[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AX7WBXX2ADS0DEMA7DCQ6C":3,"skill-same:01M7AX7WBXX2ADS0DEMA7DCQ6C":54},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":30,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7AX7WBXX2ADS0DEMA7DCQ6C","mutation-audit",null,"Measuring whether UZE's tests would notice the code being wrong, with cargo-mutants - starting and monitoring `mutants.yml`, downloading the evidence, triaging each surviving mutant, writing the test a real gap needs and proving it catches the mutant. Use when someone asks about mutation testing, mutants, survivors, `missed.txt` or a \"Missed mutant\" annotation, whether tests really prove anything or only pass (\"os testes testam mesmo?\", \"teste que só passa\"), to audit a crate's tests, to check tests an agent wrote, or before refactoring code whose tests nobody has measured. Not for reviewing a whole change (that is `code:polish`), not for a coverage figure alone, and not for a security audit (that is `security-audit`).","uze-sh\u002Fuze","uze-sh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F334211959?v=4","01M7AX5KNT81AC56YMRT586MBW","uze","01M7AX5KPDQA2QP7DWGZFMH4PQ",4,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmutation-audit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mutation-audit\ndescription: Measuring whether UZE's tests would notice the code being wrong, with cargo-mutants - starting and monitoring `mutants.yml`, downloading the evidence, triaging each surviving mutant, writing the test a real gap needs and proving it catches the mutant. Use when someone asks about mutation testing, mutants, survivors, `missed.txt` or a \"Missed mutant\" annotation, whether tests really prove anything or only pass (\"os testes testam mesmo?\", \"teste que só passa\"), to audit a crate's tests, to check tests an agent wrote, or before refactoring code whose tests nobody has measured. Not for reviewing a whole change (that is `code:polish`), not for a coverage figure alone, and not for a security audit (that is `security-audit`).\ncompatibility: The GitHub CLI for runs; for the local lab, Linux with bubblewrap (bwrap), cargo and this repository's `security-audit` skill, whose sandbox it uses.\n---\n\n# Mutation audit\n\nCoverage says a line ran. A mutant asks whether a test would notice that line\nbeing wrong. The output of an audit is a triaged list and the tests it led to,\nnever a score.\n\n## The rules everything else serves\n\n**A test states behavior, and the mutant only points at it.** Read what the\ncode should do from its doc comment, `docs\u002Farchitecture\u002Finvariants.md`, the\nOpenSpec specs or the rule that owns it. A test copied from what the code does\ntoday locks in whatever bug it has. If nothing says what is right, stop and ask;\nthat absence is a finding.\n\n**A survivor is a question.** It may be a real gap, a mutant no test could\ncatch, or something only another crate's tests would catch. Read the code before\nconcluding anything.\n\n**No target score.** Some mutants are equivalent, so 100% is not the goal.\nCompare a crate with its own earlier runs, and never write a test only to move\nthe number.\n\n**A claim is proven by re-running the mutant.** \"This test covers it\" counts\nonce that mutant reads `caught`.\n\n## Before starting: results are public\n\nThe repository is public, so a run's logs, annotations, summary and artifacts\nare too. A survivor in a check names a check no test protects.\n\n- Before dispatching a crate that holds trust, consent, confinement, approval or\n  acquisition, confirm the operator accepts that, or use the lab below, which\n  publishes nothing.\n- If triage finds an exploitable flaw and not only a missing test, stop and\n  follow the `security-findings` rule. It enters the repository with its fix,\n  and the commit, test name and PR text do not explain the attack before then.\n\n## The loop\n\n### 1. Measure\n\n```sh\ngh workflow run mutants.yml -f package=\u003Ccrate>                      # that crate's tests\ngh workflow run mutants.yml -f package=\u003Ccrate> -f test_scope=workspace\ngh workflow run mutants.yml -f package=\u003Ccrate> -f mode=diff -f base=\u003Ctag> -f ref=\u003Cbranch>\n```\n\nScope `crate` is a cheap list of candidates and overstates survivors, because a\nfoundation crate's behavior is often tested by whoever uses it. Scope `workspace`\nis the verdict on whether the project as a whole notices. Use `workspace` for a\nsmall crate and `crate` first for a large one, then confirm what matters in the\nlab. In scope `crate`, the survivors of `uze-contract\u002Fsrc\u002Fdocs.rs` mean nothing: it\ncompiles only with feature `schema`, which that scope leaves off. `mode=diff` suits a branch or a release range. `ref` defaults to `main`, so\nname the branch you are auditing, or the run measures something else and succeeds.\n\nStart one crate at a time: GitHub keeps one run waiting, and a third start\nreplaces it. A run shares the account's 20 concurrent jobs with `ci.yml`, so\ncancel it (`gh run cancel \u003Cid>`) when a delivery needs them.\n\nMeasured so far, for planning a run rather than as a promise:\n\n| Run | Mutants | Median per mutant | Runner-hours | Wall clock |\n|---|---|---|---|---|\n| `uze-document`, scope `crate` | 69 | 1 s | 0.3 | 20 min |\n| `uze-document`, scope `workspace` | 69 | 97 s | 2.6 | 48 min |\n\nA mutant in a foundation crate rebuilds what depends on it, so scope `workspace`\ncosts most there.\n\n### 2. Collect\n\n```sh\ngh run watch \u003Cid> --exit-status\ngh run download \u003Cid> --pattern 'mutants-*' --dir \u003Cscratch>\npython3 .github\u002Fscripts\u002Fmutants.py report \u003Cscratch> \\\n  --package \u003Ccrate> --planned \u003Cn> --commit \u003Csha> --missed \u003Cscratch>\u002Fmissed.txt\n```\n\nThe run's summary has the same report. Annotations are only a sample of the\nsurvivors, so read `missed.txt`. **Incomplete** means shards ran out of time:\nraise `-f shards=\u003Cn>` before reading the score. A job's success says the run\nworked, and survivors do not fail it.\n\n### 3. Triage\n\nOpen each survivor at its line and put it in one row. Have someone who did not\nwrite the code judge it (the `code:reviewer` agent), since whoever wrote it reads\nwhat they meant.\n\n| Verdict | How to recognize it | What to do |\n|---|---|---|\n| **Real gap** | The change would alter something a user or a later check relies on | Step 4 |\n| **Caught elsewhere** | Scope was `crate`, and the behavior is exercised by a consumer | Re-run in scope `workspace` |\n| **Equivalent** | The mutant cannot change behavior: an unreachable branch, a value equal to what it replaces | Record it in `.cargo\u002Fmutants.toml` with the reason |\n| **Not worth testing** | A log line, a debug message, cosmetic output | Exclude it with the reason, if it recurs |\n\nPatterns from past audits:\n\n- `-> bool with true` **and** `with false` both surviving: nothing checks the\n  answer. It is the strongest signal on the list.\n- Only `with true` surviving: every test sees the true case, and nobody asked\n  whether the function ever says no.\n- `replace > with >=`: no test sits on the boundary. First check whether equality\n  can reach that line at all, since an earlier return makes the mutant equivalent.\n- `replace f -> Vec\u003C_> with vec![]` on something a check iterates: the check still\n  passes, having checked nothing.\n- A match guard replaced `with true`: a narrow error handler became a catch-all.\n  Failure paths are where this hides, as a test rarely forces a read to fail.\n\n### 4. Write the test\n\nName the behavior, and say in a comment why it matters only when that is not\nobvious. The test belongs with the code it proves, in the crate that owns the\nrule, even if a consumer already covers part of it. Don't assert an\nimplementation detail or duplicate the expression under test:\n\n```rust\nassert!(may_vote(18));                \u002F\u002F states the rule\nassert_eq!(may_vote(18), 18 >= 18);   \u002F\u002F copies the code and proves nothing\n```\n\nA test for a bug the mutant exposed lands with the fix, in a `fix:` commit. A test\nfor correct code is a `test:` commit.\n\n### 5. Prove it\n\nRun the lab over the changed files, which leaves a list that should be shorter by\nexactly what you meant to catch. `scripts\u002Flab` is relative to this skill, and the\nscript works from any directory:\n\n```sh\nAUDIT=\u003Cdir> scripts\u002Flab --package \u003Ccrate> --file '\u003Cpath>'\n```\n\n`\u003Cdir>` sits on a disk, outside the repository: the builds outgrow a memory-backed\n`\u002Ftmp`, which everything else on the machine shares, so the lab refuses a tmpfs.\n\nAdd `--test-workspace=true` to judge against the whole workspace, which first proves\nthe suite green in the box, as `cargo-mutants`' own baseline would try only the crate, and `--re\n'\u003Cpattern>'` to re-run one mutant. Read\n`$AUDIT\u002Fboxes\u002Fmutants\u002Fwork\u002Fuze\u002Fmutants.out\u002Fmissed.txt`; the file is what proves it.\n\nThe box can mislead or get in the way in four ways:\n\n- **A false `missed`.** Bun is absent, and the OpenCode tests that need it skip\n  themselves. Before calling a survivor in that code a gap, confirm it on a CI run,\n  which installs Bun.\n- **A false `caught`.** A test that fails now and then there reads as catching the\n  mutant. When a result surprises you, read that mutant's log under\n  `mutants.out\u002Flog\u002F` to see which test failed. The timing budgets (`performance`,\n  `extension_storm`, `budget`) fail on a busy machine, so a workspace run leaves\n  them out; a mutant only they would catch reads as `missed`.\n- **The machine runs out.** The box limits neither memory nor CPU. A mutant of\n  `uze-script` can take a limit off the engine, and one test reached 33 GB.\n  Watch the available memory while that crate runs.\n- **No result.** A test that always fails there stops the run at the baseline.\n  Find out why it fails: anything in a sandbox is refused an approval, for example,\n  so those tests are filtered out for a workspace run in `scripts\u002Flab`. A bare\n  `--baseline=skip` would hide it by making every mutant read `caught`.\n\nA `caught` is only as good as the test that failed. If one test catches unrelated\nmutants, or a report is too good to be true, read the logs first.\n\n### 6. Deliver\n\nOpen an ordinary pull request. Its body says which mutants the tests now catch and\nhow many remain, with the triage for what remains, and names no attack. Comparing\nbefore and after is the evidence. Say what was not run.\n\n## Recording an equivalent mutant\n\n`.cargo\u002Fmutants.toml` is the list of what was read and set aside. Match on the file\nand the change, without the line number, which moves:\n\n```toml\n# `read` has already returned when the shape equals SHAPE.\n'uze-document\u002Fsrc\u002Flib\\.rs.*replace > with >= in read$',\n```\n\nCheck it with `AUDIT=\u003Cdir> scripts\u002Flab --list --package \u003Ccrate> | wc -l`.\nAn exclusion\nwithout its reason gets deleted, and anyone changing the code it names re-reads\nit. It is for equivalents and noise, never for a real gap someone would rather not\nfix.\n\n## Never\n\n- Run `cargo mutants` outside the lab on this machine. A mutant can take a test out\n  of its isolation, and `uze-platform` and `uze-terminal` hold code that ends\n  processes (the `ending-processes` rule).\n- Add a mutation run to the `Gate`. It is slow and it reports questions.\n- Set a mutant timeout close to the suite's own length. A mutant that outlasts the\n  limit counts as detected, so an honest slow run would inflate the score.\n- Delete or weaken an assertion to make a report tidier.\n","# Mutation audit\n\nCoverage says a line ran. A mutant asks whether a test would notice that line\nbeing wrong. The output of an audit is a triaged list and the tests it led to,\nnever a score.\n\n## The rules everything else serves\n\n**A test states behavior, and the mutant only points at it.** Read what the\ncode should do from its doc comment, `docs\u002Farchitecture\u002Finvariants.md`, the\nOpenSpec specs or the rule that owns it. A test copied from what the code does\ntoday locks in whatever bug it has. If nothing says what is right, stop and ask;\nthat absence is a finding.\n\n**A survivor is a question.** It may be a real gap, a mutant no test could\ncatch, or something only another crate's tests would catch. Read the code before\nconcluding anything.\n\n**No target score.** Some mutants are equivalent, so 100% is not the goal.\nCompare a crate with its own earlier runs, and never write a test only to move\nthe number.\n\n**A claim is proven by re-running the mutant.** \"This test covers it\" counts\nonce that mutant reads `caught`.\n\n## Before starting: results are public\n\nThe repository is public, so a run's logs, annotations, summary and artifacts\nare too. A survivor in a check names a check no test protects.\n\n- Before dispatching a crate that holds trust, consent, confinement, approval or\n  acquisition, confirm the operator accepts that, or use the lab below, which\n  publishes nothing.\n- If triage finds an exploitable flaw and not only a missing test, stop and\n  follow the `security-findings` rule. It enters the repository with its fix,\n  and the commit, test name and PR text do not explain the attack before then.\n\n## The loop\n\n### 1. Measure\n\n```sh\ngh workflow run mutants.yml -f package=\u003Ccrate>                      # that crate's tests\ngh workflow run mutants.yml -f package=\u003Ccrate> -f test_scope=workspace\ngh workflow run mutants.yml -f package=\u003Ccrate> -f mode=diff -f base=\u003Ctag> -f ref=\u003Cbranch>\n```\n\nScope `crate` is a cheap list of candidates and overstates survivors, because a\nfoundation crate's behavior is often tested by whoever uses it. Scope `workspace`\nis the verdict on whether the project as a whole notices. Use `workspace` for a\nsmall crate and `crate` first for a large one, then confirm what matters in the\nlab. In scope `crate`, the survivors of `uze-contract\u002Fsrc\u002Fdocs.rs` mean nothing: it\ncompiles only with feature `schema`, which that scope leaves off. `mode=diff` suits a branch or a release range. `ref` defaults to `main`, so\nname the branch you are auditing, or the run measures something else and succeeds.\n\nStart one crate at a time: GitHub keeps one run waiting, and a third start\nreplaces it. A run shares the account's 20 concurrent jobs with `ci.yml`, so\ncancel it (`gh run cancel \u003Cid>`) when a delivery needs them.\n\nMeasured so far, for planning a run rather than as a promise:\n\n| Run | Mutants | Median per mutant | Runner-hours | Wall clock |\n|---|---|---|---|---|\n| `uze-document`, scope `crate` | 69 | 1 s | 0.3 | 20 min |\n| `uze-document`, scope `workspace` | 69 | 97 s | 2.6 | 48 min |\n\nA mutant in a foundation crate rebuilds what depends on it, so scope `workspace`\ncosts most there.\n\n### 2. Collect\n\n```sh\ngh run watch \u003Cid> --exit-status\ngh run download \u003Cid> --pattern 'mutants-*' --dir \u003Cscratch>\npython3 .github\u002Fscripts\u002Fmutants.py report \u003Cscratch> \\\n  --package \u003Ccrate> --planned \u003Cn> --commit \u003Csha> --missed \u003Cscratch>\u002Fmissed.txt\n```\n\nThe run's summary has the same report. Annotations are only a sample of the\nsurvivors, so read `missed.txt`. **Incomplete** means shards ran out of time:\nraise `-f shards=\u003Cn>` before reading the score. A job's success says the run\nworked, and survivors do not fail it.\n\n### 3. Triage\n\nOpen each survivor at its line and put it in one row. Have someone who did not\nwrite the code judge it (the `code:reviewer` agent), since whoever wrote it reads\nwhat they meant.\n\n| Verdict | How to recognize it | What to do |\n|---|---|---|\n| **Real gap** | The change would alter something a user or a later check relies on | Step 4 |\n| **Caught elsewhere** | Scope was `crate`, and the behavior is exercised by a consumer | Re-run in scope `workspace` |\n| **Equivalent** | The mutant cannot change behavior: an unreachable branch, a value equal to what it replaces | Record it in `.cargo\u002Fmutants.toml` with the reason |\n| **Not worth testing** | A log line, a debug message, cosmetic output | Exclude it with the reason, if it recurs |\n\nPatterns from past audits:\n\n- `-> bool with true` **and** `with false` both surviving: nothing checks the\n  answer. It is the strongest signal on the list.\n- Only `with true` surviving: every test sees the true case, and nobody asked\n  whether the function ever says no.\n- `replace > with >=`: no test sits on the boundary. First check whether equality\n  can reach that line at all, since an earlier return makes the mutant equivalent.\n- `replace f -> Vec\u003C_> with vec![]` on something a check iterates: the check still\n  passes, having checked nothing.\n- A match guard replaced `with true`: a narrow error handler became a catch-all.\n  Failure paths are where this hides, as a test rarely forces a read to fail.\n\n### 4. Write the test\n\nName the behavior, and say in a comment why it matters only when that is not\nobvious. The test belongs with the code it proves, in the crate that owns the\nrule, even if a consumer already covers part of it. Don't assert an\nimplementation detail or duplicate the expression under test:\n\n```rust\nassert!(may_vote(18));                \u002F\u002F states the rule\nassert_eq!(may_vote(18), 18 >= 18);   \u002F\u002F copies the code and proves nothing\n```\n\nA test for a bug the mutant exposed lands with the fix, in a `fix:` commit. A test\nfor correct code is a `test:` commit.\n\n### 5. Prove it\n\nRun the lab over the changed files, which leaves a list that should be shorter by\nexactly what you meant to catch. `scripts\u002Flab` is relative to this skill, and the\nscript works from any directory:\n\n```sh\nAUDIT=\u003Cdir> scripts\u002Flab --package \u003Ccrate> --file '\u003Cpath>'\n```\n\n`\u003Cdir>` sits on a disk, outside the repository: the builds outgrow a memory-backed\n`\u002Ftmp`, which everything else on the machine shares, so the lab refuses a tmpfs.\n\nAdd `--test-workspace=true` to judge against the whole workspace, which first proves\nthe suite green in the box, as `cargo-mutants`' own baseline would try only the crate, and `--re\n'\u003Cpattern>'` to re-run one mutant. Read\n`$AUDIT\u002Fboxes\u002Fmutants\u002Fwork\u002Fuze\u002Fmutants.out\u002Fmissed.txt`; the file is what proves it.\n\nThe box can mislead or get in the way in four ways:\n\n- **A false `missed`.** Bun is absent, and the OpenCode tests that need it skip\n  themselves. Before calling a survivor in that code a gap, confirm it on a CI run,\n  which installs Bun.\n- **A false `caught`.** A test that fails now and then there reads as catching the\n  mutant. When a result surprises you, read that mutant's log under\n  `mutants.out\u002Flog\u002F` to see which test failed. The timing budgets (`performance`,\n  `extension_storm`, `budget`) fail on a busy machine, so a workspace run leaves\n  them out; a mutant only they would catch reads as `missed`.\n- **The machine runs out.** The box limits neither memory nor CPU. A mutant of\n  `uze-script` can take a limit off the engine, and one test reached 33 GB.\n  Watch the available memory while that crate runs.\n- **No result.** A test that always fails there stops the run at the baseline.\n  Find out why it fails: anything in a sandbox is refused an approval, for example,\n  so those tests are filtered out for a workspace run in `scripts\u002Flab`. A bare\n  `--baseline=skip` would hide it by making every mutant read `caught`.\n\nA `caught` is only as good as the test that failed. If one test catches unrelated\nmutants, or a report is too good to be true, read the logs first.\n\n### 6. Deliver\n\nOpen an ordinary pull request. Its body says which mutants the tests now catch and\nhow many remain, with the triage for what remains, and names no attack. Comparing\nbefore and after is the evidence. Say what was not run.\n\n## Recording an equivalent mutant\n\n`.cargo\u002Fmutants.toml` is the list of what was read and set aside. Match on the file\nand the change, without the line number, which moves:\n\n```toml\n# `read` has already returned when the shape equals SHAPE.\n'uze-document\u002Fsrc\u002Flib\\.rs.*replace > with >= in read$',\n```\n\nCheck it with `AUDIT=\u003Cdir> scripts\u002Flab --list --package \u003Ccrate> | wc -l`.\nAn exclusion\nwithout its reason gets deleted, and anyone changing the code it names re-reads\nit. It is for equivalents and noise, never for a real gap someone would rather not\nfix.\n\n## Never\n\n- Run `cargo mutants` outside the lab on this machine. A mutant can take a test out\n  of its isolation, and `uze-platform` and `uze-terminal` hold code that ends\n  processes (the `ending-processes` rule).\n- Add a mutation run to the `Gate`. It is slow and it reports questions.\n- Set a mutant timeout close to the suite's own length. A mutant that outlasts the\n  limit counts as detected, so an honest slow run would inflate the score.\n- Delete or weaken an assertion to make a report tidier.\n",{"name":5,"description":7,"compatibility":24},"The GitHub CLI for runs; for the local lab, Linux with bubblewrap (bwrap), cargo and this repository's `security-audit` skill, whose sandbox it uses.","main","e2cfbb55eec2aa007135f9a2256b73f7170a3b9e",".agents\u002Fskills\u002Fmutation-audit",1,"https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze","https:\u002F\u002Fuze.sh","https:\u002F\u002Fgithub.com\u002Fuze-sh","🧩 Agents come and go. Your work stays.","2026-11-13 05:15:37",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add uze-sh\u002Fuze --skill mutation-audit",{"tool":40,"command":41},"bunx","bunx skills add uze-sh\u002Fuze --skill mutation-audit",{"tool":43,"command":44},"pnpm","pnpm dlx skills add uze-sh\u002Fuze --skill mutation-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmutation-audit\u002FSKILL.md",true,[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"scripts\u002Flab","SCRIPT","脚本",4147,"https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmutation-audit\u002Fscripts\u002Flab",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7AXDFA81RA77NHGYVZRCH0E","commit","North Star fixture skill — used to prove native\u002Fgenerated delivery across harnesses.","https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002Ftests\u002F_fixtures\u002Fgolden\u002Fmarketplace\u002Fplugins\u002Fflow\u002Fskills\u002Fcommit\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7AXCYQ5WMH46JRJVF57FTHA","oc-skill","opencode native","https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002Ftests\u002F_fixtures\u002Fforeign\u002Fopencode\u002Fnative-plugin\u002Fskills\u002Foc-skill\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7AXCVSFQ76DR4GXGJ1Q9PBA","uze-plugin-first","Emits the deterministic UZE Plugin First conformance proof.","https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002Ftests\u002F_fixtures\u002Fforeign\u002Fcodex\u002Fnative-plugin\u002Fskills\u002Fuze-plugin-first\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7AXCTD57QJ3GEN54W5PREV2","hello","says hello","https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002Ftests\u002F_fixtures\u002Fforeign\u002Fclaude\u002Fnative-plugin\u002Fskills\u002Fhello\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7AXCR1HKRHJ7PP39JQS8SQ5","agy-native","antigravity native","https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002Ftests\u002F_fixtures\u002Fforeign\u002Fantigravity\u002Fnative-plugin\u002Fskills\u002Fagy-native\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7AXCNTR4WXE4VT89MK4XQST","review","Review code for correctness and missing tests","https:\u002F\u002Fgithub.com\u002Fuze-sh\u002Fuze\u002Fblob\u002Fmain\u002Ftests\u002F_fixtures\u002Fcanonical\u002Fworkflow\u002Fskills\u002Freview\u002FSKILL.md",[],[]]