本文へ移動
cccskills
無料GitHub で公開日本語紹介

statechart

TLA+モデルや合意済みの図から状態遷移図を作り、ルール違反に至る経路を示して、システムの設計や不具合を確認するスキルです。

原文原文の説明を見る

Check a TLA+ model of a system that moves between states, such as a product flow, a protocol, or a service, and draw it as a Mermaid statechart. The report gives the shortest path to each state that breaks a rule. Use for /statechart, or to show a bug as a path through states.

michael-denyer/pstack-claudeスター 3,612(GitHub 3,612 + cccskills 0)

実行スコア 未検証

インストール方法を見る

こんなときに便利

  • 状態遷移を図で確認したいとき
  • ルール違反に至る経路を探したいとき
  • 合意した図からモデルを作りたいとき

日本語での紹介

できること

システムがどの状態からどこへ移るかを、Mermaidの状態遷移図にします。TLA+モデルがある場合や、コード・設計をモデル化できる場合は、モデルから図を作成します。まだモデルがない場合は、関係者が合意した図からTLA+の骨組みを生成できます。状態には読み手が観察できる内容を、遷移にはきっかけとなるイベントを記し、変数名やアクション名は図のラベルに出しません。合意したルールを不変条件として確認し、破られる場合は番号付きの経路で示します。コードをモデル化したときは、不具合の経路を実際のコードで再現できるかも確かめます。

こんなときに便利

プロダクトの画面遷移、プロトコル、サービスの動きを、開発者以外も読める図で確認したいときに役立ちます。設計レビューでルール違反の経路を探す場合や、既存コードの挙動を仕様と照らし合わせたい場合にも向いています。

使い方の例

  • 「このTLA+モデルから状態遷移図を作って」
  • 「このサービスの不具合が起きる経路を図で示して」
  • 「合意済みの状態図からTLA+の骨組みを作って」

注意点

実行にはJavaとTLCが必要です。初回実行時はmise経由でインストールされ、約305MBのダウンロードにネットワーク接続を使います。既存のJavaとTLCを使う方法も案内されています。

この紹介文は、公開されている SKILL.md をもとに AI（OpenAI Codex）が作成しました。正確な仕様は下の原文を確認してください。

含まれるファイル（200）

  • SKILL.md8.9 KB
  • references/render.md3.6 KB
  • scripts/backends/cfg.ts1.2 KB
  • scripts/backends/mermaid.ts7.3 KB
  • scripts/backends/plain-text.ts2.3 KB
  • scripts/backends/report.ts6.9 KB
  • scripts/bun.lock555 B
  • scripts/frontends/config.ts10.4 KB
  • scripts/frontends/dot.ts2.4 KB
  • scripts/frontends/marks.ts3.2 KB
  • scripts/frontends/messages.ts1.8 KB
  • scripts/frontends/spec.ts4.1 KB
  • scripts/frontends/trace.ts988 B
  • scripts/frontends/value.ts4.6 KB
  • scripts/frontends/verdict.ts1.7 KB
  • scripts/frontends/view.ts4.3 KB
  • scripts/ir.ts14.8 KB
  • scripts/package.json233 B
  • scripts/passes/annotate.ts3.7 KB
  • scripts/passes/label.ts8.4 KB
  • scripts/passes/lift.ts2.8 KB
  • scripts/passes/loop-check.ts2.1 KB
  • scripts/passes/paths.ts1.9 KB
  • scripts/passes/reach.ts4.0 KB
  • scripts/passes/region-check.ts3.4 KB
  • scripts/passes/regions.ts9.3 KB
  • scripts/pipeline.ts2.9 KB
  • scripts/run.ts16.9 KB
  • scripts/statechart991 B
  • scripts/statechart.ts5.9 KB
  • scripts/test/chart.test.ts38.8 KB
  • scripts/test/charts/Braces.mmd312 B
  • scripts/test/charts/Escapes.mmd244 B
  • scripts/test/charts/Phases.mmd584 B
  • scripts/test/cli.test.ts49.2 KB
  • scripts/test/config-fuzz.test.ts8.5 KB
  • scripts/test/ConfigOracle.java2.7 KB
  • scripts/test/corpus.test.ts12.5 KB
  • scripts/test/corpus/Counter/chart.mmd112 B
  • scripts/test/corpus/Counter/ChartRun.out2.6 KB
  • scripts/test/corpus/Counter/Counter.cfg64 B
  • scripts/test/corpus/Counter/Counter.tla185 B
  • scripts/test/corpus/Counter/graph.dot633 B
  • scripts/test/corpus/Counter/report.md243 B
  • scripts/test/corpus/Counter/sany.out37.3 KB
  • scripts/test/corpus/Counter/verdict-1.out2.1 KB
  • scripts/test/corpus/CounterAction/chart.mmd518 B
  • scripts/test/corpus/CounterAction/ChartRun.out2.7 KB
  • scripts/test/corpus/CounterAction/CounterAction.cfg89 B
  • scripts/test/corpus/CounterAction/CounterAction.tla255 B
  • scripts/test/corpus/CounterAction/graph.dot798 B
  • scripts/test/corpus/CounterAction/report.md436 B
  • scripts/test/corpus/CounterAction/sany.out42.9 KB
  • scripts/test/corpus/CounterAction/verdict-1.exit3 B
  • scripts/test/corpus/CounterAction/verdict-1.out2.1 KB
  • scripts/test/corpus/CounterAction/verdict-2.exit3 B
  • scripts/test/corpus/CounterAction/verdict-2.out3.1 KB
  • scripts/test/corpus/CounterAction/verdict-3.out2.6 KB
  • scripts/test/corpus/CounterDeadlock/chart.mmd462 B
  • scripts/test/corpus/CounterDeadlock/ChartRun.out2.7 KB
  • scripts/test/corpus/CounterDeadlock/CounterDeadlock.cfg63 B
  • scripts/test/corpus/CounterDeadlock/CounterDeadlock.tla225 B
  • scripts/test/corpus/CounterDeadlock/graph.dot633 B
  • scripts/test/corpus/CounterDeadlock/report.md624 B
  • scripts/test/corpus/CounterDeadlock/sany.out41.8 KB
  • scripts/test/corpus/CounterDeadlock/verdict-1.exit3 B
  • scripts/test/corpus/CounterDeadlock/verdict-1.out2.1 KB
  • scripts/test/corpus/CounterDeadlock/verdict-2.exit3 B
  • scripts/test/corpus/CounterDeadlock/verdict-2.out3.0 KB
  • scripts/test/corpus/CounterFan/chart.mmd1.7 KB
  • scripts/test/corpus/CounterFan/ChartRun.out3.1 KB
  • scripts/test/corpus/CounterFan/CounterFan.cfg37 B
  • scripts/test/corpus/CounterFan/CounterFan.tla338 B
  • scripts/test/corpus/CounterFan/graph.dot5.3 KB
  • scripts/test/corpus/CounterFan/report.md239 B
  • scripts/test/corpus/CounterFan/sany.out48.4 KB
  • scripts/test/corpus/CounterFan/verdict-1.exit3 B
  • scripts/test/corpus/CounterFan/verdict-1.out2.4 KB
  • scripts/test/corpus/CounterFan/verdict-2.out2.6 KB
  • scripts/test/corpus/CounterGuard/chart.mmd63 B
  • scripts/test/corpus/CounterGuard/ChartRun.exit3 B
  • scripts/test/corpus/CounterGuard/ChartRun.out3.3 KB
  • scripts/test/corpus/CounterGuard/CounterGuard.cfg66 B
  • scripts/test/corpus/CounterGuard/CounterGuard.tla192 B
  • scripts/test/corpus/CounterGuard/graph.dot302 B
  • scripts/test/corpus/CounterGuard/report.md954 B
  • scripts/test/corpus/CounterGuard/sany.out36.1 KB
  • scripts/test/corpus/CounterGuard/verdict-1.exit3 B
  • scripts/test/corpus/CounterGuard/verdict-1.out2.4 KB
  • scripts/test/corpus/CounterGuard/verdict-2.exit3 B
  • scripts/test/corpus/CounterGuard/verdict-2.out2.9 KB
  • scripts/test/corpus/CounterInitPast/chart.mmd282 B
  • scripts/test/corpus/CounterInitPast/ChartRun.out2.5 KB
  • scripts/test/corpus/CounterInitPast/CounterInitPast.cfg54 B
  • scripts/test/corpus/CounterInitPast/CounterInitPast.tla169 B
  • scripts/test/corpus/CounterInitPast/graph.dot84 B
  • scripts/test/corpus/CounterInitPast/report.md425 B
  • scripts/test/corpus/CounterInitPast/sany.out35.3 KB
  • scripts/test/corpus/CounterInitPast/verdict-1.exit3 B
  • scripts/test/corpus/CounterInitPast/verdict-1.out1.3 KB
  • scripts/test/corpus/CounterInitPast/verdict-2.out2.5 KB
  • scripts/test/corpus/CounterInitPastHolds/chart.mmd16 B
  • scripts/test/corpus/CounterInitPastHolds/ChartRun.out2.5 KB
  • scripts/test/corpus/CounterInitPastHolds/CounterInitPastHolds.cfg50 B
  • scripts/test/corpus/CounterInitPastHolds/CounterInitPastHolds.tla171 B
  • scripts/test/corpus/CounterInitPastHolds/graph.dot84 B
  • scripts/test/corpus/CounterInitPastHolds/report.md211 B
  • scripts/test/corpus/CounterInitPastHolds/sany.out34.8 KB
  • scripts/test/corpus/CounterInitPastHolds/verdict-1.out2.0 KB
  • scripts/test/corpus/CounterInstance/chart.mmd326 B
  • scripts/test/corpus/CounterInstance/ChartRun.out2.8 KB
  • scripts/test/corpus/CounterInstance/CounterInstance.cfg41 B
  • scripts/test/corpus/CounterInstance/CounterInstance.tla217 B
  • scripts/test/corpus/CounterInstance/CounterSteps.tla113 B
  • scripts/test/corpus/CounterInstance/graph.dot599 B
  • scripts/test/corpus/CounterInstance/report.md295 B
  • scripts/test/corpus/CounterInstance/sany.out73.3 KB
  • scripts/test/corpus/CounterInstance/verdict-1.exit3 B
  • scripts/test/corpus/CounterInstance/verdict-1.out3.0 KB
  • scripts/test/corpus/CounterJump/chart.mmd547 B
  • scripts/test/corpus/CounterJump/ChartRun.out2.7 KB
  • scripts/test/corpus/CounterJump/CounterJump.cfg57 B
  • scripts/test/corpus/CounterJump/CounterJump.tla303 B
  • scripts/test/corpus/CounterJump/graph.dot1.0 KB
  • scripts/test/corpus/CounterJump/report.md374 B
  • scripts/test/corpus/CounterJump/sany.out44.9 KB
  • scripts/test/corpus/CounterJump/verdict-1.exit3 B
  • scripts/test/corpus/CounterJump/verdict-1.out2.1 KB
  • scripts/test/corpus/CounterJump/verdict-2.out2.6 KB
  • scripts/test/corpus/CounterLoop/chart.mmd320 B
  • scripts/test/corpus/CounterLoop/ChartRun.out2.6 KB
  • scripts/test/corpus/CounterLoop/CounterLoop.cfg41 B
  • scripts/test/corpus/CounterLoop/CounterLoop.tla232 B
  • scripts/test/corpus/CounterLoop/graph.dot593 B
  • scripts/test/corpus/CounterLoop/report.md285 B
  • scripts/test/corpus/CounterLoop/sany.out41.5 KB
  • scripts/test/corpus/CounterLoop/verdict-1.exit3 B
  • scripts/test/corpus/CounterLoop/verdict-1.out2.8 KB
  • scripts/test/corpus/CounterOrder/chart.mmd406 B
  • scripts/test/corpus/CounterOrder/ChartRun.out2.7 KB
  • scripts/test/corpus/CounterOrder/CounterOrder.cfg51 B
  • scripts/test/corpus/CounterOrder/CounterOrder.tla194 B
  • scripts/test/corpus/CounterOrder/graph.dot299 B
  • scripts/test/corpus/CounterOrder/report.md606 B
  • scripts/test/corpus/CounterOrder/sany.out39.0 KB
  • scripts/test/corpus/CounterOrder/verdict-1.exit3 B
  • scripts/test/corpus/CounterOrder/verdict-1.out2.1 KB
  • scripts/test/corpus/CounterOrder/verdict-2.exit3 B
  • scripts/test/corpus/CounterOrder/verdict-2.out2.7 KB
  • scripts/test/corpus/CounterRules/chart.mmd485 B
  • scripts/test/corpus/CounterRules/ChartRun.out2.9 KB
  • scripts/test/corpus/CounterRules/CounterRules.cfg79 B
  • scripts/test/corpus/CounterRules/CounterRules.tla265 B
  • scripts/test/corpus/CounterRules/graph.dot302 B
  • scripts/test/corpus/CounterRules/Moves.tla70 B
  • scripts/test/corpus/CounterRules/report.md509 B
  • scripts/test/corpus/CounterRules/sany.out60.8 KB
  • scripts/test/corpus/CounterRules/verdict-1.exit3 B
  • scripts/test/corpus/CounterRules/verdict-1.out2.2 KB
  • scripts/test/corpus/CounterRules/verdict-2.exit3 B
  • scripts/test/corpus/CounterRules/verdict-2.out2.7 KB
  • scripts/test/corpus/CounterRules/verdict-3.exit3 B
  • scripts/test/corpus/CounterRules/verdict-3.out3.0 KB
  • scripts/test/corpus/CounterRules/verdict-4.out2.8 KB
  • scripts/test/corpus/CounterStart/chart.mmd351 B
  • scripts/test/corpus/CounterStart/ChartRun.out2.7 KB
  • scripts/test/corpus/CounterStart/CounterStart.cfg53 B
  • scripts/test/corpus/CounterStart/CounterStart.tla180 B
  • scripts/test/corpus/CounterStart/graph.dot466 B
  • scripts/test/corpus/CounterStart/report.md343 B
  • scripts/test/corpus/CounterStart/sany.out36.6 KB
  • scripts/test/corpus/CounterStart/verdict-1.exit3 B
  • scripts/test/corpus/CounterStart/verdict-1.out1.3 KB
  • scripts/test/corpus/CounterStart/verdict-2.out2.6 KB
  • scripts/test/corpus/CounterStop/chart.mmd87 B
  • scripts/test/corpus/CounterStop/ChartRun.out2.6 KB
  • scripts/test/corpus/CounterStop/CounterStop.cfg53 B
  • scripts/test/corpus/CounterStop/CounterStop.tla172 B
  • scripts/test/corpus/CounterStop/graph.dot466 B
  • scripts/test/corpus/CounterStop/report.md127 B
  • scripts/test/corpus/CounterStop/sany.out36.1 KB
  • scripts/test/corpus/CounterStop/verdict-1.out2.2 KB
  • scripts/test/corpus/CounterTie/chart.mmd600 B
  • scripts/test/corpus/CounterTie/ChartRun.out2.8 KB
  • scripts/test/corpus/CounterTie/CounterTie.cfg96 B
  • scripts/test/corpus/CounterTie/CounterTie.tla263 B
  • scripts/test/corpus/CounterTie/graph.dot798 B
  • scripts/test/corpus/CounterTie/report.md675 B
  • scripts/test/corpus/CounterTie/sany.out44.3 KB
  • scripts/test/corpus/CounterTie/verdict-1.exit3 B
  • scripts/test/corpus/CounterTie/verdict-1.out2.1 KB
  • scripts/test/corpus/CounterTie/verdict-2.exit3 B
  • scripts/test/corpus/CounterTie/verdict-2.out2.5 KB
  • scripts/test/corpus/CounterTie/verdict-3.exit3 B
  • scripts/test/corpus/CounterTie/verdict-3.out3.2 KB
  • scripts/test/corpus/CounterTie/verdict-4.out2.6 KB
  • scripts/test/corpus/CounterTieInGraph/chart.mmd455 B
  • scripts/test/corpus/CounterTieInGraph/ChartRun.out2.7 KB
  • scripts/test/corpus/CounterTieInGraph/CounterTieInGraph.cfg72 B
  • scripts/test/corpus/CounterTieInGraph/CounterTieInGraph.tla283 B

SKILL.md（原文）

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Statechart

The chart shows how a system moves between states, in the words of the person who reads it. That person, the reader, decides whether the behavior is right.

Run

Work in a scratch folder outside the repo. Write a TLA+ spec and its config. Then run:

<skill dir>/scripts/statechart SPEC.tla [--config FILE] [--view FILE] [--out DIR]

scripts/statechart.ts is TypeScript, so run it with a runtime that can execute TypeScript.

The first run installs TLC and Java with mise and needs the network.

Write the spec

  • Write each rule that the reader agrees to as an INVARIANT. A rule can be about a screen, a result, a stored value, or a message. If the model has no variable for a rule, add the variable. Never weaken a rule to make it hold.
  • Write Next as a disjunction of the actions, such as YouPressPlay \/ YouPressStop. If you do not, TLC names every step Next.
  • A state with no step out breaks NoDeadlock, also when it is a correct end state. When an INVARIANT or a PROPERTY already has that name, the rule is CHECK_DEADLOCK. Add to Next an action that is true only in the end states and changes nothing, such as Done == phase \in {"paid", "failed"} /\ UNCHANGED vars, and give it a label in step().

Pick the chart

You do the work that needs judgment: the words on each state and arrow, the phases and their colors, the title, and the report to the reader. Put your work in a view module, and give it with --view.

To show the reader's words, the view exports state(vars). The value that state() returns picks the form:

  • A string gives a flat chart: export const state = (v) => (v.paid ? "Paid" : "Paying");
  • An array gives parent states: export const state = (v) => v.main.split(".");
  • An object gives one parallel region for each key: export const state = (v) => ({ Playback: v.playback, Volume: v.volume });

Label each state with what the reader can see or cares about, such as "Paying" or "Lease held, write pending". Keep variable names out of labels. In vars, a TLA+ sequence is an object with keys from 1, so v.pc[1] is pc[1]. A set is an array.

The view can also export step(action, from, to). It gets the TLC action name and the values before and after the step, and it returns the label of the arrow. Write each step label as the user sees it happen, such as "you press play" or "the connect fails". Do not name the code or the TLA+ action. Two actions that end the same in the chart get the same label, so that they share one arrow.

When a step can occur only in some conditions, end its label with the condition in brackets, in the reader's words, such as you press play [while the file loads]. In a regions chart, the command writes the condition on the other regions on the arrow, in the words of their labels, such as [when Offline]. Your brackets replace it, and two arrows from one state can then look the same. So in a regions chart, do not write brackets for a condition on another region. When a value that no label shows decides where a step goes, name the result in the label, such as "the roster read fails".

The view can also export these:

  • group(vars) returns the name of a phase. Each chart state gets the color of its group. When the model states behind one chart state are in different groups, that state gets no color.
  • colors gives each group name a color class.
  • title is a string that the chart shows at the top.

The command calls state() and group() at most once for each model state, and step() at most once for each step. The chart and the report both use those answers. So make each function depend only on its arguments.

The chart does not draw a step that stays in one label. Split a label when the reader must see such a step.

Aim for about 20 arrows or fewer, because a busier chart is hard to read. First return coarser labels from state(). Give one label to values that act the same, and leave out a detail that the reader does not need, such as a call in flight whose return changes nothing. Keep each state of a bug path, and keep each mark. When a merge changes a breaks state to mayBreak, it hides where a rule breaks. Do not merge two states that break different rules, because the reader then cannot see which rule breaks where. If the chart is still too busy, return null from step() for the steps that the reader does not need, such as a reset that every state has, or a step whose arrow repeats what other arrows show. Obey these rules when you hide steps:

  • Keep each chart state reachable by arrows from a start state.
  • Keep at least one arrow out of each chart state that has a step out in the model.
  • Hide all the steps of an arrow, or none of them. When you hide only some, its condition gets narrower.
  • In the hand-off, say which steps the chart hides.

Read the report

  • In the chart, a state that breaks a rule has the class breaks. When only some model states behind it break the rule, it has the class mayBreak. The Legend names the rules of each mark. When two rules break, it names both on one mark, so say in the hand-off which state breaks which rule. In a regions chart, a state gets a mark when each combination of region states that includes it can break a rule. When a combination can break a rule and none of its states has a mark, each state in that combination gets a mark.
  • TLC goes past a state that breaks a rule, so the chart shows the states after a bug.
  • Because TLC goes past bugs, a model with no limit on its states can run without end. Keep the constants small, or add a CONSTRAINT.
  • With a VIEW or a SYMMETRY, TLC counts states that it treats as the same as one state, and the chart draws that one state. An arrow can lead to it rather than to the state that the step reaches, and the report says so.
  • TLC checks the rules in each state past a CONSTRAINT or an ACTION_CONSTRAINT, but it does not explore that state or check it for deadlock. When TLC's shortest path for a rule ends in such a state, the chart draws that state, and the report gives that path. The chart does not draw the other states past the bound. A deadlock in such a state does not show. TLC also checks the rules after each step that an ACTION_CONSTRAINT excludes, also when it reaches the next state another way. When TLC's shortest path for a rule ends with such a step, the chart draws that step.
  • The command checks the rules with TLC on the config as written, with one worker. When a rule breaks, the command removes that rule and runs TLC again, until no rule breaks. After the first break, each run stops at 100,000 distinct states, so that a large model does not run without end. When a run reaches that bound or stops on an error, the report lists the rules that it did not check under "Rules not checked", and the chart does not mark them. A rule that is not checked can hold or break. To check it, remove the rules that break from the config, or make the model smaller. The bound adds a module that changes TLC's order of the variables, so for a property TLC can find a different counterexample than a run without the bound.
  • tlc.out is what TLC printed on the config as written. When the chart does not show the bug path of a rule that breaks, tlc-RULE.out is what TLC printed for the run that found it. When TLC repeats its first warning, plain TLC prints it twice, but tlc.out shows it once, because TLC leaves the second copy out of the output that this command reads. That happens only when Java runs with -XX:+UseParallelGC, since otherwise TLC's first warning is its advice to pass that flag, which it prints once.

Show the chart

Show chart.mmd to the user as a mermaid code block. The chart has a budget of 500 states, counted by TLC on the config as written. Above that, the chart draws only the paths to the rules that break, and when no rule breaks, the command writes no chart.mmd. It still checks each rule, and the report gives the state count and each bug path. To see the whole graph, make the model smaller.

Render charts with Pele. When the user asks for an image, or a chart is too large to read as text, follow references/render.md. Do not use a different renderer unless the user asks for it.

Hand off

Give each chart and its Mermaid text to the person who must decide. Add one line for each bug: the rule, the reader's sentence for that rule, and the path as the report numbers it. Say what the model leaves out. Give the command that makes the files again, with a new --out folder.

When the model describes code, replay each bug path against the real code, as a test or a live repro, one step for each action. If a bug does not occur, think that the model is wrong until you show that it is not.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

architect

無料概要あり

実装前に型・関数の入出力・モジュール構成を描き、複数モデルによる異なる設計案を比較して、選んだ設計に沿う実装と必要な見直しまで進めるスキル。

  • 複雑な機能を実装前に設計したいとき
  • モジュール構成の代替案比較
  • 実装と設計判断の整合性確認
michael-denyer/pstack-claude3,6122026年10月29日 更新

arena

無料概要あり

同じ課題を複数のAIエージェントに並行して依頼し、評価基準で比較した案を土台に、ほかの案の優れた部分を組み合わせ、成果物の検証まで進めるスキル。

  • 複数の設計案を比較したいとき
  • 同じ課題の実装方法を探りたいとき
  • 候補案の良い部分を統合したいとき
michael-denyer/pstack-claude3,6122026年10月29日 更新

automate-me

無料概要あり

応答の好みや検証・レビューの進め方を、会話履歴と質問から整理します。エージェントに普段の働き方を伝える個人用の `-mode` スキルを作成・更新します。

  • 応答の長さや口調を揃えたいとき
  • 検証・レビュー方針を共有したいとき
  • 働き方の変化を指示に反映したいとき
michael-denyer/pstack-claude3,6122026年10月29日 更新

babysit

無料概要あり

公開済みのPRを継続的に見守り、CIの失敗やマージ競合、対応が明確なレビュー指摘を修正するスキル。修正後も状態を確認し、マージ可能な状態へ進めます。

  • 公開後のPR対応を継続して任せたいとき
  • CI失敗の修正と再確認
  • 対応が明確なレビュー指摘の修正
michael-denyer/pstack-claude3,6122026年10月29日 更新

benchmark-checklist

無料概要あり

処理速度の測定結果を、ボトルネックや設定、エラー、再現性、実際の処理実行まで点検。高速化の報告や技術選定に使える数値かを確かめるスキルです。

  • PRの高速化報告を点検したいとき
  • ライブラリや設定を公平に比較する
  • 不自然な測定結果を調べたいとき
michael-denyer/pstack-claude3,6122026年10月29日 更新

blast-radius

無料概要あり

コード変更が差分の外で何を壊しうるかを調べ、安全性を支える重要な前提を実際のコード実行で検証し、確認できたリスクと未証明の点を整理するスキル。

  • 小さなコード変更の影響を調べたいとき
  • 設計前に既存コードの前提を確かめたいとき
  • マージ前に安全性の根拠を検証したいとき
michael-denyer/pstack-claude3,6122026年10月29日 更新

michael-denyer のスキルをすべて見る

このスキルの問題を報告する