Silent-executor mode. Give it a task, it says "yaparım...", does the work, says "tamam." — no explanation, summary, code block, progress note or task list in between. Questions still get full answers. Commands: /oduncu kalk — mode on /oduncu yat — mode off /oduncu talk — trace on: the completion line carries the.
★not rated 5 28d agoA
tokens not measured
originalMIT
Build valid, fair, evidence-based assessments for any subject and grade: guided mode selection, test blueprint and topics-by-Bloom matrix design, item drafting by format rules, per-item passports, a review checklist, and classical psychometrics computed from real response data. Human expert review of every item is a…
★not rated 5 3mo agoA
tokens not measured
originalMIT
28 Claude Code skills that correct blind spots in Claude's knowledge of libGDX 1.14.x, gdx-ai, gdx-controllers, box2dlights, and Universal Tween Engine.
★not rated 5 9mo agoA
tokens not measured
originalMIT
Documentation-first development for AI coding agents — ten chain skills (persistent memory, zero-ambiguity specs, append-only decisions, git contract, independent verification gate, gated doc maintenance, brownfield onboarding) plus a bundled verifier agent and router + run-loop drivers shipped as both commands and…
★not rated 5 4mo agoA
tokens not measured
originalMIT
Your comeback, engineered. Honesty-first resume tailoring for any job description — clean, ATS-safe Word + PDF output — plus a private profile that remembers who you are and your real situation (work authorization, timeline). Built to grow into role-matching and job-search support. Knocked down. Not out.
★not rated 5 4mo agoA
tokens not measured
originalMIT
Integrate and debug the Hyper Solutions anti-bot API (Akamai, Incapsula, DataDome, Kasada) across the Go, Python, and JS/TS SDKs and raw REST. Bundles a request-debugging workflow: capture traffic via the powhttp MCP or analyze an exported HAR via the har-analyzer MCP, and apply a full rule set for…
Agentic software-delivery loop: turn specs into a dependency-ordered GitHub Issues backlog, then let agents claim, implement, adversarially review, patch, and merge tasks in isolated git worktrees behind a single correctness gate.
★not rated 5
changed yesterdayA
tokens not measured
originalMIT
wise copilot — flat slash commands, a workflow engine with an SDLC agent roster (CEO/CTO/architect/engineer/QA/security/SRE/…), a session-mining self-improvement loop (mine + refine + reset), and shared scripts for everyday git / PR / ticket-planning / skill-authoring tasks. The /wise command is a natural-language he.
★not rated 5
changed 4d agoA
tokens not measured
originalMIT
One head, many tentacles: a task queue built on GitHub Issues where named agent workers (Claude Code, GitHub Copilot CLI, Pi, or any protocol-conforming tool) claim tasks, execute them, validate against acceptance criteria, and record the evidence — dependencies, expiring leases, and automatic dead-worker recovery…
Skills for a Figma file several people share: work out its conventions, stub the screens still missing, draw them inside those conventions, wire the flow arrows, audit a page before handoff, hand sections over pinned to a version, QA what shipped, and bring the canonical page current. Installed with pm, it reads pm's…
★not rated 5
changed 5d agoA
tokens not measured
originalMIT
Portable project memory + development workflow for coding agents: auto-loads STATUS+RULES each session, enforces folder-level CONTEXT.md on edit, nudges durable state updates at turn end, scaffolds the system into any repo via guided discovery, and ships a tiered 6-phase workflow skill set covering every phase (brief.
End-to-end Marketing Mix Model framework: raw data discovery and question generation, campaign taxonomy mapping, finance reconciliation, framework-agnostic project spec, causal specification, prior generation, model fitting, diagnostics, experiment design with power analysis, and stakeholder reports and presentation…
An autonomous app development studio for Claude Code. 30 role agents (CEO/CPO/CTO, chief-of-staff, product-manager/validator/researcher, tech-lead/tech-manager, iOS/Android/backend/web devs, monetization, ux-architect/product-designer, code review, QA, test-automation, verification, release-auditor/manager, security…
★not rated 5 9d agoA
tokens not measured
originalMIT
Business-first computer vision delivery guide for Claude Code and Codex. Turn an operational goal into a scoped proof plan, verified evidence, costs, and a decision.
★not rated 5
changed 1mo agoA
tokens not measured
originalApache-2.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: