文件历史

提交图

6 次代码提交

作者 SHA1 备注 提交日期
Saurav Panda 6dc4e95d4e Merge pull request #168 from iskyiskyisky/domain-skills/amazon-cart-orders
domain-skills: amazon — cart.md, orders.md
2026-05-02 16:53:19 -07:00
Sarath S Menon fb1a51dd9b refactor: move to src layout, agent-workspace, and fix SKILL.md invocation format (#229)
* refactor(tests): reorganize into tests/unit and tests/integration

Moves all root-level test_*.py files into a structured tests/ directory:
- tests/unit/ — admin, helpers (was test_screenshot), run
- tests/integration/ — js expression tests
- tests/conftest.py — shared fake_png pytest fixture, eliminating duplication

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor: move to src layout, agent-workspace, and fix SKILL.md invocation format

- Move package to src/browser_harness/ and domain-skills/interaction-skills to agent-workspace/
- Fix all browser-harness <<'PY' heredoc examples in SKILL.md and run.py HELP string to use the correct -c '...' flag format (heredoc was never supported by the CLI)
- Update SKILL.md path references from domain-skills/ to agent-workspace/domain-skills/

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-28 15:38:11 +05:30
Sarath Suresh fbd9146df5 refactor: rename goto/click/screenshot to avoid Playwright name overlap
- goto()       → goto_url()
- click()      → click_at_xy()
- screenshot() → capture_screenshot()

These three shared exact names with Playwright but different argument
shapes, causing agent confusion. Updated helpers.py and all markdown
skill files.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-24 11:26:07 +05:30
Isky 17e88b4e46 domain-skills: amazon — cart.md, orders.md
Two new domain skills for amazon.com derived from a logged-in session:

- cart.md: documents the empty-cart trap where `[data-asin]` selectors
  match recommendation widgets even on an empty cart, plus the stable
  subtotal selectors and the price-change banner format.

- orders.md: covers the order-list card structure, the order-search
  quirk (the `?search=` URL param doesn't filter — must submit the
  form or hit the post-submit `/your-orders/search/` URL), and the
  tracking page (whose `data-test-id` selectors are all null — extract
  from `body.innerText` anchored on the "Arriving" line).
2026-04-23 01:40:43 -07:00
sauravpanda 4f05481d2a Replace drafted skills with browser-harness validated versions
Ran actual browser-harness sessions against each site and rewrote
the skill files from live test findings. Key corrections:

GitHub: wait(2) after wait_for_load() for React hydration; search API
  separate 10 req/min limit; search/code needs auth (401 unauthed)

HackerNews: athing also matches comment rows (use 'athing submission');
  job posts break naive score-zip; html.unescape() required for titles

Amazon: .zg-item-immersion gone from Best Sellers; #priceblock_ourprice
  returns null (legacy); review count selector collides with cross-sell
  widget — use [aria-label*='ratings'] instead

News: The Verge is Atom not RSS (namespace dict required); Reuters
  hard-blocks http_get with 403 even with User-Agent; BBC shows no
  consent banner from US IP; parallel fetch is 4.3x faster (0.16s vs 0.70s)

ProductHunt: goto() ERR_ABORTED — always use new_tab(); /posts/ URLs
  don't exist (it's /products/); homepage has 30 fixed items no lazy load;
  [data-test^='post-item-'] is the correct card selector
2026-04-18 01:22:30 -07:00
sauravpanda f0f70e7362 Add domain skills for 6 public, no-login-required sites
- github/scraping.md: GitHub API + trending page patterns, rate limiting
- hackernews/scraping.md: http_get + Algolia API for search/filtering
- producthunt/scraping.md: React SPA browser scraping + GraphQL token approach
- amazon/product-search.md: ASIN extraction, price parsing, CAPTCHA handling
- news-aggregation/multi-source.md: RSS-first approach, parallel fetch, consent banners
- job-boards/indeed-glassdoor.md: URL construction, job key extraction, salary normalization

All skills derived from real user task patterns. No credentials or sensitive data included.
2026-04-18 00:16:18 -07:00