assess-coding-improvement

スター8

フォーク0

更新日2026年6月10日 01:10

After fixing PR review feedback, assess whether the fix reveals a generalizable improvement to the fleet's development procedures (style guide, coding rules, simplify checks, review criteria, worker direction) and, if so, file or append to a fleet:coding-improvement ticket. Auto-invoked as the last step of a feedback AMEND (see FLEET-FEEDBACK-HANDLING.md Step i). Also use when the user asks "should this be a fleet rule?", "assess coding improvement", or "file a coding-improvement". It is a reflection pass — it never touches the PR's code, labels, or claim.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

ソース

jakildev

jakildev/IrredenEngine

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

関連職種SOC

SOC 職業分類に基づく

マネジメントアナリストビジネス・金融業務職·SOC 13-1111

SKILL.md

readonly

このリポジトリの他の Skills

同じリポジトリ

review-pr

jakildev/IrredenEngine

Review an open GitHub PR on the Irreden Engine repo and post a structured review. Use when the user says "review PR <N>", "review #<N>", "review the last PR", "check my PR", "review any new PRs", "review the PR queue", "check for new PRs to review", "review the open PRs", or otherwise asks for a code review — and also invoke automatically from a persistent reviewer-loop session when `gh pr list` surfaces a PR that has not yet been reviewed by this fleet. Designed to be invoked by a dedicated reviewer agent (dispatched into a pool worktree) whose job is to look at another agent's work with a fresh context. Writes a structured review covering ownership, ECS invariants, allocation hot paths, naming, tests, and project-specific smells, then posts it as a PR comment.

2026-07-268

simplify

jakildev/IrredenEngine

Polish the dirty working tree before committing — catch Irreden-Engine smells that a reviewer would otherwise flag. Use whenever you're about to commit, after addressing review feedback, after amending a commit, or whenever the user says "simplify", "clean up", "polish", "self-review", or "review my changes". Also auto-invoked by commit-and-push before the commit message is drafted. The skill finds per-entity getComponent in tick functions, allocation in hot loops, ECS naming convention slips, opportunities to reuse existing helpers, dead code, debug logs left behind, tautological comments, triple-nested loops over voxel volumes, renderer leaks from creation code, CPU-side SDF grid evaluation, linear-search in save/load hot paths, and stale or drifting CLAUDE.md / role / skill docs. Dispatches a parallel reuse-detection subagent fan-out so the reuse pass runs concurrently with the main checks. Applies safe fixes inline and reports anything that needs human judgment. Saves a review-fix-rereview round-trip.

2026-07-268

commit-and-push

jakildev/IrredenEngine

Stage, commit, push a feature branch, and open a GitHub PR against master for the Irreden Engine repo. Use whenever the user says "commit", "commit my changes", "commit and push", "open a PR", "make a PR", "wrap up this chunk", or otherwise indicates the current slice of work is ready for review. The skill assumes the parallel-agent workflow where work happens on short-lived feature branches, another agent reviews the PR, and the user merges via the GitHub UI. NEVER commit directly to master.

2026-07-218

platform-catchup

jakildev/IrredenEngine

Process the backlog of `fleet:needs-<host>-smoke` PRs on the current host. Builds a representative demo cohort against current `origin/master`, runs each with `--auto-screenshot`, and on green batch-swaps `fleet:needs-<host>-smoke` → `fleet:verified-<host>` on every eligible merged PR. On red (build break), files / opens a fix PR for the offender and holds labels on PRs that touch the implicated source paths until the fix lands. On partial (per-demo runtime hang or crash but build green), sweeps the rest, then fix-forwards the offending demo this session (issue only as the documented fallback). Runs on Linux, macOS, AND native Windows (MSYS2 mingw64) — Windows is now the primary validation host. Use when the human cues "platform-catchup", "catch up smoke tests", or "catch up Windows builds". Skill is **cue-only**, never auto-run — multi-target builds and ~40-demo runs are expensive, the human chooses when to spend them.

2026-07-158

render-debug-loop

jakildev/IrredenEngine

Build, run, and visually evaluate a rendering demo in an automated loop. Captures screenshots across a demo's configured shot list (zoom, camera offset, render-mode combinations), reads each image, diagnoses rendering issues against a topic-indexed reference (trixel / SDF shapes, lighting, backend parity), applies fixes, and repeats. Use whenever iterating on render pipeline bugs, shape alignment, lighting, parity drift, or any visual regression in the engine.

2026-07-158

render-verify

jakildev/IrredenEngine

Automated pass/fail render-regression harness for Irreden Engine demos. Wraps build → run → capture → compare → report: builds a demo, runs it with `--auto-screenshot`, then compares each shot against a committed reference image using a stdlib-only Python comparator. Reports per-shot pass/fail with diff images written for mismatches. Use after any render pipeline change to catch visual regressions automatically, or as a sanity pass on `master` before cutting releases.

2026-07-158

assess-coding-improvement (Irreden Engine)

The flow lives in docs/agents/skills/assess-coding-improvement.md. Read it first, then apply the engine deltas below. This wrapper carries deltas only — see docs/design/skill-sharing.md for why.

Deltas (Irreden Engine)

Delta key

Engine value

repo

jakildev/IrredenEngine (game PRs: jakildev/irreden — add --repo jakildev/irreden to every gh call, and read game comments with fleet-pr comments <N> --repo game)

comments tool

fleet-pr comments <N>

convention surfaces

searched in Step 3, in this order (see below)

automated-check surface

the simplify skill + its simplify-* subagents in .claude/agents/

review checklist

the engine checklist in .claude/skills/review-pr/SKILL.md

Engine convention surfaces (Step 3 search order)

docs/agents/CLAUDE-BASELINE.md — cross-cutting baseline: naming, the ECS footgun, style, ownership/lifetime, IRMath. The authoritative home for a missing cross-cutting rule (Class A).

.claude/rules/cpp-*.md — the C++ coding rules: cpp-ecs.md / cpp-ecs-smells.md, cpp-math.md, cpp-systems.md, cpp-lua-enums.md.

The nearest module CLAUDE.md (under engine/, engine/prefabs/, creations/) — the right home for a rule that's specific to one subsystem rather than cross-cutting.

The automated-check surface above — for a mechanically-detectable rule that should be caught pre-commit (the strongest Class-B target).

The review checklist above (+ docs/agents/skills/review-pr.md) — the backstop enforcement surface.

Worker direction: .claude/commands/role-*.md and docs/agents/AUTHOR-PIPELINE.md.

Engine notes

The label fleet:coding-improvement is defined in scripts/fleet/fleet-labels and docs/agents/fleet-labels-reference.md; fleet-labels creates it on the repo if missing.

Several surfaces (.claude/commands/role-*.md, .claude/skills/**/SKILL.md) are gated self-config the fleet can't auto-edit — that's exactly why the ticket is filed un-queued (no human:approved) for the human to triage.

assess-coding-improvement (Irreden Engine)

Deltas (Irreden Engine)

Delta key

Engine value

repo

jakildev/IrredenEngine (game PRs: jakildev/irreden — add --repo jakildev/irreden to every gh call, and read game comments with fleet-pr comments <N> --repo game)

comments tool

fleet-pr comments <N>

convention surfaces

searched in Step 3, in this order (see below)

automated-check surface

the simplify skill + its simplify-* subagents in .claude/agents/

review checklist

the engine checklist in .claude/skills/review-pr/SKILL.md

Engine convention surfaces (Step 3 search order)

docs/agents/CLAUDE-BASELINE.md — cross-cutting baseline: naming, the ECS footgun, style, ownership/lifetime, IRMath. The authoritative home for a missing cross-cutting rule (Class A).

.claude/rules/cpp-*.md — the C++ coding rules: cpp-ecs.md / cpp-ecs-smells.md, cpp-math.md, cpp-systems.md, cpp-lua-enums.md.

The nearest module CLAUDE.md (under engine/, engine/prefabs/, creations/) — the right home for a rule that's specific to one subsystem rather than cross-cutting.

The automated-check surface above — for a mechanically-detectable rule that should be caught pre-commit (the strongest Class-B target).

The review checklist above (+ docs/agents/skills/review-pr.md) — the backstop enforcement surface.

Worker direction: .claude/commands/role-*.md and docs/agents/AUTHOR-PIPELINE.md.

Engine notes

The label fleet:coding-improvement is defined in scripts/fleet/fleet-labels and docs/agents/fleet-labels-reference.md; fleet-labels creates it on the repo if missing.