opencode-skills-antigravity 1.0.68 → 1.0.70

package/bundled-skills/.antigravity-install-manifest.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "updatedAt": "2026-03-31T13:22:39.691Z",
+  "updatedAt": "2026-03-31T16:59:54.384Z",
   "entries": [
     ".gitignore",
     "00-andruia-consultant",

package/bundled-skills/docs/integrations/jetski-cortex.md

@@ -1,54 +1,54 @@
 ---
 title: Jetski/Cortex + Gemini Integration Guide
-description: "Come usare antigravity-awesome-skills con Jetski/Cortex evitando l’overflow di contesto con 1.340+ skill."
+description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1.340+ skills."
 ---
 
-# Jetski/Cortex + Gemini: integrazione sicura con 1.340+ skill
+# Jetski/Cortex + Gemini: safe integration with 1,1.340+ skills
 
-Questa guida mostra come integrare il repository `antigravity-awesome-skills` con un agente basato su **Jetski/Cortex + Gemini** (o framework simili) **senza superare il context window** del modello.
+This guide shows how to integrate the `antigravity-awesome-skills` repository with an agent based on **Jetski/Cortex + Gemini** (or similar frameworks) **without exceeding the model context window**.
 
-L’errore tipico visto in Jetski/Cortex è:
+The common error seen in Jetski/Cortex is:
 
 > `TrajectoryChatConverter: could not convert a single message before hitting truncation`
 
-Il problema non è nelle skill, ma **nel modo in cui vengono caricate**.
+The issue is not with the skills themselves, but **with how they are loaded**.
 
 ---
 
-## 1. Antipattern da evitare
+## 1. Anti-pattern to avoid
 
-Non bisogna mai:
+Never do:
 
-- leggere **tutte** le directory `skills/*/SKILL.md` all’avvio;
-- concatenare il contenuto di tutte le `SKILL.md` in un singolo system prompt;
-- reiniettare l’intera libreria per **ogni** richiesta.
+- read **all** `skills/*/SKILL.md` directories at startup;
+- concatenate all `SKILL.md` content into a single system prompt;
+- re-inject the entire library for **every** request.
 
-Con oltre 1.340 skill, questo approccio riempie il context window prima ancora di aggiungere i messaggi dell’utente, causando l’errore di truncation.
+With over 1,1.340 skills, this approach fills the context window before user messages are even added, causing truncation.
 
 ---
 
-## 2. Pattern raccomandato
+## 2. Recommended pattern
 
-Principi chiave:
+Core principles:
 
-- **Manifest leggero**: usare `data/skills_index.json` per sapere *quali* skill esistono, senza caricare i testi completi.
-- **Lazy loading**: leggere `SKILL.md` **solo** per le skill effettivamente invocate in una conversazione (es. quando compare `@skill-id`).
-- **Limiti espliciti**: imporre un massimo di skill/tokens caricati per turno, con fallback chiari.
-- **Path safety**: verificare che i path del manifest restino dentro `SKILLS_ROOT` prima di leggere `SKILL.md`.
+- **Light manifest**: use `data/skills_index.json` to know *which* skills exist without loading full text.
+- **Lazy loading**: read `SKILL.md` **only** for skills actually invoked in a conversation (for example, when `@skill-id` appears).
+- **Explicit limits**: enforce a maximum number of skills/tokens loaded per turn, with clear fallbacks.
+- **Path safety**: verify manifest paths remain inside `SKILLS_ROOT` before reading `SKILL.md`.
 
-Il flusso consigliato è:
+The recommended flow is:
 
-1. **Bootstrap**: all’avvio dell’agente leggere `data/skills_index.json` e costruire una mappa `id -> meta`.
-2. **Parsing dei messaggi**: prima di chiamare il modello, estrarre tutti i riferimenti `@skill-id` dai messaggi utente/sistema.
-3. **Risoluzione**: mappare gli id trovati in oggetti `SkillMeta` usando la mappa di bootstrap.
-4. **Lazy load**: leggere i file `SKILL.md` solo per questi id (fino a un massimo configurabile).
-5. **Prompt building**: costruire i system messages del modello includendo solo le definizioni delle skill selezionate.
+1. **Bootstrap**: on agent startup, read `data/skills_index.json` and build an `id -> meta` map.
+2. **Message parsing**: before calling the model, extract all `@skill-id` references from user/system messages.
+3. **Resolution**: map the found IDs into `SkillMeta` objects using the bootstrap map.
+4. **Lazy load**: read `SKILL.md` files only for these IDs (up to a configurable maximum).
+5. **Prompt building**: build model system messages including only the selected skill definitions.
 
 ---
 
-## 3. Struttura di `skills_index.json`
+## 3. Structure of `skills_index.json`
 
-Il file `data/skills_index.json` è un array di oggetti, ad esempio:
+The file `data/skills_index.json` is an array of objects, for example:
 
 ```json
 {
@@ -63,24 +63,24 @@ Il file `data/skills_index.json` è un array di oggetti, ad esempio:
 }
 ```
 
-Campi chiave:
+Key fields:
 
-- **`id`**: identificatore usato nelle menzioni `@id` (es. `@brainstorming`).
-- **`path`**: directory che contiene la `SKILL.md` (es. `skills/brainstorming/`).
+- **`id`**: identifier used in `@id` mentions (for example, `@brainstorming`).
+- **`path`**: directory containing `SKILL.md` (for example, `skills/brainstorming/`).
 
-Per ottenere il percorso alla definizione della skill:
+To resolve the path to a skill definition:
 
 - `fullPath = path.join(SKILLS_ROOT, meta.path, "SKILL.md")`.
 
-> Nota: `SKILLS_ROOT` è la directory radice dove avete installato il repository (es. `~/.agent/skills`).
+> Note: `SKILLS_ROOT` is the root directory where you installed the repository (for example, `~/.agent/skills`).
 
 ---
 
-## 4. Pseudo‑codice di integrazione (TypeScript)
+## 4. Integration pseudocode (TypeScript)
 
-> Esempio completo in: [`docs/integrations/jetski-gemini-loader/`](../../docs/integrations/jetski-gemini-loader/).
+> Full example in: [`docs/integrations/jetski-gemini-loader/`](../../docs/integrations/jetski-gemini-loader/).
 
-### 4.1. Tipi di base
+### 4.1. Core Types
 
 ```ts
 type SkillMeta = {
@@ -93,7 +93,7 @@ type SkillMeta = {
 };
 ```
 
-### 4.2. Bootstrap: caricare il manifest
+### 4.2. Bootstrap: load the manifest
 
 ```ts
 function loadSkillIndex(indexPath: string): Map<string, SkillMeta> {
@@ -107,7 +107,7 @@ function loadSkillIndex(indexPath: string): Map<string, SkillMeta> {
 }
 ```
 
-### 4.3. Parsing dei messaggi per trovare `@skill-id`
+### 4.3. Parse messages to find `@skill-id`
 
 ```ts
 const SKILL_ID_REGEX = /@([a-zA-Z0-9-_./]+)/g;
@@ -140,7 +140,7 @@ function resolveSkillsFromMessages(
 }
 ```
 
-### 4.4. Lazy loading dei file `SKILL.md`
+### 4.4. Lazy loading `SKILL.md` files
 
 ```ts
 async function loadSkillBodies(
@@ -159,9 +159,9 @@ async function loadSkillBodies(
 }
 ```
 
-### 4.5. Costruzione del prompt Jetski/Cortex
+### 4.5. Build the Jetski/Cortex prompt
 
-Pseudocodice per la fase di pre‑processing, prima del `TrajectoryChatConverter`:
+Pseudocode for the pre-processing phase before `TrajectoryChatConverter`:
 
 ```ts
 async function buildModelMessages(
@@ -203,70 +203,70 @@ async function buildModelMessages(
 }
 ```
 
-> Suggerimento: aggiungete una stima dei token per troncare o riassumere i `SKILL.md` se il context window si avvicina al limite.
-> Il reference loader di questo repo supporta anche un fallback esplicito: `overflowBehavior: "error"`.
+> Tip: Add token estimation to trim or summarize `SKILL.md` files when the context window approaches its limit.
+> This repository's reference loader also supports an explicit fallback: `overflowBehavior: "error"`.
 
 ---
 
-## 5. Gestione degli overflow di contesto
+## 5. Context overflow handling
 
-Per evitare errori difficili da capire per l’utente, impostate:
+To avoid unclear errors for the user, set:
 
-- una **soglia di sicurezza** (es. 70–80% del context window);
-- un **limite massimo di skill per turno** (es. 5–10).
+- a **safety threshold** (for example, 70–80% of the context window);
+- a **maximum number of skills per turn** (for example, 5–10).
 
-Strategie quando si supera la soglia:
+Strategies when the threshold is exceeded:
 
-- ridurre il numero di skill incluse (es. in base a recenza o priorità); oppure
-- restituire un errore chiaro all’utente, ad esempio:
+- reduce the number of included skills (for example, by recency or priority); or
+- return a clear error to the user, for example:
 
-> "Sono state richieste troppe skill in un singolo turno. Riduci il numero di `@skill-id` nel messaggio o dividili in più passaggi."
+> "Too many skills were requested in a single turn. Reduce the number of `@skill-id` references in your message or split them into multiple turns."
 
 ---
 
-## 6. Scenari di test raccomandati
+## 6. Recommended test scenarios
 
-- **Scenario 1 – Messaggio semplice ("hi")**
-  - Nessun `@skill-id` → nessuna `SKILL.md` caricata → il prompt rimane piccolo → nessun errore.
-- **Scenario 2 – Poche skill**
-  - Messaggio con 1–2 `@skill-id` → solo le relative `SKILL.md` vengono caricate → nessun overflow.
-- **Scenario 3 – Molte skill**
-  - Messaggio con molte `@skill-id` → si attiva il limite `maxSkillsPerTurn` o il controllo di token → nessun overflow silenzioso.
+- **Scenario 1 – Simple message ("hi")**
+  - No `@skill-id` → no `SKILL.md` loaded → prompt remains small → no error.
+- **Scenario 2 – Few skills**
+  - Message with 1–2 `@skill-id` references → only related `SKILL.md` files are loaded → no overflow.
+- **Scenario 3 – Many skills**
+  - Message with many `@skill-id` references → `maxSkillsPerTurn` or token guardrails trigger → no silent overflow.
 
 ---
 
-## 7. Sottoinsiemi di skill e bundle
+## 7. Skill subsets and bundles
 
-Per ulteriore controllo:
+For additional control:
 
-- spostate le skill non necessarie in `skills/.disabled/` per escluderle in certi ambienti;
-- usate i **bundle** descritti in [`docs/users/bundles.md`](../users/bundles.md) per caricare solo gruppi tematici.
+- move unnecessary skills into `skills/.disabled/` to exclude them in certain environments;
+- use the **bundles** described in [`docs/users/bundles.md`](../users/bundles.md) to load only focused groups.
 
-## 8. Recovery su Windows se siete gia in crash loop
+## 8. Windows crash-loop recovery
 
-Se l’host continua a riaprire la stessa trajectory corrotta dopo un errore di truncation:
+If the host keeps reopening the same corrupted trajectory after a truncation error:
 
-- rimuovete la skill o il pacchetto problematico;
-- cancellate Local Storage / Session Storage / IndexedDB usati da Antigravity;
-- svuotate `%TEMP%`;
-- riavviate con un loader lazy e limiti espliciti.
+- remove the problematic skill or package;
+- clear Antigravity Local Storage / Session Storage / IndexedDB;
+- clear `%TEMP%`;
+- restart with lazy loading and explicit limits.
 
-Guida completa:
+Complete guide:
 
 - [`docs/users/windows-truncation-recovery.md`](../users/windows-truncation-recovery.md)
 
-Per evitare che il problema si ripresenti:
+To prevent recurrence:
 
-- mantenete `overflowBehavior: "error"` quando preferite un fallimento esplicito;
-- continuate a validare che i path risolti restino dentro `skillsRoot`.
+- keep `overflowBehavior: "error"` when you prefer explicit failure;
+- continue validating that resolved paths remain inside `skillsRoot`.
 
 ---
 
-## 9. Riepilogo
+## 9. Summary
 
-- Non concatenate mai tutte le `SKILL.md` in un singolo prompt.
-- Usate `data/skills_index.json` come manifest leggero.
-- Caricate le skill **on‑demand** in base a `@skill-id`.
-- Impostate limiti chiari (max skill per turno, soglia di token).
+- Do not concatenate all `SKILL.md` files into a single prompt.
+- Use `data/skills_index.json` as a lightweight manifest.
+- Load skills **on demand** based on `@skill-id`.
+- Set clear limits (max skills per turn, token threshold).
 
-Seguendo questo pattern, Jetski/Cortex + Gemini può usare l’intera libreria di `antigravity-awesome-skills` in modo sicuro, scalabile e compatibile con il context window dei modelli moderni.
+Following this pattern, Jetski/Cortex + Gemini can use the full `antigravity-awesome-skills` library safely, at scale, and within modern model context-window limits.

package/bundled-skills/docs/maintainers/audit.md

@@ -4,24 +4,24 @@ This document summarizes the repository coherence audit performed after the `app
 
 ## Scope
 
-- Conteggi e numeri (README, package.json, CATALOG)
-- Validazione skill (frontmatter, risk, "When to Use", link)
+- Counts and numbers (README, package.json, CATALOG)
+- Skill validation (frontmatter, risk, "When to Use", link)
 - Audit repo-wide per skill (conformance + baseline usability)
-- Riferimenti incrociati (workflows.json, bundles.json, `docs/users/bundles.md`)
-- Documentazione (`docs/contributors/quality-bar.md`, `docs/contributors/skill-anatomy.md`, security/licenses)
-- Script e build (validate, index, readme, catalog, test)
-- Note su data/ e test YAML
+- Cross references (workflows.json, bundles.json, `docs/users/bundles.md`)
+- Documentation (`docs/contributors/quality-bar.md`, `docs/contributors/skill-anatomy.md`, security/licenses)
+- Scripts and build (validate, index, readme, catalog, test)
+- Notes on data/ and test YAML
 
 ## Outcomes
 
-### 1. Conteggi
+### 1. Counts
 
 - `README.md`, `package.json`, and generated artifacts are aligned to the current collection size.
 - `npm run sync:repo-state` is the canonical maintainer command for keeping counts, generated files, contributors, and tracked web assets synchronized on local `main`.
 - `npm run sync:release-state` is the canonical release-facing variant when you want the same sync without the contributor refresh step.
 - `npm run sync:all` remains a legacy alias for the core chain, not the full maintainer sync surface.
 
-### 2. Validazione skill
+### 2. Skill validation
 
 - `npm run validate` is the operational contributor gate.
 - `npm run validate:strict` is currently a diagnostic hardening pass: it still surfaces repository-wide legacy metadata/content gaps across many older skills.
@@ -45,22 +45,22 @@ This document summarizes the repository coherence audit performed after the `app
 - The intended maintainer loop is: `audit:skills` to inspect `suggested_risk`, `sync:risk-labels` for the safe automated subset, then manual review for the ambiguous tail that should not be batch-classified.
 - Use `npm run audit:skills` for the maintainer view and `npm run audit:skills -- --json-out ... --markdown-out ...` when you want artifacts for triage or cleanup tracking.
 
-### 3. Riferimenti incrociati
+### 3. Cross references
 
 - Added `tools/scripts/validate_references.py` (also exposed as `npm run validate:references`), which verifies:
-  - ogni `recommendedSkills` in data/workflows.json esiste in skills/;
-  - ogni `relatedBundles` esiste in data/bundles.json;
-  - ogni slug in data/bundles.json (skills list) esiste in skills/;
+  - every `recommendedSkills` in data/workflows.json exists in skills/;
+  - every `relatedBundles` exists in data/bundles.json;
+  - every slug in data/bundles.json (skills list) exists in skills/;
   - every skill link in `docs/users/bundles.md` points to an existing skill.
 - Execution: `npm run validate:references`. Result: all references valid.
 
-### 4. Documentazione
+### 4. Documentation
 
 - Canonical contributor docs now live under `docs/contributors/`.
 - Canonical maintainer docs now live under `docs/maintainers/`.
 - README, security docs, licenses, and internal markdown links were rechecked after the refactor.
 
-### 5. Script e build
+### 5. Scripts and build
 
 - `npm run test` and `npm run app:build` complete successfully on the refactored layout.
 - `validate_skills_headings.test.js` acts as a lightweight regression/smoke test, not as the source of truth for full metadata compliance.
@@ -73,12 +73,12 @@ This document summarizes the repository coherence audit performed after the `app
 - User and maintainer docs checked for path drift after the layout change.
 - Follow-up still open: repository-wide cleanup required to make `validate:strict` fully green.
 
-## Comandi utili
+## Useful commands
 
 ```bash
-npm run validate          # validazione skill (soft)
+npm run validate          # skill validation (soft)
 npm run validate:strict   # hardening / diagnostic pass
-npm run audit:skills      # audit completo per skill con finding codes e status
+npm run audit:skills      # full skill audit with finding codes and status
 npm run sync:risk-labels  # conservative sync for high-confidence legacy risk labels
 npm run sync:risk-labels -- --dry-run  # preview legacy risk rewrites before touching files
 npm run validate:references  # workflow, bundle, and docs/users/bundles.md references
@@ -87,7 +87,7 @@ npm run build             # chain + catalog
 npm test                  # suite test
 ```
 
-## Issue aperte / follow-up
+## Open issues / follow-up
 
 - Gradual cleanup of legacy skills so `npm run validate:strict` can become a hard CI gate in the future.
 - Continue reducing the remaining `risk: unknown` tail with conservative sync passes plus manual maintainer review for ambiguous cases.

package/bundled-skills/docs/users/getting-started.md

@@ -1,4 +1,4 @@
-# Getting Started with Antigravity Awesome Skills (V9.3.0)
+# Getting Started with Antigravity Awesome Skills (V9.4.0)
 
 **New here? This guide will help you supercharge your AI Agent in 5 minutes.**
 

package/bundled-skills/docs/users/workflows.md

@@ -41,28 +41,28 @@ Build and ship a minimal but production-minded SaaS product.
 1. **Plan the scope**
    - **Goal:** Define MVP boundaries and acceptance criteria.
    - **Skills:** [`@brainstorming`](../../skills/brainstorming/), [`@concise-planning`](../../skills/concise-planning/), [`@writing-plans`](../../skills/writing-plans/)
-   - **Prompt example:** `Usa @concise-planning per definire milestones e criteri di accettazione del mio MVP SaaS.`
+   - **Prompt example:** `Use @concise-planning to define milestones and acceptance criteria for my SaaS MVP.`
 
 2. **Build backend and API**
    - **Goal:** Implement core entities, APIs, and auth baseline.
    - **Skills:** [`@backend-dev-guidelines`](../../skills/backend-dev-guidelines/), [`@api-patterns`](../../skills/api-patterns/), [`@database-design`](../../skills/database-design/)
-   - **Prompt example:** `Usa @backend-dev-guidelines per creare API e servizi del dominio billing.`
+   - **Prompt example:** `Use @backend-dev-guidelines to create APIs and services for the billing domain.`
 
 3. **Build frontend**
    - **Goal:** Ship core user flow with clear UX states.
    - **Skills:** [`@frontend-developer`](../../skills/frontend-developer/), [`@react-patterns`](../../skills/react-patterns/), [`@frontend-design`](../../skills/frontend-design/)
-   - **Prompt example:** `Usa @frontend-developer per implementare onboarding, empty state e dashboard iniziale.`
+   - **Prompt example:** `Use @frontend-developer to implement onboarding, the empty state, and the initial dashboard.`
 
 4. **Test and validate**
    - **Goal:** Cover critical user journeys before release.
    - **Skills:** [`@test-driven-development`](../../skills/test-driven-development/), [`@browser-automation`](../../skills/browser-automation/), `@go-playwright` (optional, Go stack)
-   - **Prompt example:** `Usa @browser-automation per creare test E2E sui flussi signup e checkout.`
-   - **Go note:** Se il progetto QA e tooling sono in Go, preferisci `@go-playwright`.
+   - **Prompt example:** `Use @browser-automation to create E2E tests for the signup and checkout flows.`
+   - **Go note:** If the QA project and tooling are in Go, prefer `@go-playwright`.
 
 5. **Ship safely**
    - **Goal:** Release with observability and rollback plan.
    - **Skills:** [`@deployment-procedures`](../../skills/deployment-procedures/), [`@observability-engineer`](../../skills/observability-engineer/)
-   - **Prompt example:** `Usa @deployment-procedures per una checklist di rilascio con rollback.`
+   - **Prompt example:** `Use @deployment-procedures for a release checklist with rollback steps.`
 
 ---
 
@@ -83,22 +83,22 @@ Run a focused security review from scope definition to remediation validation.
 1. **Define scope and threat model**
    - **Goal:** Identify assets, trust boundaries, and attack paths.
    - **Skills:** [`@ethical-hacking-methodology`](../../skills/ethical-hacking-methodology/), [`@threat-modeling-expert`](../../skills/threat-modeling-expert/), [`@attack-tree-construction`](../../skills/attack-tree-construction/)
-   - **Prompt example:** `Usa @threat-modeling-expert per mappare asset critici e trust boundaries della mia web app.`
+   - **Prompt example:** `Use @threat-modeling-expert to map critical assets and trust boundaries for my web app.`
 
 2. **Review auth and access control**
    - **Goal:** Detect account takeover and authorization flaws.
    - **Skills:** [`@broken-authentication`](../../skills/broken-authentication/), [`@auth-implementation-patterns`](../../skills/auth-implementation-patterns/), [`@idor-testing`](../../skills/idor-testing/)
-   - **Prompt example:** `Usa @idor-testing per verificare accessi non autorizzati su endpoint multitenant.`
+   - **Prompt example:** `Use @idor-testing to verify unauthorized access on multitenant endpoints.`
 
 3. **Assess API and input security**
    - **Goal:** Uncover high-impact API and injection vulnerabilities.
    - **Skills:** [`@api-security-best-practices`](../../skills/api-security-best-practices/), [`@api-fuzzing-bug-bounty`](../../skills/api-fuzzing-bug-bounty/), [`@top-web-vulnerabilities`](../../skills/top-web-vulnerabilities/)
-   - **Prompt example:** `Usa @api-security-best-practices per audit endpoint auth, billing e admin.`
+   - **Prompt example:** `Use @api-security-best-practices to audit auth, billing, and admin endpoints.`
 
 4. **Harden and verify**
    - **Goal:** Convert findings into fixes and verify evidence of mitigation.
    - **Skills:** [`@security-auditor`](../../skills/security-auditor/), [`@sast-configuration`](../../skills/sast-configuration/), [`@verification-before-completion`](../../skills/verification-before-completion/)
-   - **Prompt example:** `Usa @verification-before-completion per provare che le mitigazioni sono effettive.`
+   - **Prompt example:** `Use @verification-before-completion to prove that the mitigations are effective.`
 
 ---
 
@@ -119,22 +119,22 @@ Design and deliver a production-grade agent with measurable reliability.
 1. **Define target behavior and KPIs**
    - **Goal:** Set quality, latency, and failure thresholds.
    - **Skills:** [`@ai-agents-architect`](../../skills/ai-agents-architect/), [`@agent-evaluation`](../../skills/agent-evaluation/), [`@product-manager-toolkit`](../../skills/product-manager-toolkit/)
-   - **Prompt example:** `Usa @agent-evaluation per definire benchmark e criteri di successo del mio agente.`
+   - **Prompt example:** `Use @agent-evaluation to define benchmarks and success criteria for my agent.`
 
 2. **Design retrieval and memory**
    - **Goal:** Build reliable retrieval and context architecture.
    - **Skills:** [`@llm-app-patterns`](../../skills/llm-app-patterns/), [`@rag-implementation`](../../skills/rag-implementation/), [`@vector-database-engineer`](../../skills/vector-database-engineer/)
-   - **Prompt example:** `Usa @rag-implementation per progettare pipeline di chunking, embedding e retrieval.`
+   - **Prompt example:** `Use @rag-implementation to design chunking, embedding, and retrieval pipelines.`
 
 3. **Implement orchestration**
    - **Goal:** Implement deterministic orchestration and tool boundaries.
    - **Skills:** [`@langgraph`](../../skills/langgraph/), [`@mcp-builder`](../../skills/mcp-builder/), [`@workflow-automation`](../../skills/workflow-automation/)
-   - **Prompt example:** `Usa @langgraph per implementare il grafo agente con fallback e human-in-the-loop.`
+   - **Prompt example:** `Use @langgraph to implement the agent graph with fallbacks and human-in-the-loop flows.`
 
 4. **Evaluate and iterate**
    - **Goal:** Improve weak points with a structured loop.
    - **Skills:** [`@agent-evaluation`](../../skills/agent-evaluation/), [`@langfuse`](../../skills/langfuse/), [`@kaizen`](../../skills/kaizen/)
-   - **Prompt example:** `Usa @kaizen per prioritizzare le correzioni sulle failure modes rilevate dai test.`
+   - **Prompt example:** `Use @kaizen to prioritize fixes for the failure modes identified by testing.`
 
 ---
 
@@ -155,17 +155,17 @@ Create resilient browser automation with deterministic execution in CI.
 1. **Prepare test strategy**
    - **Goal:** Scope journeys, fixtures, and execution environments.
    - **Skills:** [`@e2e-testing-patterns`](../../skills/e2e-testing-patterns/), [`@test-driven-development`](../../skills/test-driven-development/)
-   - **Prompt example:** `Usa @e2e-testing-patterns per definire suite E2E minima ma ad alto impatto.`
+   - **Prompt example:** `Use @e2e-testing-patterns to define a minimal but high-impact E2E suite.`
 
 2. **Implement browser tests**
    - **Goal:** Build robust test coverage with stable selectors.
    - **Skills:** [`@browser-automation`](../../skills/browser-automation/), `@go-playwright` (optional, Go stack)
-   - **Prompt example:** `Usa @go-playwright per implementare browser automation in un progetto Go.`
+   - **Prompt example:** `Use @go-playwright to implement browser automation in a Go project.`
 
 3. **Triage and harden**
    - **Goal:** Remove flaky behavior and enforce repeatability.
    - **Skills:** [`@systematic-debugging`](../../skills/systematic-debugging/), [`@test-fixing`](../../skills/test-fixing/), [`@verification-before-completion`](../../skills/verification-before-completion/)
-   - **Prompt example:** `Usa @systematic-debugging per classificare e risolvere le flakiness in CI.`
+   - **Prompt example:** `Use @systematic-debugging to classify and resolve flaky behavior in CI.`
 
 ---
 

package/bundled-skills/docs/vietnamese/README.vi.md

@@ -132,13 +132,12 @@ Bộ sưu tập này sẽ không thể hình thành nếu không có công việ
 - **[zebbern/claude-code-guide](https://github.com/zebbern/claude-code-guide)**: Bộ công cụ bảo mật toàn diện & Hướng dẫn (Nguồn cho khoảng 60 kỹ năng mới).
 - **[alirezarezvani/claude-skills](https://github.com/alirezarezvani/claude-skills)**: Bộ công cụ Kỹ sư cao cấp và PM.
 - **[karanb192/awesome-claude-skills](https://github.com/karanb192/awesome-claude-skills)**: Một danh sách khổng lồ các kỹ năng đã được xác thực cho Claude Code.
-- **[zircote/.claude](https://github.com/zircote/.claude)**: Tham chiếu kỹ năng phát triển cho Shopify.
-- **[vibeforge1111/vibeship-spawner-skills](https://github.com/vibeforge1111/vibeship-spawner-skills)**: Trợ lý AI, Tích hợp, Công cụ của nhà sáng tạo (57 kỹ năng, Apache 2.0).
+- **[zircote/.claude](https://github.com/zircote/.claude)**: Kho cấu hình/dotfiles Claude Code đã được lưu trữ, có tham chiếu kỹ năng phát triển Shopify.
+- **[vibeforge1111/vibeship-spawner-skills](https://github.com/vibeforge1111/vibeship-spawner-skills)**: Bộ kỹ năng quy mô lớn cho AI agent, tích hợp, maker tools và nhiều lĩnh vực khác.
 - **[coreyhaines31/marketingskills](https://github.com/coreyhaines31/marketingskills)**: Các kỹ năng Marketing cho CRO, copywriting, SEO, quảng cáo trả phí và tăng trưởng (23 kỹ năng, MIT).
 - **[vudovn/antigravity-kit](https://github.com/vudovn/antigravity-kit)**: Các mẫu AI Agent với Kỹ năng, Agents và Quy trình làm việc (33 kỹ năng, MIT).
-- **[affaan-m/everything-claude-code](https://github.com/affaan-m/everything-claude-code)**: Bộ sưu tập cấu hình Claude Code đầy đủ từ người chiến thắng cuộc thi hackathon của Anthropic - chỉ phần kỹ năng (8 kỹ năng, MIT).
+- **[affaan-m/everything-claude-code](https://github.com/affaan-m/everything-claude-code)**: Bộ sưu tập lớn về cấu hình và quy trình làm việc cho Claude Code từ người chiến thắng hackathon của Anthropic (MIT).
 - **[webzler/agentMemory](https://github.com/webzler/agentMemory)**: Nguồn cho kỹ năng agent-memory-mcp.
-- **[sstklen/claude-api-cost-optimization](https://github.com/sstklen/claude-api-cost-optimization)**: Tiết kiệm 50-90% chi phí Claude API với các chiến lược tối ưu hóa thông minh (MIT).
 
 ### Nguồn cảm hứng
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-skills-antigravity",
-  "version": "1.0.68",
+  "version": "1.0.70",
   "description": "OpenCode CLI plugin that automatically downloads and keeps Antigravity Awesome Skills up to date.",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",