Local-first evidence-based career decision support for Japan job seekers: confirmed facts, conflicts, unknowns, verification, and user-controlled next actions.
★not rated 6
changed 3d agoA
tokens not measured
originalMIT
Claude Code plugin for the Marketing Manager platform — 37 Link Platform MCP tools for strategy, pages, links, analytics, tracking, routing, and deployment on 10x.in. Includes 25+ skills, 7 agent roles, and 5 slash commands.
Audits whether an agent actually did what it was asked. Catches the false 'Done' on Stop: missed subtasks, stubbed/no-op work, false 'tests pass', a method silently dropped in a refactor (dangling reference), and — uniquely — a standing project rule that was in context and overridden anyway. Runs on Stop, pre-commit…
★not rated 6 1mo agoA
tokens not measured
originalMIT
Build apps with Supabase as the backend. Equips AI agents with schema-driven workflows, RPC-first data access, edge functions, auth, RLS, and multi-tenancy.
★not rated 6 2mo agoA
tokens not measured
originalMIT
Your agent's memory, in a repo you own: the tome CLI, skills (capture, query, ingest, retrospect, write-a-plan, pickup-task), a SessionStart hook that points every session at the vault, a scoped Stop sync reminder, a no-build browse frontend (tome serve), and tome init to scaffold a fresh vault.
★not rated 6 1mo agoA
tokens not measured
originalMIT
Loop Engineering portable: bucle autónomo que revisa un proyecto por flujos de ejecución (GitNexus), escribe tests (test-first), arregla lo seguro en worktrees aislados, lo verifica con un evaluador adversarial independiente y abre PRs — nunca auto-mergea. Incluye la skill /forja y 4 subagentes…
★not rated 6 2mo agoA
tokens not measured
originalMIT
Blindfolds the LLM from your secrets. Stores API keys, tokens, and passwords in your OS keychain. The LLM works with placeholders, never sees actual values. Kernel-level sandbox enforcement on macOS.
★not rated 6 4mo agoA
tokens not measured
originalMIT
Rook — an MCP bridge for Rhino 3D and Grasshopper, with skills for designing, planning, and executing parametric definitions and LLM-powered Chirp components.
Real-time statusline HUD for Claude Code with GLM API balance tracking. Shows context usage, active tools, running agents, todo progress, and GLM token balance.
★not rated 6 7mo agoA
tokens not measured
originalMIT
Convert pixel-exact design mockups (e.g. HTML from Claude's design tool) into production Tailwind / shadcn-on-Radix components that use a real token system instead of arbitrary values like text-[13.5px].
★not rated 6 2mo agoA
tokens not measured
originalMIT
UI/UX design review skill based on FormFactor design school methodology. Reviews designs against professional standards for visual hierarchy, spacing, typography, color, layout composition, and Figma best practices.
★not rated 6 5mo agoA
tokens not measured
originalMIT
A spec-driven development pipeline for AI coding agents — PRD → Plan → Tasks → Agents → Implement, with per-slice review gates, ADR management, and cost capture.
★not rated 6 2mo agoA
tokens not measured
originalMIT
Run the validated Kshana PNT-resilience engine from an AI agent — SGP4/SDP4, IAU frames, GNSS availability/DOP/ARAIM, Allan/MTIE timing, GNSS-INS fusion and quantum-sensor models. The agent calls the real, externally-validated engine instead of guessing the math. Requires the kshana-mcp server on PATH (cargo install…
★not rated 6 15d agoA
tokens not measured
AGPL-3.0
Strict issue-ledger and exit-gate system that prevents false completion claims. Uses your signed-in Codex as an independent reviewer - Claude cannot claim 'all fixed' until every finding is actually closed.
★not rated 6 5mo agoA
tokens not measured
originalMIT