Latest Agent Skills

Routes UI evidence, comparisons, critiques, references, best practices, and design research to one research workflow.

Applies practical test-first and regression testing to behavior changes, bug fixes, state transitions, and public contracts.

Improves structure without behavior changes, using tests and focused slices; not for features unless behavior change is explicit.

Improves measured performance while preserving correctness, reliability, and maintainability.

Reviews code, diffs, or PRs for correctness, regressions, security, architecture, maintainability, and test gaps.

Plans parallel agents or worktrees with isolated ownership, validation lanes, and merge rules. Use only for safely separable work.

Applies TypeScript/JavaScript rules for types, async behavior, APIs, tooling, tests, and architecture.

Routes ambiguous multi-stage UI work across research, concept, Figma, implementation, and QA. Do not use for a clear leaf task.

Strict test-first gate only when explicitly requested or required by repository policy. Do not use for ordinary practical testing.

Reproduces failures, gathers evidence, tests hypotheses, fixes root causes, and adds regression coverage.

Routes Figma creation, editing, inspection, connection, components, or motion to the matching Figma workflow.

Routes UI implementation or redesign to the narrowest build workflow for pages, apps, dashboards, and styled frontends.

Implements security-sensitive changes with conservative trust boundaries, secret protection, tests, and verification.

Applies safe ESPHome rules for YAML, lambdas, sensors, switches, relays, boot behavior, fail-safes, and validation.

Applies senior Python rules for typing, async, APIs, persistence, tests, packaging, and architecture.

Routes rendered UI testing, visual regression, browser QA, accessibility, responsive, performance, or frontend review to a leaf skill.

Applies ESP32 rules for GPIO, boot states, relays, sensors, connectivity, firmware safety, and validation.

Applies C/C++ rules for resource safety, ownership, ABI, builds, tests, and validation.

Applies Rust rules for ownership, modules, errors, unsafe code, concurrency, tests, and tooling.

Limited local mode for small reversible changes. Skips routers, external tools, broad workflows, and high-risk work.

Applies Go rules for packages, explicit errors, interfaces, concurrency, tests, and tooling.

Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?"

Perform a post-implementation retrospective analysis measuring spec adherence, implementation deviations, and lessons learned.

Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: "Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file"

Skill for the Workflow-contracts area of paddock. 51 symbols across 11 files.

Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "How does X work?", "What calls this function?", "Show me the auth flow"

Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?", "Trace this bug"

Verify tasks marked [X] in tasks.md are implemented, not phantom completions (marked done but backed by missing or dead code).

Code simplification suggestions — clarity, unnecessary complexity, redundant abstractions. Advisory only.

Code comment accuracy verification, documentation completeness assessment, comment rot detection.

Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What GitNexus tools are available?", "How do I use GitNexus?"

Skill for the Observability area of paddock. 105 symbols across 26 files.

Initialize a Git repository with an initial commit

Skill for the Integrations area of paddock. 25 symbols across 2 files.

Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.

Error handling review — silent failure detection, catch block analysis, error logging.

Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"

Verify tasks marked [X] in tasks.md are implemented, not phantom completions (marked done but backed by missing or dead code).

Type design analysis — encapsulation, invariant expression, usefulness, and enforcement.

Test coverage quality analysis — behavioral coverage, critical gap identification, test resilience evaluation.

Validate current branch follows feature branch naming conventions

Run a full project health diagnostic — checks structure, agents, features, scripts, extensions, and git status.

Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.

Skill for the Onboarding area of paddock. 41 symbols across 7 files.

Skill for the Governance area of paddock. 28 symbols across 23 files.

General code quality review — project guideline compliance, bug detection, code quality analysis.

Create a feature branch with sequential or timestamp numbering

Post-implementation quality gate that reviews changes, fixes small issues (scout rule), creates tasks for medium issues, and generates analysis for large issues.

Archive merged feature specs into project memory with provenance, sweep discovery, and gated cleanup

Skill for the Dashboard area of paddock. 80 symbols across 16 files.

Perform a non-destructive post-implementation verification gate validating the implementation against spec.md, plan.md, tasks.md, and constitution.md.

Comprehensive code review using specialized agents — orchestrates code, comments, tests, errors, types, and simplify agents sequentially.

Detect Git remote URL for GitHub integration

Automatically stages and commits all changes after a Spec Kit command completes, using configurable event-based hooks.

Skill for the Sessions area of paddock. 50 symbols across 13 files.

Skill for the Adapters area of paddock. 108 symbols across 22 files.

Speckit Implement

Generate a custom checklist for the current feature based on user requirements.

Skill for the Scripts area of paddock. 486 symbols across 34 files.

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.