CtrlK
BlogDocsLog inGet started
Tessl Logo

pua-ja

お前のAIを詰めろ。日本企業の詰め文化と体系的デバッグ方法論で全ての手段を尽くさせる。トリガー条件:(1) タスク失敗2回以上または同じアプローチの微調整ループ; (2)「解決できません」と言おうとする・手動対応を推奨・未検証で環境を原因帰属; (3) 受け身——検索しない・ソースを読まない・指示待ち; (4) ユーザーの不満:'もっと頑張れ'、'なんでまた失敗したの'、'なんとかしろ'。全タスクタイプ適用。初回失敗や既知修正の実行中はトリガーしない。

59

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./codebuddy/pua-ja/SKILL.md

The canonical home for this skill is pua-ja in tanweai/pua

SKILL.md
Quality
Evals
Security

Quality

Content

56%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable and its workflows are clearly sequenced with checklists and feedback loops, but it is substantially over-padded with redundant motivational rhetoric and does not split its large reference blocks into separate files as progressive disclosure would call for.

Suggestions

Move the 大企業詰め拡張パック (company flavor speeches) and the 言い訳封殺テーブル into a separate reference file (e.g. FLAVORS.md) and reference them one level deep, keeping only the selector table and one anchor example inline in SKILL.md.

Consolidate the redundant verification/ownership messaging that repeats across 三つの鉄則, 能動性の鞭撻フレーズ, and the 主体的行動チェックリスト into a single section; the same 'build/test/curlで証拠を出せ' message appears verbatim in several places.

Make the agents/pua-enforcer.md reference explicit and signaled (a dedicated line with a clear pointer) so the Agent Team integration reads as progressive disclosure rather than a buried mention.

DimensionReasoningScore

Conciseness

The body is noticeably verbose — eight full corporate-flavor motivational speeches (トヨタ味, 電通味, 楽天味, etc.) plus repeated verification/ownership rhetoric across the 鞭撻フレーズ, 言い訳封殺テーブル, and flavor pack sections restate the same themes with heavy padding.

2 / 5

Actionability

Despite being instruction-only, it gives concrete executable guidance — 'build/test/curlを回し', 'エラー箇所の前後50行', '完全なエラーメッセージを検索' — plus ready-to-use templates ([PUA-REPORT], [自動選択:...]) with only minor gaps.

4 / 5

Workflow Clarity

Sequences are clear: the 5-step methodology, the L1–L4 escalation ladder, and the 7-item checklist all have explicit checkpoints and feedback loops (振り返り, クローズドループ), though overlapping parallel frameworks introduce minor sequencing ambiguity.

4 / 5

Progressive Disclosure

Section headers are consistent, but large separable blocks (the company flavor pack, the excuse-suppression table, the Agent Team integration) are inlined in SKILL.md, and the one reference to agents/pua-enforcer.md is passing rather than clearly signaled — content that should be a separate file stays inline.

3 / 5

Total

13

/

20

Passed

Description

80%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong overall: it clearly states what the skill does and gives explicit, numbered trigger conditions plus a negative-when guard. Its main weakness is the broad 'all task types' scope, which raises conflict risk against neighboring debugging/verification skills.

DimensionReasoningScore

Specificity

The description enumerates several concrete trigger signals — 'タスク失敗2回以上', '同じアプローチの微調整ループ', '手動対応を推奨', '未検証で環境を原因帰属' — giving actionable detection conditions rather than vague claims.

4 / 5

Completeness

It explicitly answers both 'what' (日本企業の詰め文化と体系的デバッグ方法論で全ての手段を尽くさせる) and 'when' (numbered トリガー条件 1–4 plus a negative-when clause: '初回失敗や既知修正の実行中はトリガーしない').

5 / 5

Trigger Term Quality

It includes natural user phrases ('もっと頑張れ', 'なんでまた失敗したの', 'なんとかしろ') alongside behavioral triggers, giving good keyword coverage, though a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

The triggers are specific, but '全タスクタイプ適用' is very broad and the skill itself overlaps with systematic-debugging and verification-before-completion, creating moderate overlap risk with closely related skills.

3 / 5

Total

16

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tanweai/pua
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.