ulises-jeremias/agent-toolkit-complete

WHAT — Create and maintain Architecture Decision Records (ADRs) per the process. Covers when to write an ADR, required sections, review, and linking to epics/PRs. English for cross-team artifacts unless the user asks otherwise.

WHAT - Capture explicit agreements, terms, parties involved, dates, validity, and linked work items using the Agreement Document structure.

Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs before code; cite sources; prefer AGENTS.md for agent behavior; portable across Cursor/Copilot/Claude; use agent-toolkit CLI when needed.

WHAT — AWS Well-Architected Framework review (6 pillars) — operational excellence, security, reliability, performance, cost, sustainability + WAR process. Checklist for workload evaluation on AWS; complementary to official AWS MCP for live account data.

Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust.

WHAT - Draft and review bugs using the Bug Template; classifies whether an issue should be escalated to incident based on production/user impact.

WHAT — C4 model methodology (Context, Container, Component, Code) guidance — what to draw at each level, when, and how to render C4-inspired diagrams via Mermaid (PlantUML/Structurizr optional advanced). Methodology not renderer.

Use Chrome DevTools MCP to control and inspect a live Chrome instance for network, console, performance, rendering, and Deep debugging. Pairs with playwright-cli (deterministic interaction/E2E) — complements, not duplicates.

ClickUp CLI for managing tasks, sprints, comments, statuses, and Docs. Use when the user needs to interact with ClickUp — creating/editing tasks, checking sprint status, adding comments, linking PRs, managing Docs and pages, or searching tasks. Prefer this CLI over raw API calls.

WHAT — Vendor-neutral distributed cloud patterns (Retry, Bulkhead, Circuit Breaker, CQRS, Event Sourcing, etc.) abstracted from AWS/Azure/GCP sources — when to apply, tradeoffs, mapping to AWS/GCP/Azure primitives. Offline checklist, no live account required.

CodeQL operational workflow — discover/config, run/inspect, triage SARIF findings (rule/query ID, source→sink, evidence), remediate, re-validate. Distinguishes broad MegaLinter linting from semantic security analysis.

HOW — Run dbt checks as documented in the target repo (parse, compile, test, selective run). Does not configure Snowflake accounts or change cloud security.

WHAT - Capture lightweight project, product, or operational decisions that do not require a full ADR; includes rationale, date, owner, and references.

WHAT - Evidence-based design-unit assessment orchestrated by project-assessment. Evaluates visual hierarchy, UX friction, interaction, a11y, responsiveness, design-system compliance, and distinctiveness with severity/confidence evidence citations. Reuses project-assessment-evidence semantics — no second framework.

WHAT - Browser-grounded iterative design improvement. Consumes design-assessment findings, defines direction, prioritizes safe vs ambiguous changes, implements within existing design system, runs app, captures rendered evidence via browser, reviews and iterates. Reuses evidence model — no new scoring framework.

Remove AI-generated code slop and clean up code style

WHAT — Dev Companion (general): layered companion for client delivery; modes, gates, delegation to assistant and workflow-generic-project; no CLI matrices.

WHAT - Default development workflow, task lifecycle, DoR, DoD, validation, and evidence model when a project has no explicit override. Repository instructions still take precedence.

WHAT — Generate or update documentation from code: README.md from repo structure, CHANGELOG.md from git history, API reference from OpenAPI/GraphQL schemas, and AGENTS.md starters for new projects.

WHAT - Draft and review epics using the Best Practices Epic Template; includes objectives, success criteria, related tasks, stakeholders, and effort metadata.

Use the Figma MCP server to fetch design context, screenshots, variables, and assets, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.

Connects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map this component", "link component to code", "create code connect mapping", or wants to establish mappings between Figma designs and code implementations. For canvas writes (Plugin API), install the opt-in figma-use pack documented in docs/SKILLS.md.

Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.

Create a new blank Figma file. Use when the user wants to create a new Figma design or FigJam file, or when you need a new file before calling use_figma. Handles plan resolution via whoami if needed. Usage — /figma-create-new-file [editorType] [fileName] (e.g. /figma-create-new-file figjam My Whiteboard)

Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions "implement design", "generate code", "implement component", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes (Plugin API), see the opt-in figma-use pack documented in docs/SKILLS.md.

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

Review and create distinctive, production-grade frontend interfaces with high design quality and design system compliance. Evaluates using three pillars: frictionless insight-to-action, quality craft, and trustworthy building. USE FOR: PR reviews, design reviews, accessibility audits, design system compliance checks, creative frontend design, UI code review, component reviews, responsive design checks, theme testing, and creating memorable UI. DO NOT USE FOR: Backend API reviews, database schema reviews, infrastructure or DevOps work, pure business logic without UI, or non-frontend code.

Triage and address open GitHub PR review and conversation comments using the gh CLI. Use when the user wants to "address PR comments", "resolve review threads", or "respond to reviewers" on the current branch's pull request.

Daily GitHub contribution planner — analyzes the gh-logged-in user's non-archived repos (owned + forks) and recent contributions, produces a prioritized plan, halts for approval, then dispatches parallel sub-agents to execute approved items via existing PR/CI/review skills.

Diagnose failing GitHub Actions checks on a PR via gh, summarize the failure context, propose a plan, and only implement after explicit user approval. External CI providers (Buildkite, CircleCI, etc.) are reported by URL only.

HOW — GitHub CLI (gh): push branch, create draft PR with title/body from template or file; fallback untracked PR_DESCRIPTION_*.md. Use when origin is GitHub.

HOW — GitLab CLI (glab): push branch, create draft MR with title/body; fallback untracked markdown. Use when origin is GitLab.

Manage Herdr workspaces, tabs, and panes for Agent Toolkit swarms with eager windows, shell-aware execution, and reuse.

WHAT - Draft and review incident reports and RCA notes using Incident Management guidance; includes detection, impact, timeline, RCA, resolution, and follow-ups.

Discover installed skills, agents, loops, and platform capabilities via agent-toolkit inventory, matrix, and skills list.

Create, scaffold, or refactor Jupyter notebooks (.ipynb) for experiments and tutorials. Prefer the bundled templates and the helper script (new_notebook.py, also exposed as newnotebook) to generate a clean starting notebook instead of authoring raw notebook JSON.

Manage Linear issues, projects and cycles via the Linear MCP server. Use when the user wants to read, triage, create or update Linear tickets, plan a sprint, audit Linear documentation, or rebalance team workload.

WHAT — Recommend the most cost-effective LLM provider for a given task type. Shows estimated cost per run across available providers and integrates with devcompanion llm-status to show what is actually available.

Execute and manage loop engineering primitives (init, run, status, audit) from an AI coding session via the agent-toolkit loop CLI.

WHAT - Evidence-based management unit assessment for governance, delivery, collaboration, culture, and AI-native management readiness. Interactive and source-driven before any score is assigned.

Configure and manage MCP providers for Agent Toolkit — setup, list, doctor, and per-tool deployment.

MCP config + implementation security audit — config secrets/auth, unpinned versions, remote vs local, OAuth, env exposure; implementation command injection, SSRF, unsafe args, tool poisoning. Static, evidence-cited.

WHAT - Create structured meeting minutes from notes or transcripts using meeting templates, with redaction, action items, decisions, and traceability.

Entry point for everything MegaLinter. Use when the user wants to lint their repository, set up MegaLinter, check or fix lint errors, make CI lint jobs pass, or says "run megalinter", "fix lint errors", "make the linters happy", "clean up code quality". Detects the repository state and orchestrates the megalinter-setup, megalinter-check and megalinter-fix skills in a loop until the repository is clean.

Collect MegaLinter lint errors for the current repository. Use when the user wants to know if the code passes linting, why the MegaLinter CI job fails, or before/after fixing lint errors. Two modes - watch a CI job (GitHub Actions, GitLab CI, Azure Pipelines, Bitbucket Pipelines) and parse its logs, or run MegaLinter locally with Docker (full run or fast parallel standalone linter runs).

Fix the errors reported by MegaLinter. Use after megalinter-check found errors, or when the user pastes MegaLinter/CI lint errors and wants them fixed. Applies safe fixes automatically (auto-fix linters first, then guided manual fixes using per-linter fix guides), asks the user when fixing is ambiguous, and can disable rules or linters with user confirmation. Never pushes to the default branch.

Install or upgrade MegaLinter on a repository. Use when the user wants to add MegaLinter to a project, set up linting CI, update MegaLinter configuration or version, or says "install megalinter", "setup linting", "add code quality checks". Always goes through npx mega-linter-runner (--install or --upgrade), then refines .mega-linter.yml.

WHAT — Mermaid diagrams from text (flowchart, sequence, class, state, ER, gantt, gitGraph) — Markdown-native, Git-native, MIT. Primary renderer for architecture pack; renders via GitHub native or mermaid CLI (mmdc) to SVG/PNG.

Getting started guide for new users. Walks through setup validation, the skill/agent hierarchy, and the three most useful commands per role (developer, PM, tech lead). Use when someone is new to the workstation or asks "where do I start?"

WHAT — Default gate for any deliverable: confirm where the final artifact will be stored and that a human will review, before writing PRDs, TRDs, ADRs, or PR bodies. Repository paths, wikis, and ticket tools differ by engagement; never assume a single location.

OWASP-mapped agentic security review — prompt injection, tool poisoning, identity, excessive agency, credential exposure, supply-chain, insecure output handling, overreliance, data leakage, insecure plugin/MCP design. Evidence-cited, severity-ranked.

WHAT - Planning, estimation, task breakdown, and iteration capacity fallback based on Best Practices. Use before finalizing backlog scope, story/task estimates, or iteration commitments.

Drive a real browser from the terminal using the Playwright CLI (snapshot, click, fill, screenshots, traces). Use when the task is CLI-first browser automation (data extraction, UI debugging, form fills, multi-tab work). For Playwright **test specs**, use e2e-runner instead.

WHAT — When the repo has no GitHub PR template, structure the pull-request body using the default in references/pr-body-default.md. Pair with output-handshake and github-cli-workflow. Does not open the PR; HOW stays in the forge skill.

WHAT — Draft and review a Product Requirements Document (PRD) using the template. Business-level requirements, acceptance criteria, and traceability. Does not replace the product owner. English for tickets, PRs, and client-facing text unless the user asks otherwise.

Clone, index, and orchestrate multi-repo work via agent-toolkit project — symlinks, quick access, and swarm workspaces.

WHAT - Interactive project assessment router: define assessment scope and units, collect evidence through project-assessment-evidence, then delegate to technical or management unit assessment skills. Always evidence-based and human-reviewed.

WHAT - Interactive evidence intake for project assessments. Ask the user where each evidence source lives, build an evidence map, track missing evidence, assumptions, freshness, and confidence before any scoring happens.

WCAG 2.2 AA curated accessibility review — distinguishes automatically detectable, browser-assisted, and manual/human-judgment findings with evidence citations and SC mapping. Composes with design-assessment/design-improvement/frontend-design-review.

Interact with Slack workspaces for reading channels/messages, sending messages, adding reactions, and browsing canvases. Use when the user asks about Slack channels, messages, or notifications — NOT for Slack app development (use the slack-cli skill for that).

Interact with the official Slack CLI to create, run, deploy, and manage Slack apps, environments, manifests, and triggers. Use when the user asks about Slack app development workflows, not workspace chat automation.

HOW — Read-only Snowflake validation patterns: use repo-documented CLI (snowflake/sql) or SQL checks. Never claim success without working credentials and evidence.

WHAT - Produce spike and research findings using the spike template; captures purpose, findings, implementation strategy, risks, tradeoffs, open questions, and references.

Inspect agent supply chain — skills/plugins/MCP/npm/py packages, hooks, scripts, remote prompts, provenance, version pins, hashes, licenses, network and dangerous permissions — before adopting.

Launch an Agent Toolkit swarm from a natural language request using agent-toolkit swarm CLI with Herdr/tmux eager windows and file handoffs.

Create artifact/commit file handoffs for Agent Toolkit swarms with worktree-per-writer, branch, and promotion integration.

Observe, diagnose, and recover Agent Toolkit swarm runs via status, handoffs, logs, and attach with worktree and shell awareness.

WHAT - Draft and review technical tasks using the Best Practices Task Template; includes summary, technical notes, AC, estimate, owner, and due date.

WHAT - Evidence-based technical unit assessment for repositories, platforms, frontend, backend, infrastructure, data, UI/UX, and AI-native structural readiness.

STRIDE + agentic threat modeling — architecture discovery → assets/trust boundaries/data flows/actors → STRIDE + agentic threats → risk-ranked mitigations → incremental review → security acceptance criteria. Swarm-friendly.

WHAT — Draft and review a Technical Requirements Document (TRD) using the template, typically from an agreed PRD. Covers architecture, data contracts, technical decisions, risks, and test strategy. English for technical artifacts and tickets unless the user asks otherwise.

Workstation health triage — validate tooling, directory layout, and run doctor with remediation suggestions.

Cut AI tells from any writing. Must always apply.

WHAT - Draft and review user stories using the task template plus the As a/I want/so that format from Best Practices examples.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

WHAT - Router for creating and refining epics, user stories, tasks, bugs, and incidents using Best Practices work item hierarchy.

DEPRECATED alias. Use workflow-client-bootstrap instead.

DEPRECATED alias. Use workflow-generic-project instead.

Scaffold and manage the stateless AI workspace — context, packs, repos, and knowledge for multi-repo orchestration.

Syncs knowledge to the agentic-harness knowledge base. Use when the assistant discovers new patterns, learns user preferences, or identifies information worth preserving for future sessions. Integrates with tech-assistant for automatic trigger points.

Manage Git worktrees per writer for Agent Toolkit swarms — isolated branches, handoff promotion, and cleanup.