its site test compares every committed card's
|
|
8
|
+
decoded pixels with the generator output, remaining strict across zlib runtimes
|
|
9
|
+
that legitimately encode those pixels with different bytes. A change to that
|
|
10
|
+
gate now retriggers Pages, so repairing a failed page build cannot leave the
|
|
11
|
+
corrected site undeployed.
|
|
12
|
+
- Member CI now runs the pinned make-skill house audit plus eval and social-card
|
|
13
|
+
guards. The member pins advance to the nine patch releases carrying that
|
|
14
|
+
contract.
|
|
15
|
+
|
|
16
|
+
## v1.3.3 — the two most quotable pages had an entity attached to nothing
|
|
17
|
+
|
|
18
|
+
With the walker repaired, the post-deploy probe reported what v1.3.2 could not
|
|
19
|
+
see: on `/agents/` and `/routing/` the publisher node stood alone. Their structured
|
|
20
|
+
data was a `FAQPage` and a `BreadcrumbList` — and a breadcrumb says where a page
|
|
21
|
+
sits, nothing about what it is or who stands behind it — so every content node on
|
|
22
|
+
the two pages an answer engine is likeliest to quote was **anonymous**, with a
|
|
23
|
+
`Person` beside it that nothing referenced.
|
|
24
|
+
|
|
25
|
+
`/routing/` now carries a `WebPage` node of its own, the `FAQPage` and the front
|
|
26
|
+
page's `ItemList` name their author, and all three reference the one `@id`.
|
|
27
|
+
|
|
28
|
+
**The fixture's own `refsSeen > 0` was counted for the whole site, so it was green
|
|
29
|
+
throughout.** One page with a reference satisfied it for all thirteen. Counted per
|
|
30
|
+
page now — and moving it inside the loop immediately found a third page,
|
|
31
|
+
`404.html`, which is the point of the change.
|
|
32
|
+
|
|
33
|
+
**The 404 is `noindex` now**, on its own merits: GitHub Pages serves it with a real
|
|
34
|
+
404 status, but a host serving that body with 200 during a migration would put a
|
|
35
|
+
page reading *"That page is not here"* into the index under the site's own name.
|
|
36
|
+
The authorship rule exempts it — keyed on the **declared** `noindex`, never on the
|
|
37
|
+
filename, because an exemption spelled `rel !== '404.html'` is a rule with a hole
|
|
38
|
+
named after one file and the next such page arrives unexamined. The exemption is
|
|
39
|
+
asserted to cover exactly one page.
|
|
40
|
+
|
|
41
|
+
Six plants across this version and the last, each watched failing. One of them
|
|
42
|
+
planted nothing on its first run and said so rather than counting as a pass — the
|
|
43
|
+
`assert` that the source actually changed is why.
|
|
44
|
+
|
|
1
45
|
## v1.3.2 — half of yesterday's fixture could not run, and the live page said so
|
|
2
46
|
|
|
3
47
|
v1.3.1 shipped a check asserting that every `Person` reference carries `@id` and
|
package/README.md
CHANGED
|
@@ -5,14 +5,15 @@
|
|
|
5
5
|
[](LICENSE)
|
|
6
6
|
[](https://skills.sshlg.me/)
|
|
7
7
|
|
|
8
|
-
**Nine
|
|
8
|
+
**Nine skill packs, 28 Agent Skills, one command.**
|
|
9
9
|
|
|
10
10
|
```bash
|
|
11
|
-
npx sshlg-skills install
|
|
12
|
-
npx sshlg-skills update # update everything already installed
|
|
11
|
+
npx sshlg-skills install
|
|
13
12
|
```
|
|
14
13
|
|
|
15
|
-
|
|
14
|
+
Verify the resolved family: `npx --yes sshlg-skills@latest list`.
|
|
15
|
+
|
|
16
|
+
**[Detailed docs →](https://skills.sshlg.me/)** · one page per skill,
|
|
16
17
|
every routing rule verbatim, and [`llms.txt`](https://skills.sshlg.me/llms.txt)
|
|
17
18
|
for the machines. · **[Follow @sshlg93 on X](https://x.com/intent/follow?screen_name=sshlg93)**
|
|
18
19
|
|
|
@@ -38,15 +39,15 @@ scripts. No services, no telemetry, no API keys.
|
|
|
38
39
|
|
|
39
40
|
| Skill | Version | What it does |
|
|
40
41
|
|---|---|---|
|
|
41
|
-
| **[super-ux](https://github.com/ssheleg/super-ux)** | 0.48.
|
|
42
|
-
| **[task-pipeline](https://github.com/ssheleg/task-pipeline)** | 1.78.
|
|
43
|
-
| **[agent-sync](https://github.com/ssheleg/agent-sync)** | 1.
|
|
44
|
-
| **[make-skill](https://github.com/ssheleg/make-skill)** | 0.23.
|
|
45
|
-
| **[sheleg-design](https://github.com/ssheleg/sheleg-design-skill)** | 1.50.
|
|
46
|
-
| **[seo-aeo-audit](https://github.com/ssheleg/seo-aeo-audit)** | 0.25.
|
|
47
|
-
| **[sheleg-dev](https://github.com/ssheleg/sheleg-dev)** | 0.10.
|
|
48
|
-
| **[agent-stack](https://github.com/ssheleg/agent-stack)** | 0.13.
|
|
49
|
-
| **[telegram-dev](https://github.com/ssheleg/telegram-dev)** | 0.1.
|
|
42
|
+
| **[super-ux](https://github.com/ssheleg/super-ux)** | 0.48.3 | 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. |
|
|
43
|
+
| **[task-pipeline](https://github.com/ssheleg/task-pipeline)** | 1.78.3 | 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. Ships `project-audit`: a cold-start audit of a whole project — discovery, probes whose unmet needs read `blind` rather than clean, production evidence including one artefact served under two channels, and an HTML report beside a JSON sidecar that says what moved. |
|
|
44
|
+
| **[agent-sync](https://github.com/ssheleg/agent-sync)** | 1.18.3 | 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". |
|
|
45
|
+
| **[make-skill](https://github.com/ssheleg/make-skill)** | 0.23.4 | 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`. |
|
|
46
|
+
| **[sheleg-design](https://github.com/ssheleg/sheleg-design-skill)** | 1.50.3 | 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. |
|
|
47
|
+
| **[seo-aeo-audit](https://github.com/ssheleg/seo-aeo-audit)** | 0.25.5 | 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. |
|
|
48
|
+
| **[sheleg-dev](https://github.com/ssheleg/sheleg-dev)** | 0.10.3 | 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. |
|
|
49
|
+
| **[agent-stack](https://github.com/ssheleg/agent-stack)** | 0.13.5 | 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. |
|
|
50
|
+
| **[telegram-dev](https://github.com/ssheleg/telegram-dev)** | 0.1.7 | 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. |
|
|
50
51
|
|
|
51
52
|
They compose. `task-pipeline` hands user-facing work to `super-ux` and takes its
|
|
52
53
|
leases from `agent-sync`; `make-skill` encodes the repo layout the others are
|
|
@@ -232,7 +233,7 @@ oblige. So the pack writes a **managed routing block** into your global agent
|
|
|
232
233
|
instructions, and the rules engage in every project instead of only when
|
|
233
234
|
someone remembers to ask.
|
|
234
235
|
|
|
235
|
-
The block opens with the **map**:
|
|
236
|
+
The block opens with the **map**: nine members, the single command that starts
|
|
236
237
|
each, and one line saying what it closes. It is generated from `skills.json`,
|
|
237
238
|
so a release moves it — and `install` and `update` refresh it, which is what
|
|
238
239
|
makes "the instruction your agents read is current" a mechanism rather than a
|
|
@@ -469,7 +470,7 @@ get wrong: one channel per agent, exact agent ids, repeated `--agent` flags, ful
|
|
|
469
470
|
|
|
470
471
|
```
|
|
471
472
|
skills.json registry — repos, plugin ids, skill names, pins
|
|
472
|
-
skills/* the
|
|
473
|
+
skills/* the nine skill packs as pinned git submodules
|
|
473
474
|
bin/sshlg-skills.js the launcher (install / update / routers / config / hooks /
|
|
474
475
|
injectors / conflicts / list / agents)
|
|
475
476
|
lib/routers-registry.js the ten routers — text, table row and required members, in one entry
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "sshlg-skills",
|
|
3
|
-
"version": "1.3.
|
|
4
|
-
"description": "
|
|
3
|
+
"version": "1.3.4",
|
|
4
|
+
"description": "Install and update nine ssheleg skill packs across Claude Code, Codex, Cursor, OpenCode and other Agent Skills-compatible tools.",
|
|
5
5
|
"bin": {
|
|
6
6
|
"sshlg-skills": "bin/sshlg-skills.js"
|
|
7
7
|
},
|
package/skills.json
CHANGED
|
@@ -31,7 +31,7 @@
|
|
|
31
31
|
"pluginMarketplace": "ssheleg/super-ux",
|
|
32
32
|
"pluginInstall": "super-ux@super-ux",
|
|
33
33
|
"desc": "Scenario-driven UI development: a versioned design chain in docs/ux/ — the product vision, personas and jobs, user flows and the paid-acquisition funnel among them, 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.",
|
|
34
|
-
"version": "0.48.
|
|
34
|
+
"version": "0.48.3",
|
|
35
35
|
"entry": "/ux",
|
|
36
36
|
"role": "what the interface must do and how it sounds",
|
|
37
37
|
"npm": "super-ux",
|
|
@@ -50,7 +50,7 @@
|
|
|
50
50
|
"evidence-docs",
|
|
51
51
|
"project-audit"
|
|
52
52
|
],
|
|
53
|
-
"version": "1.78.
|
|
53
|
+
"version": "1.78.3",
|
|
54
54
|
"entry": "/task-pipeline",
|
|
55
55
|
"role": "how a change reaches the repository",
|
|
56
56
|
"npm": "task-pipeline-skill",
|
|
@@ -67,7 +67,7 @@
|
|
|
67
67
|
"skillNames": [
|
|
68
68
|
"agent-sync"
|
|
69
69
|
],
|
|
70
|
-
"version": "1.
|
|
70
|
+
"version": "1.18.3",
|
|
71
71
|
"entry": "/agent-sync",
|
|
72
72
|
"role": "who is holding this file right now",
|
|
73
73
|
"npm": "@ssheleg/agent-sync",
|
|
@@ -84,7 +84,7 @@
|
|
|
84
84
|
"skillNames": [
|
|
85
85
|
"make-skill"
|
|
86
86
|
],
|
|
87
|
-
"version": "0.23.
|
|
87
|
+
"version": "0.23.4",
|
|
88
88
|
"entry": "/skill-audit",
|
|
89
89
|
"role": "how the skill or plugin itself is built",
|
|
90
90
|
"npm": "@ssheleg/make-skill",
|
|
@@ -101,7 +101,7 @@
|
|
|
101
101
|
"skillNames": [
|
|
102
102
|
"sheleg-design"
|
|
103
103
|
],
|
|
104
|
-
"version": "1.50.
|
|
104
|
+
"version": "1.50.3",
|
|
105
105
|
"entry": "/sheleg-design",
|
|
106
106
|
"role": "how it looks and moves",
|
|
107
107
|
"npm": "sheleg-design-skill",
|
|
@@ -129,7 +129,7 @@
|
|
|
129
129
|
"skillNames": [
|
|
130
130
|
"seo-aeo-audit"
|
|
131
131
|
],
|
|
132
|
-
"version": "0.25.
|
|
132
|
+
"version": "0.25.5",
|
|
133
133
|
"entry": "/seo-aeo-audit",
|
|
134
134
|
"role": "whether a machine will find it",
|
|
135
135
|
"npm": "@ssheleg/seo-aeo-audit",
|
|
@@ -152,7 +152,7 @@
|
|
|
152
152
|
"google-auth",
|
|
153
153
|
"frontend-performance"
|
|
154
154
|
],
|
|
155
|
-
"version": "0.10.
|
|
155
|
+
"version": "0.10.3",
|
|
156
156
|
"entry": null,
|
|
157
157
|
"role": "integrations: money in, tracking, sign-in, speed",
|
|
158
158
|
"npm": "@ssheleg/sheleg-dev",
|
|
@@ -172,7 +172,7 @@
|
|
|
172
172
|
"agent-interop",
|
|
173
173
|
"agent-harness"
|
|
174
174
|
],
|
|
175
|
-
"version": "0.13.
|
|
175
|
+
"version": "0.13.5",
|
|
176
176
|
"entry": null,
|
|
177
177
|
"role": "agent orchestrators, their evals, the protocols they speak, and the wallet under LLM resale",
|
|
178
178
|
"npm": "@ssheleg/agent-stack",
|
|
@@ -191,7 +191,7 @@
|
|
|
191
191
|
"telegram-userbots",
|
|
192
192
|
"telegram-miniapps"
|
|
193
193
|
],
|
|
194
|
-
"version": "0.1.
|
|
194
|
+
"version": "0.1.7",
|
|
195
195
|
"entry": null,
|
|
196
196
|
"role": "which Telegram API each surface speaks, and what each one costs",
|
|
197
197
|
"npm": "@ssheleg/telegram-dev",
|