0672b260b3
feat(pua): sweep open issues and add offline adapters
...
Summary:
- Filter UserPromptSubmit prompts inside the hook and soften hook wording so
normal first-attempt prompts stay silent and frustration prompts read as
user-installed productivity context.
- Add offline mode, remove stop-feedback /tmp plugin-root rendezvous, and add
feedback endpoint body caps, origin checks, and D1-backed rate limiting.
- Add diagnosis-first discipline, Huawei military-order mode, Codex subcommand
alias skills, a lightweight pi adapter, and Trae prompt/rule files.
- Clarify ambiguous 下场 wording, add FAQ guidance, and bump manifests to
v3.3.0.
Rationale:
- Open issues covered over-aggressive hooks, model refusal, closed-network
usage, Codex subcommands, Pi/Trae support, feedback abuse, ambiguous lifecycle
wording, Huawei tone, and the misleading-traceback blind spot.
- The fixes convert ad-hoc prompt pressure into mechanical gates: script-level
trigger filtering, offline config gates, endpoint abuse controls, and static
regression checks.
Tests:
- for f in hooks/*.sh scripts/*.sh evals/*.sh; do bash -n "$f"; done
- bash evals/test-windows-python-hooks.sh
- bash evals/test-yaml-frontmatter.sh
- bash evals/test-release-consistency.sh
- bash evals/test-agent-governance.sh
- bash evals/test-pua-loop-hook.sh
- bash evals/test-integrity-guard.sh
- bash evals/test-issue-regressions.sh
- bash evals/test-behavior.sh
- bash evals/run-trigger-test.sh
- ./landing/node_modules/.bin/tsc -p pi/pua/tsconfig.json --noEmit
- npm -C landing run build
- git diff --check
- python3 JSON parse check for plugin and hook manifests
Co-authored-by: Codex <codex@openai.com >
2026-05-08 23:41:30 +08:00
1f3b24bff8
fix: sync skill content across all platforms and fix landing page accuracy
...
**Skill content sync (cursor/kiro/vscode/codex/codebuddy):**
- Add Owner意识四问 (4-question owner mindset checklist)
- Add 3 new failure modes: 被动等待/差不多就行/空口完成
- Add 阿里味·关怀型 (caring variant) to 大厂PUA扩展包
- Add 自动选择机制 with output format and examples
- Add 3 new 抗合理化 entries for the new failure modes
- Fix broken 断链: add 百度味/拼多多味 definitions to cursor rules
- codex/codebuddy: add 任务生命周期行为框架 (task lifecycle framework)
- Add pua-loop skill; remove obsolete loop skill
**README fixes:**
- ja: add missing VSCode (GitHub Copilot) from supported platforms list
- zh-CN + ja: add /pua:p9 and /pua:pro to Works Well With section
**Landing page accuracy:**
- Unify flavor count: 10/14 → 13 across index.html, guide.html, i18n.ts, App.tsx
- Add Google Antigravity to hero platform badges (dist/index.html)
- Complete platform list in App.tsx: 4 → 9 platforms
- Fix CC install command: show both marketplace add + plugin install steps
**New commands:** flavor, kpi, off, on, survey
**Add CLAUDE.md** project instructions for Claude Code
2026-03-23 19:12:32 +08:00
05bb297690
fix(ja): fix unnatural Japanese expressions across all pua-ja files
...
Two Chinese-influenced phrases replaced with natural Japanese equivalents:
- 私の能力範囲を超えています → 私の能力を超えています
(能力範囲 mirrors Chinese 能力范围; English version uses "beyond my capabilities" without "range")
- 私の知識のカットオフ日を超えています → 私の知識のカットオフを超えています
(カットオフ already implies a temporal boundary; 日 is redundant)
Note: 空口完了 → 検証なしの完了宣言 is handled separately in PR #86 (donzoru)
Affects: skills/pua-ja, codex/pua-ja, codebuddy/pua-ja, cursor/rules/pua-ja, kiro/steering/pua-ja
2026-03-17 22:44:27 +08:00
cc50d9f861
feat: add CodeBuddy (Tencent) compatibility
...
- Add .codebuddy-plugin/plugin.json and marketplace.json for native
CodeBuddy plugin installation
- Add codebuddy/ directory with pua, pua-en, pua-ja SKILL.md files
for standalone manual installation
- Update all 3 READMEs (EN/ZH/JA) with CodeBuddy badge, description,
and installation instructions
- Landing page: add CodeBuddy to install tabs, platform pills, and
vintage banner platform list
2026-03-16 16:30:26 +08:00
xsser