w7-mgfcode

Manage GitHub repositories end to end - issues, labels, pull request workflows, branch protection, semantic-version releases, GitHub Actions CI, and deployment to Vercel, Google Cloud Run, and AWS. Use when setting up or fixing CI workflows, writing issue or…

Decomposes large GitHub work into a milestone → umbrella → epic → subtask hierarchy using gh CLI, native sub-issues, issue types, and Projects v2, with a deterministic slice-scoring engine that decides how many children each level should have. Use when…

Generate and maintain a repository's agent-instruction files — AGENTS.md (canonical), CLAUDE.md and GEMINI.md (thin shims that import AGENTS.md), README.md (for humans), and an optional llms.txt — with cross-file consistency, single-source-of-truth (no…

Turn an ambiguous request into a grounded plan, an evidence-backed execution, and a reviewed result. Use for non-trivial coding tasks that benefit from a plan→execute→review loop.

Analyzes any workflow material (attached document, pasted text, or URL) and maps it into a repo-ready integration plan. Detects material type, extracts reusable patterns, explains the workflow in Hungarian, generates English keyword flows in…

Turns a GitHub issue (number or URL) into an execution-ready 5-subtask work package. Resolves the issue across enterprise repos via gh CLI, traces parents, children, dependencies, blockers, milestones, builds a brief + source-of-truth + role-relevant scope,…

Runs a role-based intake interview that progressively elicits skill requirements from the user, validates completeness against complexity tier rules, and outputs a structured input brief ready for the skill-generator pipeline. Accepts URLs as input and…

Processes CodeRabbit PR review comments one by one, leveraging the "Prompt for AI Agents" codegen block when present, applying minimal safe fixes, auto-detecting validation, and auto-posting concise replies. Use when a user wants to "process coderabbit…

Analyzes workflow documents, pasted text, URLs, or repository processes; extracts reusable entities, verbs, boundaries, gates, artifacts, failure paths, and variables; inspects actual repository capabilities; then compares three to five normalized, scored…

Creates, audits, and safely updates canonical repository instructions, thin provider shims, human-facing README content, and optional llms.txt indexes. Uses repository evidence, managed regions, deterministic validation, a shown diff, and explicit approval…

Plans and initializes a new software project through one-question-at-a-time discovery, current primary-source research, explicit recommendations and trade-offs, selected host and assistant profiles, an approved file manifest, and deterministic verification.…

Analyzes workflow documents, pasted text, URLs, or repository processes; extracts reusable entities, verbs, boundaries, gates, artifacts, failure paths, and variables; inspects actual repository capabilities; then compares three to five normalized, scored…

Creates, audits, and safely updates canonical repository instructions, thin provider shims, human-facing README content, and optional llms.txt indexes. Uses repository evidence, managed regions, deterministic validation, a shown diff, and explicit approval…

Plans and initializes a new software project through one-question-at-a-time discovery, current primary-source research, explicit recommendations and trade-offs, selected host and assistant profiles, an approved file manifest, and deterministic verification.…

Reviews release notes for missing compatibility evidence and rollback steps. Use when preparing a Polymind-compatible release record.

Exercise strict frontmatter checks during validator tests; do not use this deliberately invalid package as a canonical or projected skill.

Validate, scope, and prepare one small, evidence-backed Git commit without silently staging unrelated work. Use when a user asks to create, automate, review, or improve commit quality, especially in a dirty repository with multiple workstreams or explicit…

Apply FPAT Lite's prime, brainstorm, plan, implement, validate, or handoff workflow to repository work. Use when the user names FPAT Lite, asks for a governed coding workflow, or requests one of these six modes.

Apply FPAT Lite's prime, brainstorm, plan, implement, validate, or handoff workflow to repository work. Use when the user names FPAT Lite, asks for a governed coding workflow, or requests one of these six modes.

FPAT scoring rubrics — the 7-dimension execution rubric for shaping subtasks inside an epic, and the 5-dimension continuation rubric (ship gate >= 40) for deciding which epics ship. Use when running /fpat-plan-issue, /fpat-continuation, or otherwise scoring…