red
Skill1 starsChanged 26 days agoMITView on GitHub
テストコードを作成し、失敗することを確認する(並列実行対応)。PLANの次フェーズ。「テスト書いて」「red」で起動。
1 other project uses a version of this.
Adopted by
Most recently taken up by
- labdaps/labskillstheir own version, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- labdaps/labskills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- attack-reportSkill
- carefulSkill
- codify-insightSkill
- commitSkill
- context-reviewSkill
- cycle-retrospectiveSkill
- diagnoseSkill
- evolveSkill
- flask-qualitySkill
- flutter-qualitySkill
- generate-e2eSkill
- greenSkill
- hugo-qualitySkill
- js-qualitySkill
- learnSkill
- onboardSkill
- orchestrateSkill
- php-qualitySkill
- python-qualitySkill
- refactorSkill
- reviewSkill
- security-auditSkill
- security-scanSkill
- skill-makerSkill
- specSkill
- sync-skillsSkill
- ts-qualitySkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 37
Test ListのTODOからテストケースを選択してWIPに移動。
- Distinctive: line 41
Test List に対してREDフェーズ開始時に評価する。詳細: reference.md
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Current State
!ls -t docs/cycles/*.md 2>/dev/null | head -1 || echo "(none)"
禁止事項
- 実装コード作成(GREENで行う)
- テストを通すための実装
Workflow
Cycle Doc Gate
for f in docs/cycles/*.md; do [ -f "$f" ] || continue; fm=$(awk '/^---$/{c++;next} c==1{print}' "$f"); echo "$fm" | grep -q '^phase:' || continue; echo "$fm" | grep -q 'phase: DONE' && continue; printf '%s\t%s\n' "$(echo "$fm" | awk 'sub(/^updated: */,""){gsub(/T/," ");print;exit}')" "$f"; done | sort | tail -1 | cut -f2 → found: continue / not found: BLOCK(run spec)
Pre-RED Gate (deterministic)
Cycle doc の Progress Log を確認し、以下が全て満たされなければ BLOCK:
- sync-plan完了: Progress Log に
SYNC-PLANまたはsync-planセクションがあり、Phase completed記録がある - Plan Review完了: Progress Log に
Plan Reviewまたはplan-reviewの記録がある
# Cycle doc を取得(Cycle Doc Gate で既に特定済み)
# 1. sync-plan チェック
awk '/SYNC.PLAN|sync-plan/,/Phase completed/' "$CYCLE_DOC" | grep -qi 'Phase completed'
# 2. Plan Review チェック
grep -qiE 'Plan Review|review.*plan' "$CYCLE_DOC"いずれか失敗 → BLOCK(不足ステップを案内)
Test ListのTODOからテストケースを選択してWIPに移動。
Complexity Gate
Test List に対してREDフェーズ開始時に評価する。詳細: reference.md
| Class | Criteria | Stages |
| trivial | 1-2 items, Example only, no escalation triggers | Stage 1 as 1-line GWT; Stage 2 skip; Stage 3 |
| standard | 3-5 items, Example only, no complex escalation triggers | Stage 1 simplified; Stage 2 Review skip; Stage 3 |
| complex | 6+ items OR any non-Example paradigm | Full 3-stage (all stages) |
Stage 1: Test Plan
Cycle doc の Test List を Given/When/Then + 具体テストデータに展開。詳細: reference.md
Stage 2: Test Plan Review
要件とテスト計画を照合(網羅性・カテゴリバランス)。Gap発見時は追加。詳細: reference.md
Stage 3: Test Code
テストファイル依存関係分析 → red-worker並列起動 → 結果収集・マージ → テスト実行で失敗確認。 詳細: reference.md
Stage 3.5: False-pass 自己証明
新規 test の literal が「false-pass 不在を自己証明」できることを確認(対象行除去 → count 0 / FAIL の実証)。手順: reference.md
exspec check (optional)
command -v exspec で存在確認。インストール済みかつ対応言語なら scripts/gates/exspec-check.sh を実行。
BLOCK検出時はRED失敗(修正→再実行)。未インストール or 非対応言語はスキップ。
詳細: reference.md
Verification Gate
Tests fail → PASS(→GREEN) | Tests pass → BLOCK(review test conditions)
Cycle doc更新
Progress Log追記(### {date} - RED\n- {summary}\n- Phase completed) + frontmatter更新(phase/updated)
完了
RED完了。次: Orchestrate時は自動GREEN / 手動時は /green。
Reference
- 詳細: reference.md
- red-worker: ../../agents/red-worker.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

