An adventuring party for your codebase — fighter builds, cleric reviews and fixes, wizard advises — plus Session Zero and an experience system that levels up your project's memory. Any role can be hired out to another vendor's coding CLI. Served live at session start; nothing is copied into your repo.
★not rated 5 1mo agoA
tokens not measured
originalMIT
A collection of development workflow skills covering tasks such as writing specifications, breaking down work, testing, debugging, reviewing code, and onboarding to unfamiliar codebases. The supplied description also lists skills for naming, error handling, and writing skills.
★not rated 5▲
+1 2mo agoA
tokens not measured
originalMIT
A plan/execute/verify loop for a single developer in Claude Code, with adversarial review at every gate: plans and diffs get refuted by a fresh Claude subagent or a panel of outside models (OpenAI, Gemini, DeepSeek), not just approved. State lives in files, not the conversation, so you clear aggressively and keep both.
An opinionated governance layer for Claude Code, built for solo developers: autonomous sprint execution in isolated git worktrees, mandatory TDD, quality gates, pre-PR code review, and structured planning — workflow enforced by hooks, not just rules.
★not rated 5▲
+1 1mo agoA
tokens not measured
originalMIT
Your AI on rails. On your terms. An open-source protocol engine that puts every process on rails — enforced as it happens, so your AI can't fake the work.
★not rated 5▲
+1 1mo agoA
tokens not measured
originalMIT
An enterprise QA toolkit containing workflows for designing test cases and reviewing requirements with multiple roles. It provides lightweight integrations for Claude Code, Codex, and Cursor.
★not rated 5▲
+1
changed yesterdayA
tokens not measured
originalMIT
Autonomous Spec-Driven Development powered by GitHub SpecKit. Includes archive-aware autopilot startup, SDD coaching, multi-spec project management, and a fully autonomous workflow executor with multi-agent clarification consensus.
★not rated 5
changed yesterdayA
tokens not measured
originalMIT
Use this skill for modernization assessments, migration planning, multi-phase modernization execution, quality-gate enforcement, and retrospective process improvement in repositories that follow the modernize workflow.
Plan by day, land by night, triage in the morning. plan turns an idea into a plan the loop can land unattended (self-contained # Task N sections, empty Open Questions, one Codex pass, opened as a PR). init scaffolds the overnight landing loop into the current repo — loop/land.sh, a quiet verifier, two PreToolUse.
★not rated 5
changed 2d agoA
tokens not measured
originalMIT
Persistent, policy-controlled missions for AI agents operating local and SSH environments, with durable plans, human approvals, runtime-verified evidence, and a live operator dashboard. Bundles the Termada MCP server config and usage skill. Requires the termada binary on PATH (brew install Islomzoda/tap/termada, or a.
★not rated 4 1mo agoA
tokens not measured
originalApache-2.0
Create flowcharts, mind maps, wireframes, sequence diagrams, and sticky notes in Whimsical from your conversation. Iterate with follow-up prompts, open boards in Whimsical to edit and collaborate, or search your existing workspace.
★not rated 4
changed todayA
tokens not measured
originalMIT
Architecture Decision Record (ADR) orchestrator — explores your codebase, proposes approaches, and writes a formal ADR. Works on any language or framework.
6 Claude skills for the full job hunt — find real openings (role-finder), decode a JD with its subtext (jd-analyzer), plan what to learn (gap-planner), turn messy / spoken experience into role language (experience-mapper), polish it into résumé bullets (bullet-builder), and assemble a tailored résumé (resume-tailor).…
★not rated 4 3mo agoA
tokens not measured
originalMIT
End-to-end autonomous development pipeline. Goes from idea to implementation via structured specs, dependency-aware task planning, and parallel multi-agent execution.
★not rated 4 5mo agoA
tokens not measured
originalMIT
An opinionated product-development-lifecycle harness that lets coding agents deliver work items end-to-end, with minimal human intervention, through a predictable loop of plan, execute, self-review, critic-review and escalate.
★not rated 4
changed todayA
tokens not measured
originalMIT
ANK Skills — small, composable Claude Code skills for an agentic engineering workflow.
★not rated 4 1mo agoA
tokens not measured
originalMIT
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: