Menu
SkillsMP has collected 21 skills from coleam00/ai-native-starter-pack. Open a skill to review its source and details.
Showing 21 of 21 collected skills.
Slice an epic or next-epic doc into PIV-sized tickets with a dependency graph. Turns a large strategic doc into the discrete units of work that the PIV loop consumes. Accepts a Confluence page id OR a local PRD/epic doc path; optionally cross-references a…
Drive a real browser to validate web apps end-to-end. Use when you need to navigate to a URL, interact with UI elements, fill forms, click buttons, take screenshots, assert page state, or run a full end-to-end validation flow for a web feature. The primary…
Derive the AI Layer's global rules (CLAUDE.md) and on-demand context modules FROM an existing codebase by analyzing its real structure, conventions, and patterns. Use on a brownfield codebase that has no CLAUDE.md yet (Brownfield Type A) to build the…
Creates a comprehensive, context-rich implementation plan through deep codebase analysis and external research. Use when you have a feature request and need a one-pass-ready plan before writing any code.
Primes the agent with focused understanding of the backend portion of the codebase — API routes, services, data models, and database layer — without loading unrelated frontend code. Use at the start of a session when the work is scoped to API endpoints,…
Primes the agent with focused understanding of the frontend portion of the codebase — components, routing, state management, and styling — without loading unrelated backend code. Use at the start of a session when the work is scoped to UI or client-side…
Fixes bugs surfaced by a manual or AI code review, one at a time, with tests, then runs full validation. Use after a code review has produced a list of issues or a review file.
Performs a technical code review of recently changed files for bugs, security issues, and standards compliance, then writes a report. Use before committing, as a pre-commit quality gate.
Creates a new git commit for all uncommitted changes with an atomic, conventionally-tagged message. Use when work is complete and ready to be committed.
Generates a comprehensive Product Requirements Document from the current conversation context. Use when requirements have been discussed and you need to formalize them into a professional PRD before planning.
Autonomously develops a complete feature from priming through planning, execution, and commit by chaining the four core PIV-loop skills. Use when you want a full hands-off feature build from a single description.
Executes an implementation plan task-by-task with validation at every step. Use when you have a completed feature plan and want to implement it in one pass.
Generates a structured implementation report reflecting on a just-completed feature — what was done, divergences, challenges. Use right after finishing an implementation, as the input to a system review.
Implements a bug fix for a GitHub issue based on its RCA document, adds regression tests, and validates. Use after an RCA document exists and you are ready to fix the issue.
Set up and run THIS project locally from a fresh clone — environment, dependencies, database/services, migrations, seed, and the dev server. Reads the project's own setup docs rather than assuming.
Merges two feature branches from worktrees through a safe integration branch with full testing and validation at each step. Use when parallel worktree development is done and the features need to be integrated.
Sets up one or two git worktrees with dependency sync and health-check verification, running parallel setup with two agents when two branches are given. Use when starting parallel feature development in isolated worktrees.
Primes the agent with deep codebase understanding by analyzing structure, documentation, and key files. Use when starting work on a codebase, at the beginning of a session, or when you need a fast orientation before planning or implementing. Optionally pulls…
Investigates a GitHub issue, identifies the root cause, and writes a structured RCA document for later implementation. Use when you need to diagnose a bug reported as a GitHub issue before fixing it.
Performs a meta-level review of how well an implementation followed its plan, classifying divergences and recommending AI-Layer improvements. Use after an execution report exists to find bugs in the process, not the code.
Run THIS project's full quality gate — tests, type-check, lint, and (for full-stack) the build — and report overall health with ✅/❌. Use before opening a PR; this is the gate that runs BEFORE the PR, not after.