fhgomes

@fhgomes source repo

15 skills
0 followers
8 hours ago last updated

▌
Redact · fhgomes bundle
Privacy and data-exposure specialist for code — a PRE-PUBLICATION audit of repositories that are about to go public (or already are). Hunts leaked secrets and sensitive data: API keys, tokens, passwords, connection strings, private keys, certificates, database credentials, CI secrets, service accounts, internal IPs and hostnames, private endpoints, and personal data — PII (Brazilian CPF/RG/CNPJ IDs, e-mail, phone, address, customer names), PCI (credit card numbers, CVV), PHI (health data) — in the working tree AND in GIT HISTORY, where a leak survives even after the file is deleted. Teaches remediation: move to an environment variable, .env, application.properties, parameter, or secret manager; create .env.example; fix .gitignore; rewrite history; and rotate the exposed credential. ALWAYS use when the user says: "I'm making this repo public", "can I publish this?", "is there a secret in the code?", "did a password leak?", "check whether a key was committed", "audit before publishing", "is this repo safe to op

0 installs
▌
Warden · fhgomes bundle
Offensive-defensive security specialist focused on HUNTING MALICIOUS CONTENT — malware, viruses, trojans, backdoors, webshells, ransomware, cryptominers, stealers, keyloggers, droppers, supply-chain attacks and obfuscated code — inside files, folders, repositories (PoC/proof-of-concept), URLs, websites, executables, installers, scripts, dependencies (npm/pip/maven), Docker images, e-mail attachments and USB drives. ALWAYS use when the user asks: "analyze this file", "is this .exe safe?", "scan this folder", "does this repo/PoC have a virus?", "is this link malicious?", "is this site phishing?", "check this installer", "I downloaded this, is it safe to run?", "is my PC infected?", "what is this weird process?", "analyze this script", "is this npm/pip package trustworthy?", "does this .docx/.pdf have a macro?", "check this hash", "quarantine this", "triage this binary", "static analysis", "sandbox", "reverse engineering", "this code is obfuscated", "IoC", "VirusTotal", "YARA". Also trigger when the user mention

0 installs
▌
Sentinel · fhgomes bundle
Cybersecurity and DevSecOps infrastructure hardening specialist. Use ALWAYS when conversation involves: server security, hardening of nginx/SSH/DNS/firewall, API and endpoint protection, vulnerability or CVE analysis, CVE feed triage and backlog hygiene, secure Docker/container configuration, database protection (PostgreSQL, Redis), Spring Boot / JVM security, SSL/TLS certificates, authentication (Basic Auth, OAuth2, JWT, Keycloak), WAF, rate limiting, anti-DDoS, suspicious log analysis, incident response, ethical penetration testing, Zero Trust, secrets management, DevSecOps pipelines, or any variation of "how to protect X", "is it secure?", "how to harden Y". ALSO INCLUDES AI/LLM/autonomous agent security: prompt injection (direct and indirect), agent jailbreaking, agent hijacking, Ollama security, MCP server/token protection, agent container isolation, execution sandbox, tool permissions, denial of wallet, API key protection, data leakage via AI outputs, OWASP Top 10 for LLMs, AI supply chain, OpenClaw/age

0 installs
▌
Perf Engineer · fhgomes bundle
Performance engineering and review specialist. Use ALWAYS when the conversation involves: slow endpoint, latency, p95/p99, N+1, pagination, index, EXPLAIN, connection pool, HikariCP, cache / TTL / Redis / Caffeine, JVM / GC / heap / OOM, load test / k6 / Gatling / JMeter, Lighthouse, Core Web Vitals / LCP / INP / CLS, bundle size, re-render, TanStack Query caching, jank / frame drop / FPS, Flutter DevTools, app size, "is this performant", "make it faster", "will this scale", reviewing a PR or AI-generated diff for performance, or any claim like "production-ready", "O(1)" or "sub-100 ms" made without a measurement. If in doubt whether the topic is performance, trigger this skill.

0 installs
▌
Test Engineer · fhgomes bundle
Test engineering specialist. Use ALWAYS when conversation involves: writing, adding or fixing tests, "make this testable", coverage, flaky tests, red CI, Playwright / JUnit / Mockito / Testcontainers / MockMvc / vitest / Testing Library / Flutter widget tests, TDD, "is this tested?", "why is CI red", a pre-commit or agent hook that runs tests, mocks and fakes, unit vs integration, test data and teardown, "the AI says done but nothing is tested", or any variation of "how do I test X". Also trigger when user mentions: "spec", "suite", "assertion", "flaky", "green build", "regression test", "characterization test", "smoke test", "E2E", "mock", "stub", "fixture", "teardown", "golden test", "mutation testing", "quality gate", "skip-tests", "@Disabled", "test.skip", "test.only", "single-test command", "known-red baseline". If in doubt whether the task needs a test, trigger.

0 installs
▌
Video Editing · fhgomes bundle
Cut, join, reformat (9:16 Reels/Shorts/TikTok, 1:1 and 4:5 LinkedIn) and burn captions into video with ffmpeg and faster-whisper. Use whenever the user asks to "cut the video", "make a clip", "join the segments", "version for Reels/Shorts/TikTok", "9:16", "blurred background", "burn subtitles", "CapCut-style word-by-word captions", "cold open", extract a segment or a frame, concat clips, or any command-line video editing. Also covers: delivery specs per platform (bitrate, max duration, safe zones, -14 LUFS), choosing WHICH segment becomes a clip (hook/coherence/emotion rubric), 9:16 reframing that follows the speaker (face-pan), the xfade transition catalog and which durations read well, the hook-to-content transition (punch-in + whoosh), color grading and correction (iPhone HLG, cross-source consistency, skin-tone protection) and GPU/NVENC detection at runtime (scripts/gpu_probe.py — NEVER hardcode card parameters). Ships ready scripts (word_captions.py, word_captions_map.py, face_pan.py, gpu_probe.py) — do

0 installs
▌
Obsidian Daily · fhgomes bundle
Manage Obsidian Daily Notes via obsidian-cli. Create and open daily notes, append entries (journals, logs, tasks, links), read past notes by date, and search vault content. Handles relative dates like "yesterday", "last Friday", "3 days ago". Use when you need to write a note, add to daily notes, or interact with Obsidian vault.

0 installs
▌
Config Guardian · fhgomes bundle
Validate and safeguard OpenClaw config updates (openclaw.json or openclaw config set/apply). Use this skill whenever changing gateway config, models, channels, agents, tools, sessions, or routing. Enforces backup, schema validation, and safe rollback before restarts. Use when changing OpenClaw configuration.

0 installs
▌
Harness Engineer · fhgomes bundle
Deeply identify a repository (tech stack, architecture, purpose, patterns, companion projects) and harvest what the team already knows — code patterns, conventions, business rules, war stories — into an AI harness sized to the project. router AGENTS.md, vendor entry files (CLAUDE.md, copilot-instructions, .cursorrules; Codex reads AGENTS.md natively), a docs/ or .ai/ reference folder (tech-info.md, architecture.md, business-context.md, conventions.md, guidelines.md, testing.md, extra-context.md), a versioned constitution.md with Do-Not-Break rules, workflow docs (repository-map, change-workflow, review-checklist...) and focused tech guides (junit-testing-guide.md, spring-backend-guide.md...) with verified commands and golden examples. Identifies the FULL catalog of candidate files, creates only what the repo's size justifies now, records the rest. Use whenever the user asks to create/update AGENTS.md, CLAUDE.md, .cursorrules, or copilot-instructions; to "make this repo AI-ready", "map/identify this project",

0 installs
▌
Media Transcription · fhgomes bundle
Transcribe audio and video into text and subtitles — locally (faster-whisper large-v3 on the GPU) or remotely (youtubetotranscript.com for YouTube videos). Use whenever the user asks to "transcribe", "get the text of this video/audio", "generate subtitles", "SRT", mentions Whisper, or wants the text of a talk, mentoring session, recorded meeting or YouTube video. Also use when comparing transcription quality or when a previous transcript has loops/hallucinations (the same word repeated over and over) — the fix is the large-v3 model. Ships a ready script (scripts/transcribe_gpu.py) — do not rewrite it from scratch. Also triggers on the equivalent phrases in other languages.

0 installs
▌
Openclaw Specialist · fhgomes bundle
Use when maintaining, configuring, diagnosing, or updating an OpenClaw instance — cron jobs, agents, channels, config changes, version upgrades, service restarts, or troubleshooting delivery/exec/channel issues. Also use when reviewing agent instructions or bootstraps for optimization.

0 installs
▌
Harness Engineer 2 · fhgomes bundle
Deeply identify a repository (tech stack, architecture, purpose, patterns, companion projects) and harvest what the team already knows — code patterns, conventions, business rules, war stories — into an AI harness sized to the project. router AGENTS.md, vendor entry files (CLAUDE.md, copilot-instructions, .cursorrules; Codex reads AGENTS.md natively), a docs/ or .ai/ reference folder (tech-info.md, architecture.md, business-context.md, conventions.md, guidelines.md, testing.md, extra-context.md), a versioned constitution.md with Do-Not-Break rules, workflow docs (repository-map, change-workflow, review-checklist...) and focused tech guides (junit-testing-guide.md, spring-backend-guide.md...) with verified commands and golden examples. Identifies the FULL catalog of candidate files, creates only what the repo's size justifies now, records the rest. Use whenever the user asks to create/update AGENTS.md, CLAUDE.md, .cursorrules, or copilot-instructions; to "make this repo AI-ready", "map/identify this project",

0 installs
▌
Ghost Selfhost Admin · fhgomes bundle
Full administration of a self-hosted Ghost CMS instance — initial setup (2FA login), ongoing config via Admin API (settings, themes, images, navigation, code injection, social links), and Playwright fallback for UI-only operations (portal, email config, labs, custom theme settings, user management).

0 installs
▌
Consistent Visual Generation · fhgomes bundle
Procedure for generating CONSISTENT characters, avatars and visual assets with generative AI (ChatGPT / GPT Image 2 today; Nano Banana, Midjourney, Flux as alternatives), using a Character Bible, canonical references, a checklist and side-by-side comparison. Use WHENEVER the user asks to create or maintain a character/avatar/mascot with a stable visual identity ("create an avatar for me", "keep the style", "canonical reference", "character sheet", "it came out too photorealistic", "it drifted from the reference", "character consistency", "style reference", "generate it in ChatGPT and upload it to Drive"), or when a generation drifted in style, color, hair, makeup or tattoos. Covers operating ChatGPT through the browser (unsticking the render, downloading, uploading to Drive), the folder convention and the version-in-filename convention, what to do when the user approves a variant (canon promotion), and the lessons on calibrating subtle marks (stroke shape, intensity by comparison, never "glow" for something t

0 installs
▌
Ghost Content Pipeline · fhgomes bundle
Automated pipeline for creating, publishing and optimizing content on Ghost CMS. Use whenever you need to: create posts automatically, schedule publications, improve existing posts for SEO, generate images for posts, distribute content to social networks, submit URLs for indexing (Google/Bing/IndexNow), monitor content performance, run bulk operations on posts (mass-update tags, meta descriptions, feature images), build a content calendar, or any variation of "publish on Ghost", "automate posts", "improve post SEO", "create content", "content pipeline". Also trigger when the user mentions: "ghost cron job", "auto publish", "content automation", "ghost posts", "ghost SEO", "indexnow", "google indexing", "bulk update posts", "content calendar", "repurpose content", "social media automation ghost". Also triggers on the equivalent phrases in other languages.

0 installs

15 published skills