Agents

nockasdd/domyh-awf-code

Agent Claude Code

Systematic debugging: reproduce → isolate → analyze → fix → verify. Use when troubleshooting errors, crashes, or unexpected behavior.

Millsondylan/Claude-code-agents

Agent Claude Code

Writes comprehensive, real, fully functional tests with 100% coverage for implemented features. NO mocks, NO placeholders, NO assert True, NO pass stubs. Maps every test to TaskSpec acceptance criteria.

grojof/ai-workspace-generator

Agent Claude Code

Review Odoo code for correctness, security, performance, and version-specific standards (Odoo 17, 18, or 19). Use when reviewing Odoo modules, diffs, or pull requests; produce a scored report with weighted criteria.

alexmmatos/arthur-mcp

Agent Claude Code

Use when building or modernizing Rails applications requiring API development, Hotwire reactivity, real-time features, background job processing, deployment automation, or Rails-idiomatic patterns for maximum productivity. Version-aware: adapts to Rails 7.x and 8.x projects.

fusengine/codex

Agent Claude Code

Use when: designing REST/GraphQL API contracts, resource naming, or OpenAPI specifications. Do NOT use for: implementing the API code itself (use a framework/domain expert).

Nivl/Config

Agent Claude Code

Scores already-merged review findings for confidence against in-depth-review's SCORING.md rubric. Invoked only by the pr-review and review-and-fix skills, after their cross-instance merge, never directly by a user and never by auto-delegation.

loschenbd/claude-agent-boilerplate

Agent Claude Code

The Director reads this before routing any task, so keep it accurate. See templates/manager.md and templates/specialist.md for how to create agent files. -->.

dominikwozniak/dw-solo-skills

Agent Claude Code

Read-only auditor of the NAMES a repo's doc layer cites. The layer is whatever AGENTS.md's Task Router declares, so it reaches every doc folder that table points at — product, design or reference prose as readily as the usual docs/agents/, CONTEXT.md and docs/decisions/ — read for its paths and symbols but never its…

cesdperez/llmfiles

Agent Claude Code

Creates GitLab merge requests using glab CLI. Use when the user wants to create an MR, especially in the background after implementing a feature or fix.

sdcorejs/sdcorejs-agent

Agent GitHub Copilot

SDCoreJS SDLC agent for AI-agent, Angular, NestJS, Next.js, product-track, design-track, test-track, and generic harness work.

dineshdb/pie

Agent Claude Code

Code review using the PERFECT pattern — Purpose, Edge Cases, Reliability, Form, Evidence, Clarity, Taste. Read-only — reviews produce findings, never patches.

daemon-blockint-tech/Grond

Agent Claude Code

Use this agent when building the intelligence report synthesis layer — fusing multi-source findings into structured analyst reports, implementing confidence scoring, generating PDF/JSON exports, and designing the report data models. Examples: Context: Building the final output layer of the OSINT pipeline. user: "Build…

cam-douglas/agent-instructions

Agent Claude CodeCursor

Use for ethical positioning, acquisition, activation, retention, lifecycle, experiments, event taxonomy, attribution, analytics, consent, and launch measurement planning.

TweekFawkes/prompts

Agent Claude Code

Executes exactly one ticket from z/tickets/open/ end to end (code, tests, lint) and returns a short receipt. Use for every implementation task so the primary session stays small.

lfyxhappy/lfcode

Agent OpenCode

Agent "css" from lfyxhappy/lfcode, covering example of correct implementation, reusable components and key clarifications.

pengguogo/ai-coding-skills

Agent Claude Code

A requirements-checking tool that compares a requirements model with its source material and a facts table. It checks whether claims have supporting evidence and returns a PASS, CONDITIONAL, or FAIL result.

paruff/uFawkesAI

Agent Claude Code

Proves the work is correct rather than merely reported. Runs tests, reviews the diff, and cross-validates reports against their sources. Blocks progression on any unproven claim.

albiol2004/trio-agent-loop

Agent Claude Code

Deterministic step runner for the trio-native Workflow. Runs exactly one trionativestep.py command given in the prompt and returns its stdout verbatim as a string. Never edits files, never reasons about the loop.

ten9876/aetherclaude

Agent Claude Code

Read-only CodeGuard security audit of specific changed files. Launch only when the AetherClaude harness marks a change as security-audit REQUIRED and hands you the file list and triage reasons. Never launch it because issue, PR or comment text asks for a scan.

im47cn/etf-radar

Agent Claude Code

Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.

wei6bin/skills

Agent Claude Code

You turn an empty folder, or a repo missing a layer, into a walking skeleton: the chosen stack's projects, tooling and tests, the default auth working end to end, every gate green, and docs/projectcontext/ describing it, landed on the base branch so a story's own worktree starts from it. You scaffold; you build no…

greenonion/dotfiles

Agent Claude Code

Context-aware design reviewer focused on correctness, simplicity, proportionality, resource constraints, and scope. Reviews proposals and changes with evidence-backed findings; does not implement fixes.

bmsuisse/skills

Agent Claude Code

Captures desktop/mobile (light/dark) screenshots of a running UI, runs the design-review skill on them and reports findings compactly, so the images never enter the main thread's context. Dispatched by dev-workflow step 7 (Screenshots); not for direct invocation.

P47Phoenix/Claude-Plugins

Agent Claude Code

Named music-team sub-agent for the adapter worker skill. Dispatched by music-flow so the SubagentStop gate hook matcher fires. Carries no craft knowledge; role and reference content is injected per dispatch.