[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72VRAEBX669QY0SDKV4T3PV":3,"skill-same:01M72VRAEBX669QY0SDKV4T3PV":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":13,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M72VRAEBX669QY0SDKV4T3PV","qa",null,"QA a change in the running program, the way its user meets it: drive a CLI or terminal UI through tmux, a web app through a browser, and check every requested behavior against what you observe. Use after implementing a change and before code review, or when the user asks for a QA pass, a smoke test, or a click-through of a change, or asks whether it actually works.","ahmedfidi-cmyk\u002Ftims-backend","ahmedfidi-cmyk","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F282680283?v=4","01M72VFG0D2NJTYVD30HNN0F7R","01M72VFG1MR1AGGXS2MN2YAGTZ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fahmedfidi-cmyk\u002Ftims-backend\u002Fblob\u002Falternative\u002F.agents\u002Fskills\u002Fqa\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: qa\ndescription: \"QA a change in the running program, the way its user meets it: drive a CLI or terminal UI through tmux, a web app through a browser, and check every requested behavior against what you observe. Use after implementing a change and before code review, or when the user asks for a QA pass, a smoke test, or a click-through of a change, or asks whether it actually works.\"\nargument-hint: \"[fixed-point] [spec-path]\"\nlicense: MIT\ncompatibility: Drives terminal programs through tmux, and web apps through whichever browser tool the session has (Chrome DevTools MCP, Claude in Chrome, Playwright MCP, or the host's own).\n---\n\nQA checks the running program against what was requested; tests check the code against what its author expected. A scenario passes only on a result you **observed** in the running program. A green suite, a read of the code, or an exit status on its own is not an observation.\n\nQA hunts for the fail. The author of a change grades it too kindly, so when this session wrote the change, run QA in a fresh subagent: give it the diff, the request, and this skill, and tell it to find where the change breaks.\n\nQA runs before `code-review`: once QA shows the change does what was asked, the review can spend itself on how the code is written and how it fails.\n\nQA reports to its caller and leaves the code and the issue tracker as it found them: it files, comments on, and labels no issue, since a fail in unmerged work is the caller's to fix, not a ticket. Scratch state goes in `$DIR`, a fresh `mktemp -d`. The caller fixes each fail, test-first, and runs QA again.\n\n## Process\n\n### 1. Pin the change and the request\n\nThe change is the diff since a fixed point: the one the caller or user names; else the default branch, when `HEAD` is on another branch; else `HEAD`, when the default branch has uncommitted work. Write the diff to disk with `git diff \u003Cfixed-point> > \"$DIR\u002Fdiff.patch\"` and read that file in full: a shell hook can shorten a diff printed to the terminal, and a redirected one lands on disk whole. Also read each untracked file `git status --short` lists.\n\nThe request is what the change was meant to do: the spec or issue the caller passes, else the issue its commits reference, else the request settled in this conversation. With none, ask.\n\n### 2. Write the scenarios\n\nA **scenario** is one thing a user does and the result they should then see: the steps, and the expected result taken from the request. Write the list to `$DIR\u002Fscenarios.md` before you launch anything, covering:\n\n- every requirement in the request;\n- every user-reachable path the diff changes that the request never names (a new flag, a reworded message, a moved button);\n- the unhappy paths of each: invalid or empty input, cancel or interrupt midway, the same action twice, a first run with no saved state;\n- data attacks on each new input: Goldilocks (too small, too big, just right), each boundary and one past it, 0, 1, and many items, and text with unicode, emoji, leading or trailing spaces, quotes, delimiters, and a newline;\n- CRUD on each record the change writes: create, read, update, and delete it, and follow the data to every view that shows it and through a restart;\n- a flow: the scenarios chained one after another with no reset between them, the way a user's session runs, entering and leaving each state the change adds;\n- one existing flow that shares the changed code, to catch a regression next to the change.\n\nAbove the scenarios, list the change's invariants under **Never and always**: what must never happen (data lost, a file left half-written, a secret in a log) and what must always hold (the terminal restored, the old data still readable). Check them after every scenario, the unhappy ones most of all.\n\nFor a change meant to keep behavior (a refactor), the expected result is the base build's screen. Export the base commit with `git archive \u003Cbase> | tar -x -C \"$DIR\u002Fbase\"` and build it there. A `git worktree` shares `.git\u002Fhooks` with the main checkout, so a dependency install in one runs the old commit's `prepare` script and rewrites the main checkout's hooks. Drive both builds with the same keys, from folders with the same name and the same seeded state, and diff the captures. Mask only what changes on every run, such as a clock.\n\nDone when every requirement and every changed user-reachable path maps to at least one scenario.\n\n### 3. Launch the program\n\nBuild and start it from the working tree with the repo's own commands (its README, `package.json` scripts, `Makefile`, or `--help`). Point it at scratch state: a directory under `$DIR`, a test database, a seeded test account, a local server. A scenario that can only run against real user data, a production service, or a live account is **blocked**: name what it needs and move on.\n\nPick the driver by the program's interface:\n\n- A CLI or terminal UI: read [TERMINAL.md](TERMINAL.md).\n- A web app: read [BROWSER.md](BROWSER.md).\n- A library or HTTP API with no UI: call its public interface from a scratch script in `$DIR`, or with `curl`, the way its caller would.\n\n### 4. Run every scenario\n\nDo each step as the user would: type the command, press the keys, click, fill in the form, submit. After each step, read what the program shows and compare it with the expected result. Check the logs, stderr, and browser console for errors on every scenario, passing ones too.\n\nJudge each result with the FEW HICCUPPS oracles as well as the request. A result that matches the request still fails when it contradicts the rest of the product (a sibling command names its flags, keys, or exit codes another way), the program's own claims (`--help`, the README, its error text), or the conventions of its platform and of comparable tools (`NO_COLOR`, `-` for stdin, a 4xx status for a bad request). An error message passes when it names the bad input and what to do next.\n\nA screen that says \"Saved\" shows only that the program claims the write. Confirm each write at its store: read back the file, the database row, or the API, then restart or reload and read it again.\n\nRecord each scenario in `scenarios.md` as **pass**, **fail**, or **blocked**, with its evidence: the captured screen, the output, a screenshot path, the error. Evidence is what the tool wrote: redirect or `tee` output into a file in `$DIR` and cite that file, so a retyped summary never stands in for it. A fail also records the steps that reproduce it, the expected result, and the observed one. Before you record a fail, spend a few steps on it:\n\n- **Isolate**: cut the steps to the fewest that still fail.\n- **Maximize**: follow the same path to a worse outcome, such as a crash or lost data.\n- **Generalize**: try the sibling paths that reach the same code, and name every one that fails.\n- **Introduced or pre-existing**: run the same steps on the base build, exported as for a refactor, and record which it is.\n\nA fail ends that scenario, not the run.\n\nOnce every scripted scenario has a status, run one exploratory charter on the riskiest part of the change: \"Explore \u003Ctarget> with \u003Cresources> to discover \u003Cinformation>\", for about twenty actions. Add each problem it finds to `scenarios.md` as a new scenario with its status.\n\nDone when every scenario has a status and its evidence.\n\n### 5. Clean up and report\n\nStop everything you started: each tmux session with `tui stop qa-\u003Cname>` (the run's tmux server exits with its last session), then servers and browser tabs. Delete `$DIR` and every other scratch directory by its literal path, typed out as the earlier call printed it, keeping only the evidence files the report cites: an `rm -rf` on a variable or a command substitution, such as `\"$(cat \u002Ftmp\u002Fqa-dir)\"`, is denied. Done when `tmux ls` lists none of your sessions and `$DIR` holds nothing but those evidence files. A cleanup command that fails or is blocked goes in the report as leftover state, with the command to remove it.\n\nReport one line per scenario (status, what it checked, the evidence or its path), then every fail in full, then:\n\n- **Not covered**: what no scenario tested and why, such as a platform, a browser, or a terminal you did not run.\n- **Concerns**: what is neither a pass nor a fail but looked wrong, such as a slow first load or a stray warning. A result that contradicts a sentence of the request is a fail, also when that sentence calls the path unchanged or out of scope.\n\nThen the verdict:\n\n- Any fail: **Fails QA**.\n- Otherwise, any blocked scenario: **Passes with gaps**, naming each blocked scenario and what it needs.\n- Otherwise: **Passes QA**.\n","QA checks the running program against what was requested; tests check the code against what its author expected. A scenario passes only on a result you **observed** in the running program. A green suite, a read of the code, or an exit status on its own is not an observation.\n\nQA hunts for the fail. The author of a change grades it too kindly, so when this session wrote the change, run QA in a fresh subagent: give it the diff, the request, and this skill, and tell it to find where the change breaks.\n\nQA runs before `code-review`: once QA shows the change does what was asked, the review can spend itself on how the code is written and how it fails.\n\nQA reports to its caller and leaves the code and the issue tracker as it found them: it files, comments on, and labels no issue, since a fail in unmerged work is the caller's to fix, not a ticket. Scratch state goes in `$DIR`, a fresh `mktemp -d`. The caller fixes each fail, test-first, and runs QA again.\n\n## Process\n\n### 1. Pin the change and the request\n\nThe change is the diff since a fixed point: the one the caller or user names; else the default branch, when `HEAD` is on another branch; else `HEAD`, when the default branch has uncommitted work. Write the diff to disk with `git diff \u003Cfixed-point> > \"$DIR\u002Fdiff.patch\"` and read that file in full: a shell hook can shorten a diff printed to the terminal, and a redirected one lands on disk whole. Also read each untracked file `git status --short` lists.\n\nThe request is what the change was meant to do: the spec or issue the caller passes, else the issue its commits reference, else the request settled in this conversation. With none, ask.\n\n### 2. Write the scenarios\n\nA **scenario** is one thing a user does and the result they should then see: the steps, and the expected result taken from the request. Write the list to `$DIR\u002Fscenarios.md` before you launch anything, covering:\n\n- every requirement in the request;\n- every user-reachable path the diff changes that the request never names (a new flag, a reworded message, a moved button);\n- the unhappy paths of each: invalid or empty input, cancel or interrupt midway, the same action twice, a first run with no saved state;\n- data attacks on each new input: Goldilocks (too small, too big, just right), each boundary and one past it, 0, 1, and many items, and text with unicode, emoji, leading or trailing spaces, quotes, delimiters, and a newline;\n- CRUD on each record the change writes: create, read, update, and delete it, and follow the data to every view that shows it and through a restart;\n- a flow: the scenarios chained one after another with no reset between them, the way a user's session runs, entering and leaving each state the change adds;\n- one existing flow that shares the changed code, to catch a regression next to the change.\n\nAbove the scenarios, list the change's invariants under **Never and always**: what must never happen (data lost, a file left half-written, a secret in a log) and what must always hold (the terminal restored, the old data still readable). Check them after every scenario, the unhappy ones most of all.\n\nFor a change meant to keep behavior (a refactor), the expected result is the base build's screen. Export the base commit with `git archive \u003Cbase> | tar -x -C \"$DIR\u002Fbase\"` and build it there. A `git worktree` shares `.git\u002Fhooks` with the main checkout, so a dependency install in one runs the old commit's `prepare` script and rewrites the main checkout's hooks. Drive both builds with the same keys, from folders with the same name and the same seeded state, and diff the captures. Mask only what changes on every run, such as a clock.\n\nDone when every requirement and every changed user-reachable path maps to at least one scenario.\n\n### 3. Launch the program\n\nBuild and start it from the working tree with the repo's own commands (its README, `package.json` scripts, `Makefile`, or `--help`). Point it at scratch state: a directory under `$DIR`, a test database, a seeded test account, a local server. A scenario that can only run against real user data, a production service, or a live account is **blocked**: name what it needs and move on.\n\nPick the driver by the program's interface:\n\n- A CLI or terminal UI: read [TERMINAL.md](TERMINAL.md).\n- A web app: read [BROWSER.md](BROWSER.md).\n- A library or HTTP API with no UI: call its public interface from a scratch script in `$DIR`, or with `curl`, the way its caller would.\n\n### 4. Run every scenario\n\nDo each step as the user would: type the command, press the keys, click, fill in the form, submit. After each step, read what the program shows and compare it with the expected result. Check the logs, stderr, and browser console for errors on every scenario, passing ones too.\n\nJudge each result with the FEW HICCUPPS oracles as well as the request. A result that matches the request still fails when it contradicts the rest of the product (a sibling command names its flags, keys, or exit codes another way), the program's own claims (`--help`, the README, its error text), or the conventions of its platform and of comparable tools (`NO_COLOR`, `-` for stdin, a 4xx status for a bad request). An error message passes when it names the bad input and what to do next.\n\nA screen that says \"Saved\" shows only that the program claims the write. Confirm each write at its store: read back the file, the database row, or the API, then restart or reload and read it again.\n\nRecord each scenario in `scenarios.md` as **pass**, **fail**, or **blocked**, with its evidence: the captured screen, the output, a screenshot path, the error. Evidence is what the tool wrote: redirect or `tee` output into a file in `$DIR` and cite that file, so a retyped summary never stands in for it. A fail also records the steps that reproduce it, the expected result, and the observed one. Before you record a fail, spend a few steps on it:\n\n- **Isolate**: cut the steps to the fewest that still fail.\n- **Maximize**: follow the same path to a worse outcome, such as a crash or lost data.\n- **Generalize**: try the sibling paths that reach the same code, and name every one that fails.\n- **Introduced or pre-existing**: run the same steps on the base build, exported as for a refactor, and record which it is.\n\nA fail ends that scenario, not the run.\n\nOnce every scripted scenario has a status, run one exploratory charter on the riskiest part of the change: \"Explore \u003Ctarget> with \u003Cresources> to discover \u003Cinformation>\", for about twenty actions. Add each problem it finds to `scenarios.md` as a new scenario with its status.\n\nDone when every scenario has a status and its evidence.\n\n### 5. Clean up and report\n\nStop everything you started: each tmux session with `tui stop qa-\u003Cname>` (the run's tmux server exits with its last session), then servers and browser tabs. Delete `$DIR` and every other scratch directory by its literal path, typed out as the earlier call printed it, keeping only the evidence files the report cites: an `rm -rf` on a variable or a command substitution, such as `\"$(cat \u002Ftmp\u002Fqa-dir)\"`, is denied. Done when `tmux ls` lists none of your sessions and `$DIR` holds nothing but those evidence files. A cleanup command that fails or is blocked goes in the report as leftover state, with the command to remove it.\n\nReport one line per scenario (status, what it checked, the evidence or its path), then every fail in full, then:\n\n- **Not covered**: what no scenario tested and why, such as a platform, a browser, or a terminal you did not run.\n- **Concerns**: what is neither a pass nor a fail but looked wrong, such as a slow first load or a stray warning. A result that contradicts a sentence of the request is a fail, also when that sentence calls the path unchanged or out of scope.\n\nThen the verdict:\n\n- Any fail: **Fails QA**.\n- Otherwise, any blocked scenario: **Passes with gaps**, naming each blocked scenario and what it needs.\n- Otherwise: **Passes QA**.\n",{"name":5,"license":14,"description":7,"argument-hint":23,"compatibility":24},"[fixed-point] [spec-path]","Drives terminal programs through tmux, and web apps through whichever browser tool the session has (Chrome DevTools MCP, Claude in Chrome, Playwright MCP, or the host's own).","alternative","802b0604842ee12ea60f220a6e1350b2619bc8cf",".agents\u002Fskills\u002Fqa","https:\u002F\u002Fgithub.com\u002Fahmedfidi-cmyk\u002Ftims-backend","https:\u002F\u002Flahtha-henna.vercel.app","https:\u002F\u002Fgithub.com\u002Fahmedfidi-cmyk","2026-10-27 07:26:23",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add ahmedfidi-cmyk\u002Ftims-backend --skill qa",{"tool":38,"command":39},"bunx","bunx skills add ahmedfidi-cmyk\u002Ftims-backend --skill qa",{"tool":41,"command":42},"pnpm","pnpm dlx skills add ahmedfidi-cmyk\u002Ftims-backend --skill qa","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fahmedfidi-cmyk\u002Ftims-backend\u002Fblob\u002Falternative\u002F.agents\u002Fskills\u002Fqa\u002FSKILL.md",true,[46,52,56,62],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",117,"https:\u002F\u002Fgithub.com\u002Fahmedfidi-cmyk\u002Ftims-backend\u002Fblob\u002Falternative\u002F.agents\u002Fskills\u002Fqa\u002Fagents\u002Fopenai.yaml",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"BROWSER.md",2545,"https:\u002F\u002Fgithub.com\u002Fahmedfidi-cmyk\u002Ftims-backend\u002Fblob\u002Falternative\u002F.agents\u002Fskills\u002Fqa\u002FBROWSER.md",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"scripts\u002Ftui.sh","SCRIPT","脚本",6907,"https:\u002F\u002Fgithub.com\u002Fahmedfidi-cmyk\u002Ftims-backend\u002Fblob\u002Falternative\u002F.agents\u002Fskills\u002Fqa\u002Fscripts\u002Ftui.sh",{"path":63,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":64,"sourceHtmlUrl":65},"TERMINAL.md",5575,"https:\u002F\u002Fgithub.com\u002Fahmedfidi-cmyk\u002Ftims-backend\u002Fblob\u002Falternative\u002F.agents\u002Fskills\u002Fqa\u002FTERMINAL.md",[67,74,81,88,95,102],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M72VVQV31E4P4D5BA308VPMQ","writing-for-agents","Writing documents for agents. Use when creating or editing skills, modifying AGENTS.md or CLAUDE.md, or writing any doc an agent reaches by a pointer.","https:\u002F\u002Fgithub.com\u002Fahmedfidi-cmyk\u002Ftims-backend\u002Fblob\u002Falternative\u002F.agents\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M72VVNWQVHCPFYPBV66TXEQV","what-would-you-do","Explain the question you just asked and recommend an answer, with the case for and against each option.","https:\u002F\u002Fgithub.com\u002Fahmedfidi-cmyk\u002Ftims-backend\u002Fblob\u002Falternative\u002F.agents\u002Fskills\u002Fwhat-would-you-do\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M72VVKZ37YPKJRD4F8TH93HK","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fahmedfidi-cmyk\u002Ftims-backend\u002Fblob\u002Falternative\u002F.agents\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M72VVJQYG2HWQM83SRV4C006","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fahmedfidi-cmyk\u002Ftims-backend\u002Fblob\u002Falternative\u002F.agents\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M72VV2PJD13XP3WQW5181X2C","triage","Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.","https:\u002F\u002Fgithub.com\u002Fahmedfidi-cmyk\u002Ftims-backend\u002Fblob\u002Falternative\u002F.agents\u002Fskills\u002Ftriage\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":18},"01M72VTZ6YFH6MSE62Z05Q5JW0","to-tickets","Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).","https:\u002F\u002Fgithub.com\u002Fahmedfidi-cmyk\u002Ftims-backend\u002Fblob\u002Falternative\u002F.agents\u002Fskills\u002Fto-tickets\u002FSKILL.md",[],[]]