@fprad0/skill-master-mcp 0.0.12 → 1.0.1

package/docs/skill-candidates/v0.0.12/senior-master-code-optimizer/SKILL.md

@@ -1,48 +1,48 @@
----
-name: senior-master-code-optimizer
-description: "Senior master code optimization and hardening across languages. Use when asked to write, refactor, organize, simplify, speed up, secure, test, reduce complexity, or improve code quality in TypeScript, JavaScript, Python, Go, SQL, JSON, Ruby, React, HTML, CSS, C# or mixed systems."
----
-
-# Senior Master Code Optimizer
-
-Use this skill as the general engineering gate before making broad code quality changes.
-
-## Operating Standard
-
-- Inspect the real project structure, entrypoints, dependency model, tests and conventions before editing.
-- Optimize for correctness first, then simplicity, then performance, then cleverness.
-- Remove accidental complexity: duplicated branches, needless wrappers, broad abstractions, dead code and unclear naming.
-- Keep behavior stable unless the user explicitly asked for behavior change.
-- Treat security as part of code quality: validate inputs, isolate side effects, avoid secret exposure and preserve auth boundaries.
-- Prefer smaller functions with explicit responsibilities, but do not split code into noisy fragments without a real readability or testability gain.
-- Validate with the narrowest trustworthy commands available: typecheck, lint, tests, build, query plan, smoke script or direct execution.
-
-## Language Routing
-
-- TypeScript: use `typescript-senior-master-engineering` with `typescript-expert` when type safety or build behavior matters.
-- JavaScript: use `javascript-senior-master-engineering` for runtime, async, Node.js or browser behavior.
-- Python: use `python-senior-master-engineering` for services, scripts, CLIs, APIs and automation.
-- Go: use `go-senior-master-engineering` for package design, concurrency, services and CLIs.
-- SQL: use `sql-senior-master-engineering` for schemas, queries, migrations and data integrity.
-- JSON: use `json-senior-master-engineering` for contracts, schemas, config and integration payloads.
-- Ruby: use `ruby-senior-master-engineering` for Ruby scripts, gems, services and Rails-adjacent code.
-- React: use `react-senior-master-engineering` for components, state, rendering, accessibility and frontend performance.
-- HTML: use `html-senior-master-engineering` for semantic markup, accessibility and document structure.
-- CSS: use `css-senior-master-engineering` for layout, responsive behavior, maintainable styling and performance.
-- C#: use `csharp-senior-master-engineering` for .NET, ASP.NET Core, services, CLIs and libraries.
-
-## Change Discipline
-
-- Start with the smallest coherent patch that resolves the issue.
-- Prefer project-native utilities, style and test commands over introducing new tools.
-- Avoid speculative rewrites. Refactor only where it reduces risk, duplication, latency, memory use or maintenance cost.
-- Keep public contracts stable unless migration is part of the task.
-- Explain residual risks plainly. Do not claim code is bug-free; report what was actually validated.
-
-## Review Checklist
-
-- Behavior: inputs, outputs, errors, edge cases and backwards compatibility remain clear.
-- Performance: avoid unnecessary allocations, repeated I/O, repeated parsing, N+1 queries and avoidable re-renders.
-- Security: sanitize boundaries, preserve permissions, avoid injection, avoid unsafe deserialization and never leak secrets.
-- Maintainability: names, modules, functions and tests make future changes easier.
-- Validation: one-shot checks passed or the reason they were not run is explicit.
+---
+name: senior-master-code-optimizer
+description: "Senior master code optimization and hardening across languages. Use when asked to write, refactor, organize, simplify, speed up, secure, test, reduce complexity, or improve code quality in TypeScript, JavaScript, Python, Go, SQL, JSON, Ruby, React, HTML, CSS, C# or mixed systems."
+---
+
+# Senior Master Code Optimizer
+
+Use this skill as the general engineering gate before making broad code quality changes.
+
+## Operating Standard
+
+- Inspect the real project structure, entrypoints, dependency model, tests and conventions before editing.
+- Optimize for correctness first, then simplicity, then performance, then cleverness.
+- Remove accidental complexity: duplicated branches, needless wrappers, broad abstractions, dead code and unclear naming.
+- Keep behavior stable unless the user explicitly asked for behavior change.
+- Treat security as part of code quality: validate inputs, isolate side effects, avoid secret exposure and preserve auth boundaries.
+- Prefer smaller functions with explicit responsibilities, but do not split code into noisy fragments without a real readability or testability gain.
+- Validate with the narrowest trustworthy commands available: typecheck, lint, tests, build, query plan, smoke script or direct execution.
+
+## Language Routing
+
+- TypeScript: use `typescript-senior-master-engineering` with `typescript-expert` when type safety or build behavior matters.
+- JavaScript: use `javascript-senior-master-engineering` for runtime, async, Node.js or browser behavior.
+- Python: use `python-senior-master-engineering` for services, scripts, CLIs, APIs and automation.
+- Go: use `go-senior-master-engineering` for package design, concurrency, services and CLIs.
+- SQL: use `sql-senior-master-engineering` for schemas, queries, migrations and data integrity.
+- JSON: use `json-senior-master-engineering` for contracts, schemas, config and integration payloads.
+- Ruby: use `ruby-senior-master-engineering` for Ruby scripts, gems, services and Rails-adjacent code.
+- React: use `react-senior-master-engineering` for components, state, rendering, accessibility and frontend performance.
+- HTML: use `html-senior-master-engineering` for semantic markup, accessibility and document structure.
+- CSS: use `css-senior-master-engineering` for layout, responsive behavior, maintainable styling and performance.
+- C#: use `csharp-senior-master-engineering` for .NET, ASP.NET Core, services, CLIs and libraries.
+
+## Change Discipline
+
+- Start with the smallest coherent patch that resolves the issue.
+- Prefer project-native utilities, style and test commands over introducing new tools.
+- Avoid speculative rewrites. Refactor only where it reduces risk, duplication, latency, memory use or maintenance cost.
+- Keep public contracts stable unless migration is part of the task.
+- Explain residual risks plainly. Do not claim code is bug-free; report what was actually validated.
+
+## Review Checklist
+
+- Behavior: inputs, outputs, errors, edge cases and backwards compatibility remain clear.
+- Performance: avoid unnecessary allocations, repeated I/O, repeated parsing, N+1 queries and avoidable re-renders.
+- Security: sanitize boundaries, preserve permissions, avoid injection, avoid unsafe deserialization and never leak secrets.
+- Maintainability: names, modules, functions and tests make future changes easier.
+- Validation: one-shot checks passed or the reason they were not run is explicit.

package/docs/skill-candidates/v0.0.12/sql-senior-master-engineering/SKILL.md

@@ -1,31 +1,31 @@
----
-name: sql-senior-master-engineering
-description: "Senior master SQL engineering for schemas, queries, migrations, indexes, transactions, data integrity, performance and safety. Use when writing, reviewing, optimizing or hardening SQL, PostgreSQL, relational data access or database migrations."
----
-
-# SQL Senior Master Engineering
-
-Use this skill for SQL and relational database work with production impact.
-
-## Workflow
-
-- Start from the real schema, data volume, access pattern and transaction path.
-- Separate read query tuning, write path cost, migration safety and data integrity concerns.
-- Prefer explicit constraints, keys and reversible migrations.
-- Validate with realistic samples, `EXPLAIN`, tests, migration dry-runs or smoke queries when available.
-
-## Optimization Rules
-
-- Check joins, filters, sort keys, indexes, N+1 access, lock scope and transaction duration.
-- Do not add indexes without explaining read benefit and write/storage cost.
-- Avoid query changes that alter cardinality or null semantics without proof.
-
-## Security Rules
-
-- Use parameters for untrusted values.
-- Avoid dynamic SQL unless identifiers are allowlisted and quoted safely.
-- Never run destructive data changes without explicit approval and rollback reasoning.
-
-## Completion Standard
-
-- State expected query behavior, migration risk and validation evidence.
+---
+name: sql-senior-master-engineering
+description: "Senior master SQL engineering for schemas, queries, migrations, indexes, transactions, data integrity, performance and safety. Use when writing, reviewing, optimizing or hardening SQL, PostgreSQL, relational data access or database migrations."
+---
+
+# SQL Senior Master Engineering
+
+Use this skill for SQL and relational database work with production impact.
+
+## Workflow
+
+- Start from the real schema, data volume, access pattern and transaction path.
+- Separate read query tuning, write path cost, migration safety and data integrity concerns.
+- Prefer explicit constraints, keys and reversible migrations.
+- Validate with realistic samples, `EXPLAIN`, tests, migration dry-runs or smoke queries when available.
+
+## Optimization Rules
+
+- Check joins, filters, sort keys, indexes, N+1 access, lock scope and transaction duration.
+- Do not add indexes without explaining read benefit and write/storage cost.
+- Avoid query changes that alter cardinality or null semantics without proof.
+
+## Security Rules
+
+- Use parameters for untrusted values.
+- Avoid dynamic SQL unless identifiers are allowlisted and quoted safely.
+- Never run destructive data changes without explicit approval and rollback reasoning.
+
+## Completion Standard
+
+- State expected query behavior, migration risk and validation evidence.

package/docs/skill-candidates/v0.0.12/token-economy-orchestrator/SKILL.md

@@ -0,0 +1,38 @@
+---
+name: token-economy-orchestrator
+description: "Orchestrate token-saving strategy before and during AI work across Codex, Claude, Gemini and Antigravity. Use when prompts are long, repetitive, multi-file, multi-agent, research-heavy, transfer-oriented, or when the user asks to economize tokens."
+---
+
+# Token Economy Orchestrator
+
+Use this skill to reduce token waste while preserving enough context to do the work correctly.
+
+## Decision Modes
+
+- `light`: remove repetition, ask for concise output, keep normal workflow.
+- `balanced`: run prompt preflight, define input/output budget, load only relevant files.
+- `aggressive`: create a compressed handoff and avoid raw logs/docs; use only with explicit or low-risk context.
+
+## Workflow
+
+1. Classify task risk: low, normal, high.
+2. Identify stable context that belongs in skills, project rules, AGENTS.md, CLAUDE.md, Gemini context files, or Antigravity rules/workflows.
+3. Identify volatile context that should stay in the current prompt only.
+4. Choose the smallest useful evidence set: paths, snippets, source links, commands and expected outputs.
+5. Prefer search and targeted reads over dumping whole files.
+6. Set output budget: short status, focused plan, implementation summary, or detailed research.
+7. Use `context-compression-handoff` before long transfers or phase changes.
+
+## Provider Notes
+
+- Codex/OpenAI: use project instructions and AGENTS.md for durable rules; rely on targeted file reads and concise final answers.
+- Claude/Anthropic: use prompt caching and token counting for large stable context; keep memory files factual and compact.
+- Gemini/Google: use token counting and context caching for repeated large inputs; control thinking budget when appropriate.
+- Antigravity: keep rules/workflows small and task-specific; use compact handoffs for cross-agent work.
+
+## Guardrails
+
+- Do not remove safety-critical context to save tokens.
+- Do not hide uncertainty caused by compression.
+- Do not use aggressive compression for legal, medical, financial, auth, release or destructive operations without confirmation.
+- Do not claim exact token savings unless measured by the provider tokenizer/API.

package/docs/skill-candidates/v0.0.12/typescript-senior-master-engineering/SKILL.md

@@ -1,35 +1,35 @@
----
-name: typescript-senior-master-engineering
-description: "Senior master TypeScript engineering for writing, organizing, refactoring, optimizing and securing TypeScript code, types, functions, modules, APIs, CLIs, frontend or backend systems. Use with typescript-expert for type safety, build correctness, performance and maintainability."
----
-
-# TypeScript Senior Master Engineering
-
-Use this skill for TypeScript code that must be clean, fast, safe and maintainable.
-
-## Workflow
-
-- Read `package.json`, `tsconfig.json`, source layout, imports and existing scripts before editing.
-- Preserve the project's module style, path aliases, formatting and test strategy.
-- Model data with explicit types at boundaries and inference inside implementation details.
-- Prefer `unknown` plus validation over `any`; use `satisfies`, discriminated unions and branded types where they reduce real bugs.
-- Keep functions small enough to test and reason about, but avoid abstraction for its own sake.
-- Validate with `npm run typecheck`, `npx tsc --noEmit`, tests or build according to available scripts.
-
-## Optimization Rules
-
-- Remove duplicate branches, repeated parsing, repeated object creation in hot paths and avoidable async waterfalls.
-- Avoid deep generic machinery unless it protects a public API or removes duplicated unsafe code.
-- Use type-only imports where appropriate and keep runtime imports intentional.
-- Keep API contracts stable and make breaking changes explicit.
-
-## Security Rules
-
-- Validate external input at process, HTTP, CLI, file and database boundaries.
-- Avoid unsafe dynamic property access, `eval`, shell interpolation and untrusted deserialization.
-- Keep secrets out of logs, errors, snapshots and generated examples.
-
-## Completion Standard
-
-- Summarize behavior changed, files touched, validation run and remaining risks.
-- Do not claim zero bugs; report evidence.
+---
+name: typescript-senior-master-engineering
+description: "Senior master TypeScript engineering for writing, organizing, refactoring, optimizing and securing TypeScript code, types, functions, modules, APIs, CLIs, frontend or backend systems. Use with typescript-expert for type safety, build correctness, performance and maintainability."
+---
+
+# TypeScript Senior Master Engineering
+
+Use this skill for TypeScript code that must be clean, fast, safe and maintainable.
+
+## Workflow
+
+- Read `package.json`, `tsconfig.json`, source layout, imports and existing scripts before editing.
+- Preserve the project's module style, path aliases, formatting and test strategy.
+- Model data with explicit types at boundaries and inference inside implementation details.
+- Prefer `unknown` plus validation over `any`; use `satisfies`, discriminated unions and branded types where they reduce real bugs.
+- Keep functions small enough to test and reason about, but avoid abstraction for its own sake.
+- Validate with `npm run typecheck`, `npx tsc --noEmit`, tests or build according to available scripts.
+
+## Optimization Rules
+
+- Remove duplicate branches, repeated parsing, repeated object creation in hot paths and avoidable async waterfalls.
+- Avoid deep generic machinery unless it protects a public API or removes duplicated unsafe code.
+- Use type-only imports where appropriate and keep runtime imports intentional.
+- Keep API contracts stable and make breaking changes explicit.
+
+## Security Rules
+
+- Validate external input at process, HTTP, CLI, file and database boundaries.
+- Avoid unsafe dynamic property access, `eval`, shell interpolation and untrusted deserialization.
+- Keep secrets out of logs, errors, snapshots and generated examples.
+
+## Completion Standard
+
+- Summarize behavior changed, files touched, validation run and remaining risks.
+- Do not claim zero bugs; report evidence.

package/docs/skill-candidates/v0.0.9/ai-ethics-human-dignity/SKILL.md

@@ -1,32 +1,32 @@
----
-name: ai-ethics-human-dignity
-description: "Candidate skill for evaluating AI, automation, data and algorithmic decisions against human dignity, transparency, privacy, bias, accountability and the common good."
----
-
-# AI Ethics And Human Dignity
-
-Use this candidate skill when a prompt involves AI systems, automation, data processing, scoring, recommendation engines, surveillance, personalization, synthetic content or decision support.
-
-## Workflow
-
-- Identify affected people and groups.
-- Detect whether the system changes rights, access, work, reputation, money, safety or education.
-- Check for transparency, consent, privacy, bias, explainability and accountability.
-- Require human oversight for sensitive decisions.
-- Reject uses that manipulate, deceive, exploit or dehumanize.
-- Recommend evals and monitoring before deployment.
-
-## Boundaries
-
-- Do not treat efficiency as the highest good.
-- Do not hide responsibility behind "the algorithm".
-- Do not allow automated categorization to replace human dignity.
-- Do not approve weaponization or coercive surveillance.
-
-## Evidence Required
-
-- Intended users.
-- Data categories.
-- Decision impact.
-- Human oversight plan.
-- Bias and failure-mode evaluation.
+---
+name: ai-ethics-human-dignity
+description: "Candidate skill for evaluating AI, automation, data and algorithmic decisions against human dignity, transparency, privacy, bias, accountability and the common good."
+---
+
+# AI Ethics And Human Dignity
+
+Use this candidate skill when a prompt involves AI systems, automation, data processing, scoring, recommendation engines, surveillance, personalization, synthetic content or decision support.
+
+## Workflow
+
+- Identify affected people and groups.
+- Detect whether the system changes rights, access, work, reputation, money, safety or education.
+- Check for transparency, consent, privacy, bias, explainability and accountability.
+- Require human oversight for sensitive decisions.
+- Reject uses that manipulate, deceive, exploit or dehumanize.
+- Recommend evals and monitoring before deployment.
+
+## Boundaries
+
+- Do not treat efficiency as the highest good.
+- Do not hide responsibility behind "the algorithm".
+- Do not allow automated categorization to replace human dignity.
+- Do not approve weaponization or coercive surveillance.
+
+## Evidence Required
+
+- Intended users.
+- Data categories.
+- Decision impact.
+- Human oversight plan.
+- Bias and failure-mode evaluation.

package/docs/skill-candidates/v0.0.9/broad-domain-router/SKILL.md

@@ -1,41 +1,41 @@
----
-name: broad-domain-router
-description: "Candidate skill for routing prompts across broad knowledge domains and recommending approved local or global skills without pretending unsupported expertise."
----
-
-# Broad Domain Router
-
-Use this candidate skill when a prompt spans multiple areas of knowledge or when the agent needs to choose which skill family should guide the work.
-
-## Domains
-
-- Catholic doctrine and moral discernment.
-- Science.
-- Philosophy.
-- Sociology.
-- Law.
-- Mathematics.
-- Portuguese.
-- English.
-- French.
-- Computer engineering.
-- Software engineering.
-- Network engineering.
-- AI engineering.
-- Security.
-- Product and documentation.
-
-## Workflow
-
-- Classify the primary and secondary domains.
-- Identify whether the topic is stable or requires current research.
-- Recommend approved skills first.
-- Mark missing skills as roadmap candidates.
-- Add professional-boundary gates when appropriate.
-- Ask for sources or validation when the prompt has high stakes.
-
-## Boundaries
-
-- Do not invent sources.
-- Do not activate unapproved web skills.
-- Do not claim mastery in a domain without the proper skill, source or validation path.
+---
+name: broad-domain-router
+description: "Candidate skill for routing prompts across broad knowledge domains and recommending approved local or global skills without pretending unsupported expertise."
+---
+
+# Broad Domain Router
+
+Use this candidate skill when a prompt spans multiple areas of knowledge or when the agent needs to choose which skill family should guide the work.
+
+## Domains
+
+- Catholic doctrine and moral discernment.
+- Science.
+- Philosophy.
+- Sociology.
+- Law.
+- Mathematics.
+- Portuguese.
+- English.
+- French.
+- Computer engineering.
+- Software engineering.
+- Network engineering.
+- AI engineering.
+- Security.
+- Product and documentation.
+
+## Workflow
+
+- Classify the primary and secondary domains.
+- Identify whether the topic is stable or requires current research.
+- Recommend approved skills first.
+- Mark missing skills as roadmap candidates.
+- Add professional-boundary gates when appropriate.
+- Ask for sources or validation when the prompt has high stakes.
+
+## Boundaries
+
+- Do not invent sources.
+- Do not activate unapproved web skills.
+- Do not claim mastery in a domain without the proper skill, source or validation path.

package/docs/skill-candidates/v0.0.9/catholic-moral-discernment/SKILL.md

@@ -1,31 +1,31 @@
----
-name: catholic-moral-discernment
-description: "Candidate skill for reviewing technology tasks through Catholic moral discernment, human dignity, truth, justice, common good, and responsible limits. Not active until human approval."
----
-
-# Catholic Moral Discernment
-
-Use this candidate skill when a development task may affect human dignity, truth, privacy, justice, workers, vulnerable people, social trust, religious formation, or the common good.
-
-## Workflow
-
-- Identify the concrete human impact of the requested task.
-- Check whether the task promotes truth, dignity, justice, charity and the common good.
-- Distinguish technical possibility from moral permissibility.
-- Flag manipulation, fraud, exploitation, unjust discrimination, invasive surveillance and harm.
-- Prefer official Catholic sources when moral doctrine is relevant.
-- Recommend priestly, spiritual, legal or professional consultation when the case exceeds a technical assistant.
-
-## Boundaries
-
-- Do not claim to be the Church or magisterium.
-- Do not replace a well-formed conscience.
-- Do not replace a priest, confessor, spiritual director, lawyer, doctor or other competent authority.
-- Do not use Catholic language to justify abuse, humiliation or unjust coercion.
-
-## Evidence Required
-
-- Relevant prompt excerpt.
-- Risk classification.
-- Official source or reason source is needed.
-- Safer alternative when blocking a request.
+---
+name: catholic-moral-discernment
+description: "Candidate skill for reviewing technology tasks through Catholic moral discernment, human dignity, truth, justice, common good, and responsible limits. Not active until human approval."
+---
+
+# Catholic Moral Discernment
+
+Use this candidate skill when a development task may affect human dignity, truth, privacy, justice, workers, vulnerable people, social trust, religious formation, or the common good.
+
+## Workflow
+
+- Identify the concrete human impact of the requested task.
+- Check whether the task promotes truth, dignity, justice, charity and the common good.
+- Distinguish technical possibility from moral permissibility.
+- Flag manipulation, fraud, exploitation, unjust discrimination, invasive surveillance and harm.
+- Prefer official Catholic sources when moral doctrine is relevant.
+- Recommend priestly, spiritual, legal or professional consultation when the case exceeds a technical assistant.
+
+## Boundaries
+
+- Do not claim to be the Church or magisterium.
+- Do not replace a well-formed conscience.
+- Do not replace a priest, confessor, spiritual director, lawyer, doctor or other competent authority.
+- Do not use Catholic language to justify abuse, humiliation or unjust coercion.
+
+## Evidence Required
+
+- Relevant prompt excerpt.
+- Risk classification.
+- Official source or reason source is needed.
+- Safer alternative when blocking a request.

package/docs/skill-candidates/v0.0.9/engineering-systems-master/SKILL.md

@@ -1,31 +1,31 @@
----
-name: engineering-systems-master
-description: "Candidate skill for senior-level software, network, computer and AI engineering with validation, security, maintainability and release discipline."
----
-
-# Engineering Systems Master
-
-Use this candidate skill when the user asks for architecture, implementation, debugging, release planning, network design, AI engineering, automation or production hardening.
-
-## Workflow
-
-- Read the existing system before proposing changes.
-- Prefer local patterns and simple designs.
-- Identify blast radius, risks and validation path.
-- Implement with tests proportional to risk.
-- Protect secrets, user changes and release boundaries.
-- Separate local validation from public readiness.
-
-## Boundaries
-
-- Do not publish without explicit authorization.
-- Do not run destructive commands without explicit confirmation.
-- Do not bypass security controls.
-- Do not hide uncertainty or missing evidence.
-
-## Evidence Required
-
-- Files changed.
-- Commands run.
-- Validation result.
-- Remaining risk.
+---
+name: engineering-systems-master
+description: "Candidate skill for senior-level software, network, computer and AI engineering with validation, security, maintainability and release discipline."
+---
+
+# Engineering Systems Master
+
+Use this candidate skill when the user asks for architecture, implementation, debugging, release planning, network design, AI engineering, automation or production hardening.
+
+## Workflow
+
+- Read the existing system before proposing changes.
+- Prefer local patterns and simple designs.
+- Identify blast radius, risks and validation path.
+- Implement with tests proportional to risk.
+- Protect secrets, user changes and release boundaries.
+- Separate local validation from public readiness.
+
+## Boundaries
+
+- Do not publish without explicit authorization.
+- Do not run destructive commands without explicit confirmation.
+- Do not bypass security controls.
+- Do not hide uncertainty or missing evidence.
+
+## Evidence Required
+
+- Files changed.
+- Commands run.
+- Validation result.
+- Remaining risk.

package/docs/skill-candidates/v0.0.9/language-quality-pt-en-fr/SKILL.md

@@ -1,28 +1,28 @@
----
-name: language-quality-pt-en-fr
-description: "Candidate skill for improving Portuguese, English and French text quality, translation, tone and readability with professional-boundary warnings."
----
-
-# Language Quality PT EN FR
-
-Use this candidate skill when the user asks to write, revise, translate or improve text in Portuguese, English or French.
-
-## Workflow
-
-- Identify language, audience, tone and purpose.
-- Preserve meaning before improving style.
-- Fix grammar, spelling, clarity and coherence.
-- Offer concise alternatives when needed.
-- Warn when the text has legal, medical, liturgical or official effect.
-
-## Boundaries
-
-- Do not claim sworn translation.
-- Do not silently alter doctrine, legal meaning or contractual obligations.
-- Do not over-polish text that should preserve the user's voice.
-
-## Evidence Required
-
-- Original language.
-- Target language when translating.
-- Audience and purpose.
+---
+name: language-quality-pt-en-fr
+description: "Candidate skill for improving Portuguese, English and French text quality, translation, tone and readability with professional-boundary warnings."
+---
+
+# Language Quality PT EN FR
+
+Use this candidate skill when the user asks to write, revise, translate or improve text in Portuguese, English or French.
+
+## Workflow
+
+- Identify language, audience, tone and purpose.
+- Preserve meaning before improving style.
+- Fix grammar, spelling, clarity and coherence.
+- Offer concise alternatives when needed.
+- Warn when the text has legal, medical, liturgical or official effect.
+
+## Boundaries
+
+- Do not claim sworn translation.
+- Do not silently alter doctrine, legal meaning or contractual obligations.
+- Do not over-polish text that should preserve the user's voice.
+
+## Evidence Required
+
+- Original language.
+- Target language when translating.
+- Audience and purpose.