knowledge graph agents

Ar9av/obsidian-wiki

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

Ar9av/obsidian-wiki

Agent

Compare two outputs WITHOUT knowing which skill produced them.

Ar9av/obsidian-wiki

Agent

Evaluate expectations against an execution transcript and outputs.

raphaelmansuy/edgequake

Agent

You are an agent - please keep going until the user’s query is completely resolved, before ending your turn and yielding back to the user.

raphaelmansuy/edgequake

Agent

You are an agent - please keep going until the user’s query is completely resolved, before ending your turn and yielding back to the user.

najmuzzaman-mohammad/gawkbot

Agent

These instructions apply to AI coding agents working in Nex repositories. Keep tool-specific root files (CLAUDE.md, AGENTS.md, etc.) pointed at the same canonical repo file so Claude, Codex, and other agents receive equivalent guidance.

najmuzzaman-mohammad/gawkbot

Agent

A multi-agent rhythm for reviewing a single PR through several narrowly-scoped lenses to catch issues that one reviewer would miss.

catlog22/maestro-flow

Agent Claude Code

Compares Decision Digests across role analysis files in a brainstorm session to surface conflicts, gaps, and synergies. Read-only — returns structured text for the orchestrator to apply.

catlog22/maestro-flow

Agent Claude Code

Generates multi-file role analysis for a brainstorm session — analysis.md index + per-feature files + optional findings under {outputdir}/{role}/.

catlog22/maestro-flow

Agent Claude Code

UI design token management and prototype generation — W3C Design Tokens Format, state-based components, WCAG AA validation, responsive layout templates.

smixs/agent-second-brain

Agent Claude Code

GTD-style processing of incoming entries. Decide action for each item - do now, schedule, delegate, save, or delete.

smixs/agent-second-brain

Agent Claude Code

Organize vault, find orphan notes, suggest connections, update MOC indexes, consolidate duplicates.

qualixar/superlocalmemory

Agent

Advises on scope, roles, compliance, and GDPR use in SuperLocalMemory. Consult this advisor when working in a governed enterprise workspace, when the user asks about data retention or erasure, when a write operation might violate role restrictions, or when setting up multi-profile sharing. Never bypasses governance…

qualixar/superlocalmemory

Agent

Runs a task as a bounded loop backed by SuperLocalMemory: iterate until an INDEPENDENT gate passes — never the agent's own claim. Delegate here when a task has a checkable acceptance condition (a test suite, a JSON schema, a linter, a reconciliation rule, a security scan) and you want gate-verified completion with an…

qualixar/superlocalmemory

Agent

Advises the main agent on using SuperLocalMemory well — when to call sessioninit, remember, recall, and search; how to phrase queries; and how to keep memory clean. Delegate here for any "should I save/recall this?" decision or when memory results look wrong.

FreePeak/LeanKG

Agent

Dispatches isolated subagents to worktree branches for independent parallel tasks. Use when 3+ tasks can work independently without shared state.

FreePeak/LeanKG

Agent

Before doing ANY codebase search, navigation, or analysis, you MUST use LeanKG tools.

infinri/Writ

Agent

Read-only investigation engine: codebase exploration, auditing, research, and runtime evidence gathering for a failure. Cannot modify files. Use before planning, to answer a question that requires grounding findings in evidence (file:line, config value, schema fact), or to reproduce a failure and capture its runtime…

infinri/Writ

Agent

Implements all files listed in an approved plan. Writes production code, configuration, and updates test implementations. Use after test skeleton approval.

infinri/Writ

Agent

Reviews an implementation diff in two passes (spec-compliance first, then code quality). Read-only. Returns structured findings. Replaces the separate spec/code-quality reviewers.

joshuaswarren/remnic

Agent

Review and curate memory suggestions from Engram's review queue.

TianGzlab/OmicsClaw

Agent

OmicsClaw uses one primary repository context with a Bench-specific supplement.

TianGzlab/OmicsClaw

Agent

Issues and PRDs for this repository live in GitHub Issues for zhou-1314/OmicsClaw. Use the gh CLI for issue operations.

TianGzlab/OmicsClaw

Agent

Engineering skills use five canonical triage roles. Each role maps directly to the corresponding GitHub label.