GitHub user
Agent skills by liaohch3
- skills
- 11
- repository
- 1
Repositories by liaohch3
Skills by liaohch3, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Runs a real Codex CLI session through claude-tap and produces trace evidence and viewer screenshots for pull requests that touch capture, proxying or the viewer. | liaohch3/ | 3.3k | — | ~3k | Automated safety check: Pass | MIT | 15 days ago |
| 2 | Records a real tmux end-to-end run with asciinema, converts it to a GIF and MP4, and captures trace viewer screenshots with Playwright. | liaohch3/ | 3.3k | — | ~545 | Automated safety check: Pass | MIT | 15 days ago |
| 3 | Tests JavaScript embedded in an HTML file in two layers: pytest checks of the logic ported to Python, and Playwright runs in a real browser for the DOM. | liaohch3/ | 3.3k | — | ~924 | Automated safety check: Pass | MIT | 15 days ago |
| 4 | Runs local checks on maintainer docs for stale review dates, missing manifest paths and plan state drift, matching what the CI workflow enforces. | liaohch3/ | 3.3k | — | ~561 | Automated safety check: Pass | MIT | 15 days ago |
| 5 | Records headless Playwright sessions as .webm videos to show a bug fix working or to give pull request reviewers visual evidence. | liaohch3/ | 3.3k | — | ~714 | Automated safety check: Pass | MIT | 15 days ago |
| 6 | Runs a single merge-readiness check on a pull request: metadata, GitHub Actions status, local lint, format and test gates, and PR body rules, ending in READY or NOT_READY. | liaohch3/ | 3.3k | — | ~615 | Automated safety check: Pass | MIT | 15 days ago |
| 7 | Pushes the current work to GitHub and, when pending commits change code, bumps the version in pyproject.toml so CI publishes a new PyPI release. | liaohch3/ | 3.3k | — | ~509 | Automated safety check: Pass | MIT | 15 days ago |
| 8 | Runs real end-to-end tests for claude-tap against the actual Claude CLI, in a pytest mode and an interactive tmux mode, and checks the resulting traces. | liaohch3/ | 3.3k | — | ~693 | Automated safety check: Pass | MIT | 15 days ago |
| 9 | Validates PR evidence screenshots for size, width and blankness, and checks that generated viewer HTML renders in headless Chromium without errors. | liaohch3/ | 3.3k | — | ~716 | Automated safety check: Pass | MIT | 15 days ago |
| 10 | Fills missing translations in claude-tap's viewer_i18n.json by sending untranslated keys to OpenRouter for Japanese, Korean, French, Arabic, German and Russian. | liaohch3/ | 3.3k | — | ~666 | Automated safety check: Pass | MIT | 15 days ago |
| 11 | 11.E2E Test Run claude-tap end-to-end tests with pytest. An agent skill from liaohch3/claude-tap. | liaohch3/ | 3.3k | — | ~369 | Automated safety check: Pass | MIT | 15 days ago |
Questions, answered from the data.
What is the best skill by liaohch3?
Codex E2E Trace Validation from liaohch3/claude-tap ranks first of the 11 skills by liaohch3 listed here, with the highest score: its repository has 3.3k GitHub stars, its SKILL.md loads about 3k tokens and it passes the automated safety check with no findings. Next come Terminal Demo Video Recorder and JS-in-HTML Testing.
Are liaohch3's skills official?
None yet. All 11 skills by liaohch3 listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.