jackwener 0da77a5773 feat(autoresearch): improve operate success rate + complex publish chains ...

Iteration round 1 results:
- Browse: 50/59 → 58/59 (+8) — fixed 8 broken selectors, 1 remaining (DDG images anti-crawl)
- Publish fill-only: 5/5 → 12/13 → 13/13 — added 8 complex tasks, fixed selectors
- Save as CLI: 26/26 (maintained)

Changes:
- browse-tasks.json: fix 8 broken selectors (iana, github, quotes, trending, google, wiki, npm, httpbin)
- publish-tasks.json: add 8 complex multi-step tasks (thread compose, quote RT, search→reply, cross-platform)
- skills/opencli-operate/SKILL.md: add Common Pitfalls section, improve save-as-CLI guidance
- Fix twitter thread compose (use querySelectorAll for 2nd textarea)
- Fix zhihu editor selectors (WriteIndex-titleInput, contenteditable)

2026-04-04 03:52:26 +08:00

..

commands

feat(autoresearch): add Layer 4 Save-as-CLI eval with zhihu/xhs coverage (#741)

2026-04-04 01:27:50 +08:00

presets

feat(autoresearch): add Layer 4 Save-as-CLI eval with zhihu/xhs coverage (#741)

2026-04-04 01:27:50 +08:00

save-adapters

feat(autoresearch): add Layer 4 Save-as-CLI eval with zhihu/xhs coverage (#741)

2026-04-04 01:27:50 +08:00

baseline-browse.txt

feat: add opencli operate — browser control commands for Claude Code skill (#614)

2026-04-02 19:30:35 +08:00

baseline-skill.txt

feat: add opencli operate — browser control commands for Claude Code skill (#614)

2026-04-02 19:30:35 +08:00

browse-tasks.json

feat(autoresearch): improve operate success rate + complex publish chains

2026-04-04 03:52:26 +08:00

config.ts

feat: AutoResearch framework + V2EX test suite (60 tasks, SKILL.md optimization) (#717)

2026-04-03 11:31:22 +08:00

engine.ts

feat: AutoResearch framework + V2EX test suite (60 tasks, SKILL.md optimization) (#717)

2026-04-03 11:31:22 +08:00

eval-all.ts

feat: AutoResearch framework + V2EX/Zhihu test suites (194/194) (#731)

2026-04-03 17:14:38 +08:00

eval-browse.ts

feat: AutoResearch framework + V2EX/Zhihu test suites (194/194) (#731)

2026-04-03 17:14:38 +08:00

eval-publish.ts

feat(autoresearch): add Layer 5 Publish testing for twitter/zhihu

2026-04-04 03:19:36 +08:00

eval-save.ts

feat(autoresearch): add Layer 4 Save-as-CLI eval with zhihu/xhs coverage (#741)

2026-04-04 01:27:50 +08:00

eval-skill.ts

feat: AutoResearch framework + V2EX/Zhihu test suites (194/194) (#731)

2026-04-03 17:14:38 +08:00

eval-v2ex.ts

feat: AutoResearch framework + V2EX test suite (60 tasks, SKILL.md optimization) (#717)

2026-04-03 11:31:22 +08:00

eval-zhihu.ts

feat: AutoResearch framework + V2EX/Zhihu test suites (194/194) (#731)

2026-04-03 17:14:38 +08:00

logger.ts

feat: AutoResearch framework + V2EX test suite (60 tasks, SKILL.md optimization) (#717)

2026-04-03 11:31:22 +08:00

publish-tasks.json

feat(autoresearch): improve operate success rate + complex publish chains

2026-04-04 03:52:26 +08:00

run-browse.sh

feat: add opencli operate — browser control commands for Claude Code skill (#614)

2026-04-02 19:30:35 +08:00

run-save.sh

feat(autoresearch): add Layer 4 Save-as-CLI eval with zhihu/xhs coverage (#741)

2026-04-04 01:27:50 +08:00

run-skill.sh

feat: add opencli operate — browser control commands for Claude Code skill (#614)

2026-04-02 19:30:35 +08:00

save-tasks.json

chore(autoresearch): format save-tasks.json

2026-04-04 01:46:08 +08:00

v2ex-tasks.json

feat: AutoResearch framework + V2EX/Zhihu test suites (194/194) (#731)

2026-04-03 17:14:38 +08:00

zhihu-tasks.json

feat: AutoResearch framework + V2EX/Zhihu test suites (194/194) (#731)

2026-04-03 17:14:38 +08:00