[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B8A1679VNPYFS32ME1R2F7":3,"skill-same:01M7B8A1679VNPYFS32ME1R2F7":74},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7B8A1679VNPYFS32ME1R2F7","ui-qa-pass",null,"Runs a branch's app locally and drives a headless browser through the screens the change touches, choosing the states, themes, widths and roles by what the change could break. Takes a screenshot of each, fixes bugs and obvious polish as it goes with before and after shots, and writes a report that leads with the decisions the user needs to make. Use when the user says \"QA this\", \"do a QA pass\", \"click through every changed screen\", \"screenshot every state\", \"test it in a browser and make a report\", or before asking for review of a change people can see (app screens, marketing or docs pages, emails). Not for writing or fixing the automated browser test suite.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FDocSpring\u002Fdocspring-agent-playbook\u002Fskills\u002Fui-qa-pass\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ui-qa-pass\ndescription: Runs a branch's app locally and drives a headless browser through the screens the change touches, choosing the states, themes, widths and roles by what the change could break. Takes a screenshot of each, fixes bugs and obvious polish as it goes with before and after shots, and writes a report that leads with the decisions the user needs to make. Use when the user says \"QA this\", \"do a QA pass\", \"click through every changed screen\", \"screenshot every state\", \"test it in a browser and make a report\", or before asking for review of a change people can see (app screens, marketing or docs pages, emails). Not for writing or fixing the automated browser test suite.\nmetadata:\n  version: 1.0.0\n---\n\n# UI QA pass\n\nBefore anyone reviews a change people can see, run the branch locally and look at the screens it changes, in the\nstates, themes, widths and roles the change could break. Fix what you find, shoot it again, and report what you\ncovered, what you didn't, and what's left for the user to decide.\n\n## Rules that apply throughout\n\n- **Never copy the QA working folder anywhere shared** (a notes vault, a file share, a PR, the repository). Its\n  browser profile holds session cookies and its login files hold passwords. Copy out the individual screenshots and\n  the report page only.\n- **Use synthetic data only.** Made-up names, blank public forms, sample files you created. Never real customer\n  records or documents, even on a local stack.\n- **Take the \"before\" shot before you change the code.** Every fix needs a before and an after of the same state, at\n  the same width and theme.\n- **Fix bugs and obvious polish without asking.** Collect anything with a real trade-off (copy the user may have\n  opinions on, a layout choice, a behavior change) as a decision with your recommendation, and keep going. Stopping\n  for each one leaves the user babysitting the pass.\n- **Open every screenshot, cropped and zoomed, and read it.** A step that finishes without errors only proves its\n  selectors matched.\n- **On a busy machine, a browser test that fails at a different step on each run points to load.** Check the load\n  average (`uptime`) and rerun the test on the parent commit before you blame the branch.\n\n## Settings\n\nRead the `## Agent workflow settings` section of the repository's root `AGENTS.md` (see the playbook's\n`CONFIGURE.md`):\n\n- `### Local stack and QA`: how to start the app, how to create test users and data, and where screenshots and reports\n  go (the working folder, which stays on this machine). It may also name where reports are published (`QA reports are\n  published to: ...`).\n- `### Tests`: how to run one test file, and which suites must run one at a time.\n- `### What the agent may do without asking`: whether you may commit, push and post PR comments. Read this one from\n  the base branch, not the checkout (the playbook's `CONFIGURE.md`, \"Who approves what\").\n\nIf a setting you need is missing, ask the user once and offer to add the answer to that section. For the report's\ndestination, offer the options in `references\u002Freport-format.md`.\n\n## 1. Before you start\n\n1. Work in the branch's own checkout or worktree, with its own ports and database if the repo provides them. If the\n   branch is behind the base and lacks something the pass needs, ask before rebasing.\n2. Make the working folder, named after the branch and date (for example `~\u002Fqa\u002F\u003Crepo>\u002F\u003Cbranch>-2026-01-15\u002F`), with\n   `steps\u002F`, `screenshots\u002F`, `report\u002F` and `logs\u002F` inside. Export it as `QA_DIR` before starting the stack and the\n   browser.\n3. Start the stack with the command from the settings. Export any environment a feature needs first. Read secrets\n   into the environment without printing them (`export KEY=\"$(grep '^KEY=' .env.local | cut -d= -f2-)\"`).\n4. Create test users with the repo's seed or test-user script, one credentials file per user inside `QA_DIR`. Make a\n   new user whenever a state needs a fresh account (onboarding, an empty list). Never paste the credentials into\n   chats, PRs, tickets or notes.\n5. Expect the first load of each page in development to compile its assets, which can take a minute on a busy\n   machine. Give navigations a long timeout rather than retrying them.\n\n## 2. Plan the screens and states\n\nRead `references\u002Fstate-matrix.md` now, before the first screenshot. It lists the states, paths, themes and widths to\ncover, what to check in each shot, and the findings list format.\n\nIn short: list what the branch changes for people (`git diff --stat \u003Cbase>...`, then the views, components, styles,\npages, emails and copy it touches). Exercise the changed interaction fully: its states (empty, loading or in progress,\ndone, failed, disabled, limits, long text, many items), its paths (skip, cancel, retry, go back, reload halfway) and the\nroles that see it. Then add the themes and widths the product supports where the change could look different: a layout\nor style change needs each supported theme and the narrow widths, a copy change needs the width where the text is\nlongest. Sample screens that only share a changed component. Write down the matrix you chose and what you left out, so\nthe report can say exactly what was tested. Give each area a letter and each finding an ID (A1, A2, B1).\n\n## 3. Drive the browser with step files\n\nWrite one small script per screen or state in `QA_DIR\u002Fsteps\u002F`, so you can run the same step again for the \"after\"\nshot. Use the browser automation your harness or repo already has (Playwright, Puppeteer, a browser MCP server). If\nthe repo has nothing, `scripts\u002Frun_step.mjs` in this skill is a short Playwright example to copy and adapt.\n\nInstalling Playwright adds a dependency to the repository (and a `package.json`, if it has none) and downloads a\nChromium build, so show the user the install command and ask before running it. Pin an exact version that has been out\nfor a while; `npx playwright install` then fetches the browser build that version expects. After copying the runner\nto `scripts\u002Fqa\u002F` in your repo:\n\n```bash\nnpm install --save-dev --save-exact playwright@1.64.1 && npx playwright install chromium   # once, after a yes\nexport QA_BASE_URL=http:\u002F\u002Flocalhost:3000 QA_DIR=~\u002Fqa\u002Fmyapp\u002Fmy-branch-2026-01-15\nnode scripts\u002Fqa\u002Frun_step.mjs \"$QA_DIR\u002Fsteps\u002Fsettings.mjs\"                 # the \"before\" shots\nQA_SUFFIX=R2 node scripts\u002Fqa\u002Frun_step.mjs \"$QA_DIR\u002Fsteps\u002Fsettings.mjs\"    # the \"after\" shots, as \u003Cname>-R2.png\n```\n\nA step exports one async function that gets the page and a few helpers (`url`, `viewport`, `theme`, `settle`,\n`shot`, `clearHover`, `boxes`, `newContext`). `scripts\u002Fexample_step.mjs` shows one. The runner keeps cookies between\nruns in `QA_DIR\u002Fbrowser-profile`, prints what the step returns, and prints the console errors and uncaught exceptions\nfrom every page the step used, popups and `qa.newContext()` contexts included: treat each as a finding. If you drive\nthe browser another way, attach the error listeners to every page and context yourself, or say in the report which\nones weren't watched.\n\n## 4. Force each state\n\n- Prefer real conditions first: an environment variable (restart the service after), a record changed through the\n  app's console or seed script, the account's plan or permissions, a limit you actually reach. To catch a background\n  job's queued state, stop the job worker, take the shot, then start it again.\n- Then intercept requests for failures and server answers you can't produce for real: in Playwright,\n  `page.route('**\u002Fapi\u002Fupload', (route) => route.abort())` for a network failure, or\n  `route.fulfill({ status: 500, contentType: 'application\u002Fjson', body: '{\"error\":\"...\"}' })` for a server error or a\n  poll that never finishes. Remove the route at the end of the step (`page.unroute`).\n- For a signed-out visitor or a second user, open a fresh browser context in the step with no cookies\n  (`qa.newContext('signed-out')` in the example runner, so its errors are watched too). An owner usually sees more\n  than a visitor.\n- If you change code to force a state, change it back and check `git diff` before you commit.\n\n## 5. Fix as you go\n\nFor each problem:\n\n1. Take the \"before\" shot (if the step that found it didn't already).\n2. Fix it. Check the dev server or bundler log for build errors before you conclude a fix didn't work.\n3. Run the step again with a new suffix (`QA_SUFFIX=R2`), so the earlier shot survives.\n4. Check the \"after\" really shows the fix: its file time is later than your edit, and the zoomed crop shows the change.\n   An \"after\" taken before the fix, or cropped so the change is out of frame, proves nothing.\n5. Read every control's value in the after shot, and separately whether the viewer can change it. Each control shows\n   the effective value; disabling a control doesn't change its value, so a disabled, ticked checkbox is right when the\n   setting is on and the viewer can't edit it.\n6. Run the tests for the files you touched (one at a time for suites that share state) and the linter.\n7. For visual fixes, look at each supported theme, and use your design-review skill if the repo has one.\n\nRead `references\u002Fscreenshot-pitfalls.md` whenever a shot looks wrong or a fix seems not to have worked. Check the\nbuild, the page state, the viewport, the theme and whether the page had finished loading before you decide; and tell a\ncapture problem from a real defect before you reset anything, since a blank band can be either.\n\n## 6. Report\n\nRead `references\u002Freport-format.md` before you write the report. It covers the structure, the destinations (a private\nhosted page such as an artifact, a PR comment with images, a static page), images and later rounds.\n\nThe order is fixed: the decisions the user needs to make, each with a recommendation; then small defaults you'll take\nunless they object; then findings by area with before and after shots and the state each shot shows; then what you\ndidn't test and why. Each round of the user's feedback becomes a new \"Round N\" section at the top of the same report.\n\n## 7. After the pass\n\n- Commit fixes locally as the settings allow, in themed commits. By default, push only after the user has seen the\n  report (visible changes are theirs to accept), unless they or the settings say otherwise. The precedence for approvals\n  is in the playbook's `CONFIGURE.md`: the user's instruction in the task, then the settings, then what invoking this\n  skill approves (fixing and committing locally). Don't commit screenshots.\n- Once the branch has a PR, draft the QA results comment (date, commit SHA, what passed, what wasn't tested) and post\n  it when the settings allow posting comments, or after the user approves the text.\n- Turn a lesson that would help the next pass (a pitfall, a way to force a state) into an edit to the repo's QA\n  runbook or the nearest `AGENTS.md`, in the branch's PR.\n- Leave the stack running while the user reviews. Stop it, and the browser, when they're done.\n","# UI QA pass\n\nBefore anyone reviews a change people can see, run the branch locally and look at the screens it changes, in the\nstates, themes, widths and roles the change could break. Fix what you find, shoot it again, and report what you\ncovered, what you didn't, and what's left for the user to decide.\n\n## Rules that apply throughout\n\n- **Never copy the QA working folder anywhere shared** (a notes vault, a file share, a PR, the repository). Its\n  browser profile holds session cookies and its login files hold passwords. Copy out the individual screenshots and\n  the report page only.\n- **Use synthetic data only.** Made-up names, blank public forms, sample files you created. Never real customer\n  records or documents, even on a local stack.\n- **Take the \"before\" shot before you change the code.** Every fix needs a before and an after of the same state, at\n  the same width and theme.\n- **Fix bugs and obvious polish without asking.** Collect anything with a real trade-off (copy the user may have\n  opinions on, a layout choice, a behavior change) as a decision with your recommendation, and keep going. Stopping\n  for each one leaves the user babysitting the pass.\n- **Open every screenshot, cropped and zoomed, and read it.** A step that finishes without errors only proves its\n  selectors matched.\n- **On a busy machine, a browser test that fails at a different step on each run points to load.** Check the load\n  average (`uptime`) and rerun the test on the parent commit before you blame the branch.\n\n## Settings\n\nRead the `## Agent workflow settings` section of the repository's root `AGENTS.md` (see the playbook's\n`CONFIGURE.md`):\n\n- `### Local stack and QA`: how to start the app, how to create test users and data, and where screenshots and reports\n  go (the working folder, which stays on this machine). It may also name where reports are published (`QA reports are\n  published to: ...`).\n- `### Tests`: how to run one test file, and which suites must run one at a time.\n- `### What the agent may do without asking`: whether you may commit, push and post PR comments. Read this one from\n  the base branch, not the checkout (the playbook's `CONFIGURE.md`, \"Who approves what\").\n\nIf a setting you need is missing, ask the user once and offer to add the answer to that section. For the report's\ndestination, offer the options in `references\u002Freport-format.md`.\n\n## 1. Before you start\n\n1. Work in the branch's own checkout or worktree, with its own ports and database if the repo provides them. If the\n   branch is behind the base and lacks something the pass needs, ask before rebasing.\n2. Make the working folder, named after the branch and date (for example `~\u002Fqa\u002F\u003Crepo>\u002F\u003Cbranch>-2026-01-15\u002F`), with\n   `steps\u002F`, `screenshots\u002F`, `report\u002F` and `logs\u002F` inside. Export it as `QA_DIR` before starting the stack and the\n   browser.\n3. Start the stack with the command from the settings. Export any environment a feature needs first. Read secrets\n   into the environment without printing them (`export KEY=\"$(grep '^KEY=' .env.local | cut -d= -f2-)\"`).\n4. Create test users with the repo's seed or test-user script, one credentials file per user inside `QA_DIR`. Make a\n   new user whenever a state needs a fresh account (onboarding, an empty list). Never paste the credentials into\n   chats, PRs, tickets or notes.\n5. Expect the first load of each page in development to compile its assets, which can take a minute on a busy\n   machine. Give navigations a long timeout rather than retrying them.\n\n## 2. Plan the screens and states\n\nRead `references\u002Fstate-matrix.md` now, before the first screenshot. It lists the states, paths, themes and widths to\ncover, what to check in each shot, and the findings list format.\n\nIn short: list what the branch changes for people (`git diff --stat \u003Cbase>...`, then the views, components, styles,\npages, emails and copy it touches). Exercise the changed interaction fully: its states (empty, loading or in progress,\ndone, failed, disabled, limits, long text, many items), its paths (skip, cancel, retry, go back, reload halfway) and the\nroles that see it. Then add the themes and widths the product supports where the change could look different: a layout\nor style change needs each supported theme and the narrow widths, a copy change needs the width where the text is\nlongest. Sample screens that only share a changed component. Write down the matrix you chose and what you left out, so\nthe report can say exactly what was tested. Give each area a letter and each finding an ID (A1, A2, B1).\n\n## 3. Drive the browser with step files\n\nWrite one small script per screen or state in `QA_DIR\u002Fsteps\u002F`, so you can run the same step again for the \"after\"\nshot. Use the browser automation your harness or repo already has (Playwright, Puppeteer, a browser MCP server). If\nthe repo has nothing, `scripts\u002Frun_step.mjs` in this skill is a short Playwright example to copy and adapt.\n\nInstalling Playwright adds a dependency to the repository (and a `package.json`, if it has none) and downloads a\nChromium build, so show the user the install command and ask before running it. Pin an exact version that has been out\nfor a while; `npx playwright install` then fetches the browser build that version expects. After copying the runner\nto `scripts\u002Fqa\u002F` in your repo:\n\n```bash\nnpm install --save-dev --save-exact playwright@1.64.1 && npx playwright install chromium   # once, after a yes\nexport QA_BASE_URL=http:\u002F\u002Flocalhost:3000 QA_DIR=~\u002Fqa\u002Fmyapp\u002Fmy-branch-2026-01-15\nnode scripts\u002Fqa\u002Frun_step.mjs \"$QA_DIR\u002Fsteps\u002Fsettings.mjs\"                 # the \"before\" shots\nQA_SUFFIX=R2 node scripts\u002Fqa\u002Frun_step.mjs \"$QA_DIR\u002Fsteps\u002Fsettings.mjs\"    # the \"after\" shots, as \u003Cname>-R2.png\n```\n\nA step exports one async function that gets the page and a few helpers (`url`, `viewport`, `theme`, `settle`,\n`shot`, `clearHover`, `boxes`, `newContext`). `scripts\u002Fexample_step.mjs` shows one. The runner keeps cookies between\nruns in `QA_DIR\u002Fbrowser-profile`, prints what the step returns, and prints the console errors and uncaught exceptions\nfrom every page the step used, popups and `qa.newContext()` contexts included: treat each as a finding. If you drive\nthe browser another way, attach the error listeners to every page and context yourself, or say in the report which\nones weren't watched.\n\n## 4. Force each state\n\n- Prefer real conditions first: an environment variable (restart the service after), a record changed through the\n  app's console or seed script, the account's plan or permissions, a limit you actually reach. To catch a background\n  job's queued state, stop the job worker, take the shot, then start it again.\n- Then intercept requests for failures and server answers you can't produce for real: in Playwright,\n  `page.route('**\u002Fapi\u002Fupload', (route) => route.abort())` for a network failure, or\n  `route.fulfill({ status: 500, contentType: 'application\u002Fjson', body: '{\"error\":\"...\"}' })` for a server error or a\n  poll that never finishes. Remove the route at the end of the step (`page.unroute`).\n- For a signed-out visitor or a second user, open a fresh browser context in the step with no cookies\n  (`qa.newContext('signed-out')` in the example runner, so its errors are watched too). An owner usually sees more\n  than a visitor.\n- If you change code to force a state, change it back and check `git diff` before you commit.\n\n## 5. Fix as you go\n\nFor each problem:\n\n1. Take the \"before\" shot (if the step that found it didn't already).\n2. Fix it. Check the dev server or bundler log for build errors before you conclude a fix didn't work.\n3. Run the step again with a new suffix (`QA_SUFFIX=R2`), so the earlier shot survives.\n4. Check the \"after\" really shows the fix: its file time is later than your edit, and the zoomed crop shows the change.\n   An \"after\" taken before the fix, or cropped so the change is out of frame, proves nothing.\n5. Read every control's value in the after shot, and separately whether the viewer can change it. Each control shows\n   the effective value; disabling a control doesn't change its value, so a disabled, ticked checkbox is right when the\n   setting is on and the viewer can't edit it.\n6. Run the tests for the files you touched (one at a time for suites that share state) and the linter.\n7. For visual fixes, look at each supported theme, and use your design-review skill if the repo has one.\n\nRead `references\u002Fscreenshot-pitfalls.md` whenever a shot looks wrong or a fix seems not to have worked. Check the\nbuild, the page state, the viewport, the theme and whether the page had finished loading before you decide; and tell a\ncapture problem from a real defect before you reset anything, since a blank band can be either.\n\n## 6. Report\n\nRead `references\u002Freport-format.md` before you write the report. It covers the structure, the destinations (a private\nhosted page such as an artifact, a PR comment with images, a static page), images and later rounds.\n\nThe order is fixed: the decisions the user needs to make, each with a recommendation; then small defaults you'll take\nunless they object; then findings by area with before and after shots and the state each shot shows; then what you\ndidn't test and why. Each round of the user's feedback becomes a new \"Round N\" section at the top of the same report.\n\n## 7. After the pass\n\n- Commit fixes locally as the settings allow, in themed commits. By default, push only after the user has seen the\n  report (visible changes are theirs to accept), unless they or the settings say otherwise. The precedence for approvals\n  is in the playbook's `CONFIGURE.md`: the user's instruction in the task, then the settings, then what invoking this\n  skill approves (fixing and committing locally). Don't commit screenshots.\n- Once the branch has a PR, draft the QA results comment (date, commit SHA, what passed, what wasn't tested) and post\n  it when the settings allow posting comments, or after the user approves the text.\n- Turn a lesson that would help the next pass (a pitfall, a way to force a state) into an edit to the repo's QA\n  runbook or the nearest `AGENTS.md`, in the branch's PR.\n- Leave the stack running while the user reviews. Stop it, and the browser, when they're done.\n",{"name":5,"metadata":24,"description":7},{"version":25},"1.0.0","main","70b6a3a3a7c774671e45af646306e1448baf0511","plugins\u002FDocSpring\u002Fdocspring-agent-playbook\u002Fskills\u002Fui-qa-pass",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill ui-qa-pass",{"tool":42,"command":43},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill ui-qa-pass",{"tool":45,"command":46},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill ui-qa-pass","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FDocSpring\u002Fdocspring-agent-playbook\u002Fskills\u002Fui-qa-pass\u002FSKILL.md",true,[50,56,60,64,70],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Freport-format.md","REFERENCE","参考文档",3881,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FDocSpring\u002Fdocspring-agent-playbook\u002Fskills\u002Fui-qa-pass\u002Freferences\u002Freport-format.md",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fscreenshot-pitfalls.md",2599,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FDocSpring\u002Fdocspring-agent-playbook\u002Fskills\u002Fui-qa-pass\u002Freferences\u002Fscreenshot-pitfalls.md",{"path":61,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fstate-matrix.md",6350,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FDocSpring\u002Fdocspring-agent-playbook\u002Fskills\u002Fui-qa-pass\u002Freferences\u002Fstate-matrix.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fexample_step.mjs","SCRIPT","脚本",1617,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FDocSpring\u002Fdocspring-agent-playbook\u002Fskills\u002Fui-qa-pass\u002Fscripts\u002Fexample_step.mjs",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Frun_step.mjs",6575,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FDocSpring\u002Fdocspring-agent-playbook\u002Fskills\u002Fui-qa-pass\u002Fscripts\u002Frun_step.mjs",[75,84,92,100,108,116],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":19},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]