← all publishers

Bruno-Cunha-Souza

@bruno-cunha-souza source repo

Report this profile Claim this profile

• 22 skills
• 0 followers
• 16 hours ago last updated

1. ▌
   Obsidian Markdown · bruno-cunha-souza bundle

   Create/edit Obsidian Flavored Markdown — wikilinks, embeds, callouts, properties, tags, frontmatter. For .md files in Obsidian.
   0
   installs
2. ▌
   Caveman · bruno-cunha-souza bundle

   Terse posture — drop articles/filler/pleasantries/hedging. Keep technical substance, code blocks, errors exact. Mirrors user's language; never announces itself. Not for onboarding, pedagogy, security warnings. Triggers: 'caveman mode', 'modo caveman', 'be terse', '/caveman lite|full|ultra'.
   0
   installs
3. ▌
   Ponytail · bruno-cunha-souza bundle

   Lazy-senior-dev posture for code output — before writing, climb the ladder: YAGNI → reuse what's in the codebase → stdlib → native platform → installed dep → one line → minimum that works. Never cuts validation, error handling, security, or accessibility. Governs what you build, not how you talk. Intensity levels: lite / full / ultra. Use on ANY coding task (writing, refactoring, fixing, designing, choosing dependencies), or when the user says 'ponytail', 'be lazy', 'yagni', 'simplest solution', 'do less', 'menos código', 'simplifica', or complains about over-engineering, bloat, or unnecessary dependencies. Not for non-coding requests (prose, translation, summaries).
   0
   installs
4. ▌
   Only Plan · bruno-cunha-souza bundle

   Read-only planning: analyze and design without changing project files. Writes one step-by-step plan at project root (default IMPLEMENTATION_PLAN.md). Composable with other skills (e.g. /code-security-review /only-plan). Triggers: /only-plan, 'only plan', 'apenas planejar', 'não altere os arquivos'.
   0
   installs
5. ▌
   Clean Code · bruno-cunha-souza bundle

   Clean code lifecycle for Go/Rust/TypeScript/Bun/Python — writing, reviewing, refactoring. Naming, functions, DRY, code smells, duplication (literal/logical/structural), dead-code removal with false-positive guardrails, safe refactoring. Triggers: 'clean code', 'código limpo', 'refactor', 'refatorar', 'remove duplication', 'remover duplicação', 'dead code', 'código morto', 'code smells', '/clean-code'.
   0
   installs
6. ▌
   Code Review · bruno-cunha-souza bundle

   Lifecycle code review Go/Rust/TS/Python. Auto-detects toolchain, runs static analysis, emits severity-ranked findings + file:line evidence, diffs, risk tags (SAFE/REVIEW/BREAKING). Covers OWASP Top 10, perf anti-patterns, test quality. Read-only — every finding cites file:line. Triggers: 'review code', 'revisar código', 'auditar código', '/code-review'.
   0
   installs
7. ▌
   MCP Builder · bruno-cunha-souza bundle

   Build MCP servers — research, implement, test, evaluate. Rust (rmcp, default), TypeScript, or Python. Tool design, strict schemas, pagination, actionable errors, spec 2026-07-28 transports, plus a 10-question evaluation that scores the result. Triggers: 'criar servidor MCP', 'expor essa API como MCP', 'build an MCP server', 'wrap this API as MCP tools', '/mcp-builder'. Not for configuring existing MCP servers.
   0
   installs
8. ▌
   Superpowers · bruno-cunha-souza bundle

   Disciplined plan-first posture — 1% skill scan, instruction hierarchy, 12 rationalizations refused, 4 pillars (TDD, systematic, simplicity, evidence), 7-stage workflow. Default OFF. Triggers: 'superpowers mode', 'modo superpowers', '/superpowers'.
   0
   installs
9. ▌
   Obsidian CLI · bruno-cunha-souza

   Obsidian CLI — read/create/search notes, properties, tasks; plugin dev (reload, JS eval, screenshot, DOM).
   0
   installs
10. ▌
    Code Debugger · bruno-cunha-souza bundle

    Lifecycle debug Go/Rust/TS/Python — symptom→reproduction→root cause→fix→regression test. Evidence-first (cites cmd output or stack frame). For runtime errors, test failures, panics, races, leaks, flaky tests. Triggers: 'debug', 'depurar', 'root cause', '/code-debugger'.
    0
    installs
11. ▌
    Github Commit · bruno-cunha-souza bundle

    Generate Conventional Commit from staged diff. Triggers: 'commit', 'create commit', 'commit message'.
    0
    installs
12. ▌
    Skill Creator · bruno-cunha-souza bundle

    Scaffold new ValarMindSkills per project conventions. Builds SKILL.md, references/, EXAMPLE files. Triggers: 'criar skill', 'nova skill', 'scaffold skill', 'create skill'.
    0
    installs
13. ▌
    Obsidian Bases · bruno-cunha-souza bundle

    Create/edit Obsidian .base files — views, filters, formulas, summaries.
    0
    installs
14. ▌
    Obsidian Brain · bruno-cunha-souza bundle

    Project memory in Obsidian vault — brain/<slug>-brain.md index + atomic sessions/topics/decisions. Auto-activates when CLAUDE.md/AGENTS.md refs vault.
    0
    installs
15. ▌
    CI CD Generator · bruno-cunha-souza bundle

    Scaffold/audit GitHub Actions CI/CD — Go/Rust/TS/Python (FastAPI/Django/Flask). Generation: workflows + coverage gates (60–80%), security scans (CodeQL/Semgrep/bandit, SCA, SBOM, gitleaks), N+1/race/leak/load tests + free-threaded 3.14t. Audit: severity-ranked findings + diff fixes. Triggers: 'criar CI', 'gerar pipeline', 'auditar pipeline', '/ci-cd-generator'.
    0
    installs
16. ▌
    Ponytail Review · bruno-cunha-souza

    Over-engineering review — finds what to DELETE, not what to fix. One line per finding with tags delete/stdlib/native/yagni/shrink and a net-lines score. Three scopes: current diff (default), whole repo ('repo'/'audit'), or 'debt' to harvest ponytail: comments into a ledger. Complements correctness review (@code-review, @github-pr-review) — this lens only hunts complexity. Use when the user says 'review for over-engineering', 'what can we delete', 'is this over-engineered', 'find bloat', 'audit for bloat', 'ponytail debt', 'list the shortcuts', '/ponytail-review'. One-shot report; applies nothing.
    0
    installs
17. ▌
    Github Pr Review · bruno-cunha-souza bundle

    Structured GitHub PR review — correctness, security, performance, maintainability. Severity-ranked findings + verdict (Approve/Request Changes/Comment). Non-PR: @code-review. Triggers: 'review PR', 'revisar PR', 'analisar pull request', '/github-pr-review'.
    0
    installs
18. ▌
    Code Optimization · bruno-cunha-souza bundle

    Lifecycle perf audit Go/Rust/TS/Python. N+1/leak/duplication sweeps, tri-axis Impact×Risk×Effort, writes OPTIMIZATION_REPORT.md. Read-only — file:line evidence. Triggers: 'optimize code', 'otimizar código', 'auditar performance', 'find bottlenecks', '/code-optimization'.
    0
    installs
19. ▌
    Prompt Engineering · bruno-cunha-souza bundle

    Lifecycle LLM prompt audit/harden/rewrite. Targets SKILL.md, RAG, tool descriptions, system prompts. Emits findings (SAFE/REVIEW/BREAKING) + rewrite + token delta. Read-only — LGTM if sound. Triggers: 'audit prompt', 'auditar prompt', 'engenharia de prompt', '/prompt-engineering'.
    0
    installs
20. ▌
    Github Release Note · bruno-cunha-souza bundle

    Generate GitHub Release notes / changelog from tag range. Triggers: 'release notes', 'changelog', 'version notes'.
    0
    installs
21. ▌
    Code Security Review · bruno-cunha-souza bundle

    Web/API security lifecycle for Go, Next.js, Python, and Bun — design controls, active testing, supply-chain/CI-CD, and LLM/agentic/MCP coverage. Maps to OWASP Web Top 10 2025 + API 2023 + LLM 2025 + Agentic 2026. Triggers: 'security review', 'revisão de segurança', 'auditar segurança', 'pentest', '/code-security-review'.
    0
    installs
22. ▌
    Context Optimization · bruno-cunha-souza bundle

    Lifecycle context audit/optimize/plan. Audit mode (Phase 0..6) + Guide mode (catalog lookup). Targets long-conv agents, RAG pipelines, sub-agents, large-doc workflows. Detects bloat/dedup/cache/masking/partition opportunities. Emits findings (SAFE/REVIEW/BREAKING) + optimization plan + token delta. Read-only — LGTM if sound. Triggers: 'optimize context', 'compact context', 'auditar contexto', 'otimizar contexto', '/context-optimization'.
    0
    installs