Claude Skills by joris887

Execute a UAT test case — select, test, process findings, fix or log, and close the cycle.

Validate module boundaries, check for architectural drift, and suggest fitness function tests. Compares actual code structure against ARCHITECTURE.md.

Execute comprehensive backlog review. Analyzes story quality, Definition of Ready compliance, dependencies, zombie stories, and generates a backlog health report.

First-run framework setup. Detects existing project stack or guides new project creation from vision/braindump.

Use when the user has a complex idea that needs design exploration before story decomposition.

Build a project from a plain-English description. Handles all technical decisions automatically. Designed for non-technical users but useful for anyone who wants fast results.

Incremental code logic verification of UAT test cases — pick batch, trace code, fix issues, update tracking.

Analyzes code quality, complexity, duplication, and architectural patterns. Use after implementing features, during code review, or when preparing for PR. Auto-invoke when user has completed significant code changes or asks to review code quality.

Create a well-formatted conventional commit with proper message structure. Use when ready to commit changes.

Resume development with smart session continuation. Reads session handoff files, sprint spec, analyzes git state, and determines the best path forward.

Create project-specific hook scripts and register them in settings.json. Extends the framework's enforcement layer.

Sprint status overview with session insights, sprint trends, and actionable next steps.

Use when the user reports a bug, error, or unexpected behavior that needs investigation.

Deploy the project to a hosting platform. Detects deployment configuration, runs pre-deploy checks, and guides first-time setup.

Deep guided elicitation for new projects. Archetype-aware, research-backed, multi-phase discovery with assumption tracking and Phase Transition Stories.

Validate framework configuration, check runtime dependencies, and report issues. Use when something isn't working or after setup.

Fix a GitHub issue following project coding standards. Creates branch, implements fix with TDD, and prepares PR.

Upgrade Exosuit to a newer version while preserving project customizations.

Generate a structured handoff document for ending a development session. Saves to docs/sessions/ for the continue skill to read.

Natural language skill discovery — describe what you want to do and get matched to the right skill.

Use when the user has an idea or requirement to decompose into backlog stories.

Prepare for manual testing session with test plan based on known issues, recent changes, and acceptance criteria.

Use when the user is inside a parallel stream (worktree branch) and wants to bring that branch up to date with the LATEST of its parent branch — typically after one or more sibling streams have merged their work up into the parent (via /merge-up). Pulls the parent's accumulated commits down into the current branch with a true merge. Inverse of /merge-up; the parent is recorded by /parallel-work in git config (branch.<name>.exosuitParent). Read-only on the parent — safe to run while the parent...

Use when the user is inside a parallel stream (worktree branch) and wants to merge that branch's committed work into the parent branch it was created from, then bring the stream back up to date with the parent. True merge (keeps individual commits); prompts before pushing the parent. Pairs with /parallel-work, which records the parent in git config (branch.<name>.exosuitParent), and with /merge-down (the inverse direction).

Use when the user wants to autonomously improve a measurable metric through iterative experimentation with git-based checkpointing and automatic rollback.

Work on multiple stories at the same time. Creates isolated parallel streams (git worktrees) from the current branch, wires up local settings, and opens each in its own Claude Code session. Also shows stream status and cleans up finished streams. Pairs with /merge-up (publish a stream's work to the parent branch) and /merge-down (pull the parent's accumulated work into a stream).

Analyze performance patterns — N+1 queries, unbounded operations, blocking I/O, memory leaks, and scaling behavior. Auto-invoke after performance-sensitive code changes.

Phase transition review — walkthrough built features, validate assumptions, refresh research, decide direction, and plan next phase.

Check status of open pull requests and provide options for next steps. Use to review PR status, handle feedback, or merge approved PRs.

Unified quality gate dispatcher. Runs selected quality checks with profile-aware defaults.

Guided interactive tour of the framework. Walks through your first sprint from zero to shipped PR.

Use when the user wants iterative self-improvement on a deliverable (document, implementation, prompt, design) until completion criteria are met.

Deep online research on any topic. Produces structured reports with citations and confidence scores. Three depth modes — quick scan, standard investigation, or deep dive.

Sprint retrospective — consumes progress.md Metrics table, adds leading-lagging analysis, anti-pattern detection, and 4Ls framework.

Security review for code touching authentication, credentials, file access, or user data. Includes CWE checklist ranked by AI vulnerability frequency, phantom package detection, ASVS-aligned controls, and supply chain checks. MANDATORY for auth code, credential handling, file operations with user data, network comms, or database queries with user input.

Analyze the repository's technology stack and generate appropriate skills, rules, and hook configurations.

Use when you want to test, measure, or compare skill effectiveness. Supports eval, compare, metrics, baseline capture, and regression detection.

Use when the user wants to ship a sprint's work to main via PR.

Pre-sprint checks, feature branch creation, and sprint planning. Ensures clean state, defines sprint goal and scope, creates sprint spec document.

Use when the user wants to implement a single story or deliver a backlog item.

Validates test coverage, quality, and TDD compliance. Detects weakened assertions, deleted tests, and tautological patterns. Auto-invoke when user has written code and needs test validation.

Process a single user testing feedback item — classify, fix or log, verify, and report.

Safely discard or revert failed implementation attempts and restore a clean working state.

Cleanly remove the Exosuit framework from a project while preserving project-specific content.

Execute comprehensive weekly maintenance routine (1-2 hours, Friday recommended). Includes health checks, quality review, dependency governance, activity insights, and planning.