agentic-workflow agents

yahor-punko/mavericks-os

Agent Claude Code

Validates completed slices against acceptance criteria. TRIGGER when: (1) developer marks a slice devdone or readyforqa, (2) runtime or manual verification is required. SKIP: artifact-only or unit-only tasks (validator run / test suite serves as QA), tasks still inprogress.

gaia-research/gaia-skill-heaven

Agent

Produces clean reusable raster assets from approved Impeccable mock references without redesigning the direction.

gaia-research/gaia-skill-heaven

Agent

Reviews a finished Impeccable build against its direction contract, the approved comp, and the chosen world's quality bar, returning an ordered list of material fixes.

gaia-research/gaia-skill-heaven

Agent

Applies leased Impeccable live manual copy-edit batches to source and returns canonical Apply results.

ruali-dev/Riven-Analyst

Agent

Part of riven-analyst

Compare a small set of sourced complete build directions for one resolved Warframe weapon.

ruali-dev/Riven-Analyst

Agent

Part of riven-analyst

Resolve a missing Riven family, compare its material variants, or research one decisive weapon mechanic.

ruali-dev/Riven-Analyst

Agent

Part of riven-analyst

Review a high-uncertainty Riven report for identity, causality, false precision, and player readability.

lantisprime/claude-sdlc

Agent Claude Code

Part of sdlc-plugin

Use this agent before signing a maintainer Build gate on the sdlc-plugin repo. Conditionally reviews dependency manifest changes (package.json, requirements.txt, go.mod, Gemfile, pom.xml, Cargo.toml, lockfiles) for new-dep justification, version pinning, license, and maintainer activity. Self-exits with a…

lantisprime/claude-sdlc

Agent Claude Code

Part of sdlc-plugin

Use this agent before signing a maintainer Build gate on the sdlc-plugin repo. Reviews the current diff for security concerns from the security-review skill checklist (input validation, authN/authZ, secrets, injection surfaces, dependency hygiene, sensitive data, output encoding, error handling, cryptography, infra…

lantisprime/claude-sdlc

Agent

Part of sdlc-plugin

Bounded subagent that turns raw source material (markdown files, plain-text files, pasted text) into a normalized, provenance-traced scope draft at .claude/sdlc/scope-drafts/. Invoked by the plan skill when scope.md does not yet exist and the human points at a source. Write scope is restricted to scope-drafts/ only …

punkadillo/figma-code-composer

Agent Claude Code

Builds framework-native components from the component nodes in a Figma manifest. Branches on configSnapshot.framework + cssSystem. Writes only inside configured component directories. Spawned by figma-coordinator after token-builder (when applicable).

punkadillo/figma-code-composer

Agent Claude Code

Orchestrator for the Figma→code pipeline. Invoked by /figma-build, /figma-update, /figma-icons, /figma-tokens. Reads .figma-pipeline/config.json, spawns figma-fetcher, validates the manifest, routes specialists, handles errors/retries/model-tier. Writes no source code.

punkadillo/figma-code-composer

Agent Claude Code

Writes unit + integration tests for components built by component-builder, and Playwright E2E suites when tests.e2e.enabled. Branches on configSnapshot.framework + tests.unit.framework + tests.unit.testingLibrary + tests.e2e.enabled. Spawned in parallel with story-author after component-builder.

fullstack455/deer-flow

Agent

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

fullstack455/deer-flow

Agent

Compare two outputs WITHOUT knowing which skill produced them.

fullstack455/deer-flow

Agent

Evaluate expectations against an execution transcript and outputs.

intentdriven/abcd

Agent

Part of abcd

Per-agent SOTA prompting research for intent-fidelity-reviewer; references baseline 01-general-best-practices.md.

intentdriven/abcd

Agent

Part of abcd

Per itd-5, every agents/.md prompt carries a promptversion and a corresponding entry here recording the bump rationale (and, at 1.0.0 lock, the self-improvement pre-flight outcome and calibration-corpus delta).

intentdriven/abcd

Agent

Part of abcd

Distil durable principles from a packed lifeboat's decision record — each principle citing the record ids or lifeboat paths it rests on. Host-delegated; feeds abcd disembark principles --principles-json.

tm42/mnemograph

Agent

Part of mnemograph

Initializes memory context at session start by analyzing the knowledge graph. Use at session start to get a compact briefing of relevant memories.

tm42/mnemograph

Agent

Part of mnemograph

Stores knowledge in the mnemograph graph with quality enforcement. Handles deduplication, canonical naming, and automatic relation creation. Use for all remember/store operations.

MarieLynneBlock/arcanum-artifex

Agent

Guidelines for creating high-quality Agent Skills for GitHub Copilot.

MarieLynneBlock/arcanum-artifex

Agent

Guidelines for creating custom agent files for GitHub Copilot.

MarieLynneBlock/arcanum-artifex

Agent

Comprehensive development guidelines for Microsoft 365 Copilot declarative agents with schema v1.5, TypeSpec integration, and Microsoft 365 Agents Toolkit workflows.