← all publishers

0xNyk

@0xnyk source repo

Report this profile Claim this profile

• 19 skills
• 0 followers
• 11 hours ago last updated

1. ▌
   Devgod · 0xnyk bundle

   Full-stack product-engineering operating system that automatically activates for matching software, web, SaaS, and product-engineering tasks even when the user does not name devgod. Use for planning, auditing, building, fixing, debugging, refactoring, designing, testing, securing, researching, optimizing, or shipping product systems; architecture, UI/design systems, accessibility, RLS/migrations, APIs, workers, auth, billing, browser QA/Playwright, deploy, product analytics/GTM engineering, agentic coding, prompt/loop optimization, PRD-to-evidence, deep research, SaaS pages, webhooks, AI services, monorepos, feature flags, GDPR flows, KPI/event contracts, supply-chain security, malware/dropper detection, or agent orchestration. Also activate when the user says devgod. Prefer unmachined for prose/UI de-slop, gstack for deploy ritual/browser QA, vercel react-best-practices for pure React perf. Excludes generic CEO strategy, mobile-only work, and notebook data science unless explicitly adapted.
   0
   installs
2. ▌
   Fixture Reader · 0xnyk bundle

   Reads fixture documentation when explicitly requested and returns a local summary.
   0
   installs
3. ▌
   Quality Gate · 0xnyk

   Production quality gate for agent sessions. Activates on session stop to evaluate work quality using 4-dimension weighted scoring (completeness, honesty, deferral ratio, work evidence). Catches rationalization patterns, verifies test claims, and generates handoff artifacts for session continuity. Use sprint contracts to define done-criteria before building.
   0
   installs
4. ▌
   Context Modes · 0xnyk bundle

   Structured work modes for agent sessions. Set LACP_CONTEXT_MODE to activate: tdd (red-green-refactor), debugging (4-phase root cause), sprint (pre-agreed criteria), verification (evidence-before-claims), brainstorm (design first), think (pause-and-reflect), orchestrate (task decomposition). Each mode injects behavioral rules at session start.
   0
   installs
5. ▌
   Session Hardening · 0xnyk

   Production hardening for agent sessions. Includes pretool guards (blocks rm -rf, co-author injection, publishing without approval, data exfiltration), continuous QA (runs tests every N file writes), and session context injection (git state, focus brief, handoff artifacts). Activates automatically via hooks.
   0
   installs
6. ▌
   Va Prep · 0xnyk

   Use when triaging inbox or calendar into a review packet. Do not send or book.
   0
   installs
7. ▌
   Chief Digest · 0xnyk

   Use when making a source-linked digest of what needs a human decision. Do not send mail or assign bots.
   0
   installs
8. ▌
   Marketer Draft · 0xnyk

   Use when drafting campaign or social copy for review. Do not send or publish.
   0
   installs
9. ▌
   Sales Review List · 0xnyk

   Use when scoring accounts and drafting outreach for review. Do not send or edit CRM.
   0
   installs
10. ▌
    Designer Packet · 0xnyk

    Use when producing a design packet with options and a buildable spec. Do not ship UI.
    0
    installs
11. ▌
    Reviewer Verdict · 0xnyk

    Use when judging a named artifact as PASS, BLOCK, or HOLD. Do not implement.
    0
    installs
12. ▌
    Researcher Brief · 0xnyk

    Use when producing a cited brief from named sources. Do not publish.
    0
    installs
13. ▌
    Implementer Spec · 0xnyk

    Use when implementing an approved spec or issue. Do not merge or self-review.
    0
    installs
14. ▌
    Agent Security · 0xnyk bundle

    Defensive agent supply-chain security for repositories that AI agents and automations touch. Use before making a repo public or pushing to one, when reviewing a cloned starter template or third-party skill/package, or when an agent has GitHub credentials that can delete/rename/transfer/archive repos. Ships two battle-tested defenses: (1) scan-repo — a deterministic, network-free leak + dropper gate that blocks secrets, obfuscated code-execution droppers, invisible-unicode, and private-context leaks from entering a public repo; and (2) repo-guard — a PATH shim + Claude Code hook that hard-blocks destructive GitHub repo-lifecycle operations unless a human confirms the exact repo. Also ships scan-content — a KNOWN-pattern tripwire for untrusted fetched content (web/search/tool/MCP output) — paired with a behavioral contract for handling untrusted content, because prompt injection is unsolved and detection alone cannot prevent it. Plus vet-incoming — an inbound supply-chain gate that vets a third-party template/p
    0
    installs
15. ▌
    Termpeek · 0xnyk bundle

    Preview images, video, PDFs, code files, diffs, and tweets from inside an agent CLI that cannot render them. Use when the user asks to see, view, preview, show, or look at a file — screenshots, generated images, charts, mockups, video clips, PDFs, or a code diff — or says "show me", "let me see it", "preview that", "what does it look like". Also use after generating or downloading an image/video/PDF so the user can actually see the result. Works in Claude Code, Codex, Hermes, Gemini CLI, and any terminal agent.
    0
    installs
16. ▌
    Unmachined · 0xnyk bundle

    Finds and removes AI slop from prose, UX copy, and web interfaces. Use when writing, auditing, or revising articles, posts, READMEs, marketing copy, UI copy, layouts, or frontend code that must not feel AI-generated; when the user says unmachined, de-slop, AI slop, anti-slop, humanize, make this human, sounds like AI or ChatGPT, looks AI-generated, feels generic, or design/copy audits; and when always-on is enabled in unmachined config (any user-facing text in the CLI must pass anti-slop rules and scan_text before ship). Quality layer, not the author: it edits what authoring skills produce. Not for greenfield brand or aesthetic invention, pure logic without user-facing strings, or evading AI detectors. Supports onboard, always-on/off, status, learn (personal voice profile), audit, fix, text, ui, and diff workflows.
    0
    installs
17. ▌
    Xint Rs · 0xnyk bundle

    X Intelligence CLI for searching, monitoring, and analyzing X/Twitter from the terminal. Use for X/Twitter research prompts such as "search x", "find tweets about", "what's X saying", trend checks, follower diffs, real-time watch tasks, sentiment/report analysis, and bookmark-sync workflows. Best when recent community discourse matters (library/API changes, launches, market or cultural events). Supports search, watch, trends, bookmarks, likes/following (OAuth), Grok analysis, and JSON/JSONL/CSV/Markdown export. Non-goals: posting original tweets, DMs, or enterprise-only features.
    0
    installs
18. ▌
    Xint · 0xnyk bundle

    X Intelligence CLI for searching, monitoring, and analyzing X/Twitter from the terminal. Use for X/Twitter research prompts such as "search x", "find tweets about", "what's X saying", trend checks, follower diffs, real-time watch tasks, sentiment/report analysis, and bookmark-sync workflows. Best when recent community discourse matters (library/API changes, launches, market or cultural events). Supports search, watch, trends, bookmarks, likes/following (OAuth), Grok analysis, and JSON/JSONL/CSV/Markdown export. Non-goals: posting original tweets, DMs, or enterprise-only features.
    0
    installs
19. ▌
    Council · 0xnyk bundle

    Convenes a multi-persona council of historical thinkers to deliberate on complex problems and synthesize a verdict.
    11
    installs