tt-a1i

63 mods across 10 repositories, 35k stars between them.

archify

01

tt-a1i/archify

Skill Claude CodeCodex

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…

34k yesterday A 130 tokens original MIT

hive AGENTS.md

02

tt-a1i/hive

Instructions file CodexOpenCode

AGENTS.md instructions for tt-a1i/hive, covering agents.md, hard bans, no test-only production fallbacks, no broad exception swallowing and no fake tests.

482 2mo ago A 502 tokens

hive CLAUDE.md

03

tt-a1i/hive

Instructions file

Claude Code instructions for tt-a1i/hive, covering claude.md, what hive is, public development source of truth and engineering rules.

482 2mo ago A 377 tokens

simplify-codebase

04

tt-a1i/simplify-codebase

Skill Claude CodeCodex

Simplification audit or authorized codebase simplification whose stated objective is to remove accidental complexity. Use for evidence-backed deletion or consolidation of dead code, duplicate state, redundant APIs or layers, ownerless abstractions, obsolete compatibility or design records, and over-engineering in any…

356 4d ago A 93 tokens original MIT

tt-a1i

05

tt-a1i/matt-skills-with-to-goal

Plugin Claude Code

Matt Pocock's engineering skills with verifiable goal handoffs and automated forked spec execution.

116 4d ago A tokens not measured original MIT

tt-a1i/matt-skills-with-to-goal

Instructions file CodexOpenCode

Instructions for tt-a1i/matt-skills-with-to-goal, a project described as: Planning → verifiable goals → fresh-session implementation for AI coding agents. Based on mattpocock/skills v1.1.

116 4d ago A 4 tokens copy · 100% MIT

ask-matt

09

tt-a1i/matt-skills-with-to-goal

Skill Claude CodeCodex

Ask which skill or flow fits your situation. A router over the skills in this repo.

116 4d ago A 22 tokens copy · 86% MIT

code-review

10

tt-a1i/matt-skills-with-to-goal

Skill Claude CodeCodex

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use…

116 4d ago A 94 tokens copy · 89% MIT

codebase-design

11

tt-a1i/matt-skills-with-to-goal

Skill Claude CodeCodex

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

116 4d ago A 57 tokens copy · 100% MIT

diagnosing-bugs

12

tt-a1i/matt-skills-with-to-goal

Skill Claude CodeCodex

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

116 4d ago A 40 tokens copy · 92% MIT

domain-modeling

13

tt-a1i/matt-skills-with-to-goal

Skill Claude CodeCodex

Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

116 4d ago A 43 tokens copy · 91% MIT

tt-a1i/matt-skills-with-to-goal

Skill Claude CodeCodex

Orchestrate one approved SPEC READY through a same-directory Codex App fork: create and name the execution task, ask it to run spec-executor, route decisions through Codex Task Messenger, validate the returned receipt, and archive a completed child. Use only when the user explicitly asks to execute an approved spec in…

116 4d ago A 117 tokens original MIT

goal-crafter

15

tt-a1i/matt-skills-with-to-goal

Skill Claude CodeCodex

Craft verifiable, tight goal prompts for AI coding agents (Claude Code /goal, Codex Automations, Pi), either from a standalone task interview or from an already-approved to-goal handoff. Use when the user says "给我一个 goal 提示词", "帮我写个 goal", "设置一个自动化任务", "我想让 agent 自动做 X", or asks to turn a task into a self-running…

116 4d ago A 113 tokens original MIT

grill-with-docs

16

tt-a1i/matt-skills-with-to-goal

Skill Claude CodeCodex

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

116 4d ago A 30 tokens copy · 100% MIT

prototype

19

tt-a1i/matt-skills-with-to-goal

Skill Claude CodeCodex

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

116 4d ago A 39 tokens copy · 94% MIT

research

20

tt-a1i/matt-skills-with-to-goal

Skill Claude CodeCodex

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

116 4d ago A 49 tokens copy · 100% MIT

roundtable

22

tt-a1i/matt-skills-with-to-goal

Skill Claude CodeCodex

Convene a roundtable of sub-agents that debate a decision or proposal from opposing perspectives — parallel independent statements, anonymous cross-review, then a chaired verdict reporting consensus and dissent.

116 4d ago A 39 tokens original MIT

tt-a1i/matt-skills-with-to-goal

Skill Claude CodeCodex

Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

116 4d ago A 44 tokens copy · 92% MIT

spec-executor

24

tt-a1i/matt-skills-with-to-goal

Skill Claude CodeCodex

Execute the latest approved SPEC READY from an inherited or forked conversation, keeping implementation work out of the planning thread. Use after to-spec when the final spec fits one implementation session and the new thread should implement, test, review, and return a structured receipt without rewriting a to-goal…

116 4d ago A 96 tokens original MIT