Go Repository TDD Builder Agent Skill

Drives test-driven development for Go persistence layers with PostgreSQL integration tests, repository implementations, and error…

Context cost
5.5k tokensestimated from the bundle, loaded when it triggers
Bundle
2 files · 22.0 kBtext throughout, nothing executable
Licence
MITthe author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

永続化層の一つの単位(集約のリポジトリか手順の口)を、コマンドデータモデルと物理設計の資料から、実物の PostgreSQL のテストを先に書いて赤を確かめ、pgx/v5 と sqlc で実装して緑にし、整える。「このリポジトリを実装して」「Outbox の回収の口を書いて」「コマンドデータモデルの BDD をテストにして」と言われたときに使う。読み取りのポートを満たす Query の実装は扱わない。

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

databasepostgresqltdd
Filed under

Databases

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md13.6 kB · preview
--- name: develop-repository ---
6# develop-repository
7
8中心にあるのは二つの考えである。**資料が決めたテーブルの型と制約をそのまま写す。** テーブル、列、制約はコマンドデータモデルが、分離レベル、index、読み取りの SQL の一覧は物理設計が決め、食い違ったら資料の持ち主へ返す。物理設計が操作ごとに決めた業務の結果(更新が0件のとき、外部キー、一意制約、CHECK の違反、やり直しの扱い)は、この skill の既定より優先する。下に書いた結果は、物理設計が決めていないときの既定である。**永続化層は判断しない。** Find は読んで値にするだけで、判断はコマンドが、トランザクションは usecase が持つ。
9
10進め方と赤は development-convention の develop-inside-out に、トランザクション、翻訳、時計、ID ジェネレーターの契約は apply-crosscutting-contracts に、付け替えは handle-errors、テストの共通の形は apply-go-test-convention に従う。イミュータブルデータモデルを選んだ場合の形は [貸出の永続化の例](references/example.md) にある。
11
12## テーブルの型を写す
13
14コマンドデータモデルが選んだ保存型を写す。リソース中心なら、資料が決めた現在の値をリソースの表に保存する。イベントを結果として返すコマンドでも、イベント履歴の表は要求しない。イミュータブルデータモデルなら三つのテーブルに出来事を積む。**リソースのテーブル**は集約が生まれたときに決まる事実を持ち、生成の Apply が一行を追加する。リソースは現在の状態と版を列(status、current_version)に持つので、状態を変える Apply は、同じトランザクションで読んだ版を条件にその列を更新し、0件なら、物理設計が決めた業務の結果を、決めていなければ「同時更新で競合した」を返す。**基底イベントのテーブル**(<対象>_base_events)は、識別子、種類、版、出来事の時点(occurred_at の一列だけ)を持ち、Apply はどれも一行を追加する。**詳細イベントのテーブル**(<対象>_<過去分詞>_events)は出来事に固有の業務が与えた値を持ち、主キーは基底イベントの識別子で、固有の値が無くても一行を追加する。派生のテーブルがあれば同じトランザクションで更新する。
15
16イミュータブルデータモデルでは、版はイベントの版をそのまま書き、同じ版の一意制約の違反は「同時更新で競合した」へ翻訳する。リソース中心の版と競合の扱いは資料と物理設計に従い、履歴の版を発明しない。イベント履歴を保存する場合の occurred_at は、イベントがコマンドの判断に使った時点を持てばその値、持たなければ Apply が時計から一度だけ取った値を、同じ操作の全部の行に写す。判断に使わない時刻をドメインから受け取らず、ここに閉じ込める(基準は development-convention の apply-layer-convention)。後続の要求を伴うイベントなら、同じトランザクションで Outbox の要求の行も追加する。値の範囲の CHECK は、ドメインモデルが値の正しさを持つ業務のテーブルには置かない。
17
18## リポジトリ:Find は判断せず、資料どおり保存する
19
20どのメソッドも、ctx のトランザクションから sqlc の Queries を組む。Find<返す型> は、コマンドを直ちに呼べる完全な集約を一つ返す。保存された状態なら行の状態から型を選んで Restore* で組み、行が無ければ「存在しない」(初期状態の型を和型に入れた集約では、材料を集めた初期状態の型)、知らない状態の値は保存値の破損とする。初期状態の型なら、判断に要る外の事実を読んで持たせるだけで、上限を見て拒んだり読み方を変えたりしない。資料が値の選び方(閾値、経路)を定めていても、リポジトリで判断せず、コマンドが決めてイベントに載せる形を返す。書き込みのメソッドはドメインのポートと資料の保存型に従う。イベント履歴を保存する Apply<イベント名> は error だけを返す。
21
22行からドメインへは New* を通し、拒まれたら「回復不能」へ付け替える。ドメインから行へは、リポジトリの直下の marshaller package の純粋な関数が、保存する結果と、一回の保存で共有する値から sqlc の引数を作る。イベント履歴を保存する場合は、名前を <イベント>To<query>Params にし、Apply<イベント名> が時刻と識別子を一度だけ取ってその関数の結果を query へ渡す。変換が時計も ID ジェネレーターも読まないので、同じ保存の全部の行に同じ値が写り、書き込みにはどの行をどの順で書くかだけが残るからである。有限な値の列は値を所有する package の定義を使う。制約(一意、外部キー、CHECK)の違反から、物理設計が決めた業務の結果の具体エラーへの対応は、リポジトリが一つの rdb.Constraints で持つ。
23
24SQL は sqlc の query のファイルにだけ書き、読み取りは物理設計の読み取りの一覧(Read-001 のような)に載っているものに限る。載っていない読み取りが要るなら、足さずに物理設計の資料へ返す。ロックを取る読み取りは物理設計が指定したときだけ書く。
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md235 words
Files2
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈60
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
5,440
on trigger
The instruction body and 1 supporting file, read only when the skill fires.
2.8%
of a 200k window
Ten skills this size would take about 28% of the window before you open a file.
050k100k150k200k context window

5.5k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

2 files, 22.0 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md13.6 kB
  • references/example.md8.4 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 2 files you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Go Repository TDD Builder · 5.5k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/go-repository-tdd-builder/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/go-repository-tdd-builder" ] && { [ ! -e .claude/skills/go-repository-tdd-builder ] || { mv .claude/skills/go-repository-tdd-builder "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/go-repository-tdd-builder" .claude/skills/ && echo "Installed .claude/skills/go-repository-tdd-builder"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add nakamori-naoya/go-repository-tdd-builder

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/go-repository-tdd-builder/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/go-repository-tdd-builder/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/go-repository-tdd-builder" ] && { [ ! -e ~/.claude/skills/go-repository-tdd-builder ] || { mv ~/.claude/skills/go-repository-tdd-builder "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/go-repository-tdd-builder" ~/.claude/skills/ && echo "Installed ~/.claude/skills/go-repository-tdd-builder" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/go-repository-tdd-builder/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as develop-repository in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, go-repository-tdd-builder.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencenakamori-naoya/go-repository-tdd-builder

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

NN
nakamori-naoya

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill