AgentStack
mwillbanks avatar

mwillbanks

14 listings · 0 installs

Open-source publisher. Listings imported from github.com/mwillbanks — credited to the original author with their license.

↗ github.com/mwillbanks
14 results
Self-run
SKILL

Ts Code Validation Gate

Evaluates completed TypeScript changes before review using a fail-closed evidence gate across formatting/linting, unit tests, semgrep, osv-scanner, and fallow, and blocks new review attempts until prior remediation-ledger items are fully resolved.

0
4
Free
Self-run
SKILL

Github Pr Review

Review GitHub pull requests directly in GitHub using GitHub MCP or gh, leave precise inline comments and final review states, and apply hard-nosed scrutiny for security, architecture, maintainability, testing, accessibility, and frontend compliance. Use whenever the user asks to review a PR, inspect a GitHub pull request, request changes, re-review a PR, post inline review comments, or submit a G…

0
3
Free
Self-run
SKILL

Code Discipline

Prevent trivial helpers, wrapper layers, rename-only utilities, duplicate constants, and local reinvention. Enforce reuse of platform primitives, framework capabilities, shared utilities, and proven libraries. Use when adding or reviewing helper sprawl, object-vs-positional parameter decisions, arrow-vs-declaration choices, class-vs-functional design, god-file boundaries, schema-file boundaries,…

0
2
Free
Self-run
SKILL

Frontend System Discipline

Prevent frontend work from inventing local design tokens, theme constants, helper layers, or style-file sprawl. Use when building or reviewing UI, components, pages, theme tokens, styled files, composition, or helper placement in frontend code.

0
2
Free
Self-run
SKILL

Agent Execution Mode

Parent-agent execution policy for implementation, validation, delegation, and mandatory code review orchestration through the code_review_ts sidecar.

0
2
Free
Self-run
SKILL

Repo Standards Enforcement

Use this skill to enforce repository-wide standards for toolchain compliance, package-manager purity, type safety, testing, maintainability, and architecture. When a more specific skill exists for a concern such as final linting or formatting remediation, that more specific skill takes precedence over this skill's generalized guidance.

0
2
Free
Self-run
SKILL

Cloud Native Runtime

>-

0
2
Free
Self-run
SKILL

Spec Change Governance

Govern spec amendments without losing history, completed work, or review context. Use when the user wants to change requirements, amend a plan, update a spec in place, mark superseded items, rerun clarification or planning, or prevent spec drift during rework.

0
2
Free
Self-run
SKILL

Review Remediation Gate

Close review findings deterministically, remediate blocking issues, and prove review closure. Use when the user says to fix review comments, address review findings, run a review-remediation pass, close out blockers, or finish work only after review issues are resolved.

0
3
Free
Self-run
SKILL

Biome Enforcement

Use this skill when a task touches code, tests, Biome config, or generated artifacts and Biome must remain the final remediation and enforcement pass using the required JSON changed-files command.

0
2
Free
Self-run
SKILL

Project Tracker

Coordinate ticket tracking and time tracking before, during, and after implementation work. Use whenever a prompt starts with `/ProjectTracker`, includes Jira keys like `AIA-123`, includes ClickUp custom IDs like `SL-7007`, or asks to sync work across parent and child boards while logging time.

0
2
Free
Self-run
SKILL

Requirements Traceability Matrix

Build a requirements-to-implementation trace matrix that proves coverage and exposes gaps. Use when the user asks to trace requirements, map specs to code, prove coverage, identify missing validation, or build a matrix for review, planning, or compliance work.

0
3
Free
Self-run
SKILL

Execution Alignment Gate

Detects materially ambiguous or under-specified requests, selects the right clarification target, and enforces bounded alignment before execution, including spec-governed continuations and approval-gated manager handoffs. Use when ambiguity could cause wrong deliverables, wrong scope, wrong implementation path, avoidable rework, or token waste from repeated follow-up.

0
5
Free
Self-run
SKILL

Speckit Feature Orchestrator

Orchestrates a full Speckit feature workflow from constitution amendment through specification, clarification, plan, tasks, and analysis as a chief-architect governor using subagents. Use when the repository already uses Speckit or the user explicitly asks for Speckit and wants to discuss, refine, or directly drive a new feature into implementation-ready Speckit artifacts in one controlled pass.

0
6
Free
You've reached the end · 14 loaded