[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7235KNNN1TN2AYW0QEBGXCP":3,"skill-same:01M7235KNNN1TN2AYW0QEBGXCP":61},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7235KNNN1TN2AYW0QEBGXCP","code-moniker-smell-review",null,"Review a repository with code-moniker's local and workspace check DSL for Fowler and Lanza-Marinescu code smells. Use when Codex needs to write, validate, or run project-specific warning-severity smell rules, distinguish executable local or indexed DSL checks from AST\u002Fhistory checks, triage check output, or plan follow-up evolutions for missing smell-detection operators.","ng-galien\u002Fcode-moniker","ng-galien","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F33391039?v=4","01M72357R83J706W38J2KE7CC7","Alexandre Boyer","01M72357RWTW344FDDX84H23P3",3,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fng-galien\u002Fcode-moniker\u002Fblob\u002Fmain\u002Fagents\u002Fskills\u002Fcode-moniker-smell-review\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: code-moniker-smell-review\ndescription: Review a repository with code-moniker's local and workspace check DSL for Fowler and Lanza-Marinescu code smells. Use when Codex needs to write, validate, or run project-specific warning-severity smell rules, distinguish executable local or indexed DSL checks from AST\u002Fhistory checks, triage check output, or plan follow-up evolutions for missing smell-detection operators.\n---\n\n# Code Moniker Smell Review\n\n## Operating Mode\n\nUse the check DSL first. Treat smell rules as heuristics, not hard\narchitecture gates, unless the user explicitly asks to enforce them.\n\nDefault every smell rule to `severity = \"warn\"`. Warning rules should\nsurface review candidates without making `code-moniker check` exit with a\nfailure by themselves.\n\nFor code-moniker itself, prefer these repo-local files:\n\n- `docs\u002Fcli\u002Fcode-smell-review.md` for the documented model and boundaries.\n- `.code-moniker.toml` for project-specific smell warnings and profiles.\n- `docs\u002Fcli\u002Fcheck-dsl.md` for exact grammar and projection semantics.\n\n## Workflow\n\n1. Inspect the target repository's language mix and existing rule overlay:\n   `code-moniker rules show . --report` when available, otherwise inspect\n   `.code-moniker.toml` and `code-moniker.fragment.toml` files.\n2. Before reviewing the local delta, inventory every mechanism it introduces\n   or changes: state machine, timeout, retry loop, cache, parser, classifier,\n   launcher, and policy. Use symbolic search\u002Fusages across the full repository,\n   name the canonical owner and consumers, and flag a parallel owner even when\n   its implementation is not a textual clone.\n3. Select checks the DSL can execute: direct child defs,\n   `out_refs`, `in_refs`, local metrics, collection algebra, entropy,\n   mode, percentile, `cv`, and `gini`; or `workspace.group` member-line\n   distributions over the current full index.\n4. Keep out-of-scope smells out of the CLI ruleset: change-history smells,\n   clone detection, transitive message chains, reaching-defs, z-scores,\n   and arbitrary corpus projections still belong to later DSL, SQL\u002FPG, or\n   extractor work.\n5. Validate rules before running a broad review:\n   `code-moniker rules show . --profile smells`.\n6. Run the review as warnings:\n   `code-moniker check \u003Crepo-root> --profile smells --report --max-violations 50`.\n7. Triage output by smell family. Report findings as review candidates with\n   file\u002Fline evidence, not as proof of incorrectness.\n8. Report a separate `Mechanism reuse \u002F duplication` verdict with the\n   repository-wide evidence. A clean DSL result is not evidence that semantic\n   duplication is absent.\n9. For a rule that would be useful but cannot be expressed, create an\n   `evolutions\u002F` note instead of forcing an invalid or misleading TOML rule.\n\n## Rule Guidance\n\nUse shape scopes for broad polyglot checks:\n\n```toml\n[[shape.callable.where]]\nid       = \"smell-long-callable\"\nseverity = \"warn\"\nexpr     = \"lines \u003C= 240\"\n```\n\nTreat this as an emergency bound, not a refactoring target. Do not extract a\nhelper from size alone; require a concrete ownership, coupling, or control-flow\nseam. Lower thresholds encourage artificial indirection, especially in\nagent-written code.\n\nUse type scopes for local OO distribution checks:\n\n```toml\n[[shape.type.where]]\nid       = \"smell-harmonious-method-size\"\nseverity = \"warn\"\nexpr     = \"count(shape:callable) >= 5 => cv(shape:callable, lines) \u003C= 0.6\"\n```\n\nUse implication guards to avoid flagging tiny symbols:\n\n```toml\n[[shape.callable.where]]\nid       = \"smell-feature-envy-local\"\nseverity = \"warn\"\nexpr     = \"count(out_refs) >= 5 => mode(out_refs, target.parent) = source.parent\"\n```\n\nUse `workspace.group` for cross-file line-distribution candidates already\navailable in the hot inventory:\n\n```toml\n[[workspace.group.where]]\nid        = \"smell-package-size-disharmony\"\nseverity  = \"warn\"\nmembers   = \"shape = 'type'\"\ngroup_by  = [\"lang\", \"segment('package')\"]\nexpr      = \"count(member) >= 8 => gini(member, lines) \u003C= 0.65\"\nmessage   = \"Uneven type sizes in {group}: {observations}\"\n```\n\nKeep the sample-size guard. `lines` is the inclusive extracted symbol span.\nThe group evaluator requires a valid line range for every selected member and\nreports coverage instead of folding a biased subset. Boolean order does not\nchange the verdict: a decisive known `AND`\u002F`OR` operand wins, otherwise the\nunavailable statistic remains fail-closed.\n\nUse segment regexes to keep path-pattern rules compact and structural:\n\n```toml\n[aliases]\nadapter_layer = \"target ~ '**\u002F*:\u002F^(adapter|infrastructure)$\u002F**'\"\n```\n\nPrefer `*:\u002Fregex\u002F` when a rule repeats the same `source ~`, `target ~`,\n`uri ~`, or `moniker ~` path with only the segment name changing. Do not\nreplace semantically different alternatives with a regex just to shorten a\nrule.\n\nDo not write rules that rely on unsupported arithmetic, AST control-flow\nshape, arbitrary corpus projections, or history. Capture those as evolutions.\n\n## Reference\n\nRead `references\u002Flocal-smell-coverage.md` when deciding whether a smell is\ncovered by the local DSL or needs a follow-up evolution.\n","# Code Moniker Smell Review\n\n## Operating Mode\n\nUse the check DSL first. Treat smell rules as heuristics, not hard\narchitecture gates, unless the user explicitly asks to enforce them.\n\nDefault every smell rule to `severity = \"warn\"`. Warning rules should\nsurface review candidates without making `code-moniker check` exit with a\nfailure by themselves.\n\nFor code-moniker itself, prefer these repo-local files:\n\n- `docs\u002Fcli\u002Fcode-smell-review.md` for the documented model and boundaries.\n- `.code-moniker.toml` for project-specific smell warnings and profiles.\n- `docs\u002Fcli\u002Fcheck-dsl.md` for exact grammar and projection semantics.\n\n## Workflow\n\n1. Inspect the target repository's language mix and existing rule overlay:\n   `code-moniker rules show . --report` when available, otherwise inspect\n   `.code-moniker.toml` and `code-moniker.fragment.toml` files.\n2. Before reviewing the local delta, inventory every mechanism it introduces\n   or changes: state machine, timeout, retry loop, cache, parser, classifier,\n   launcher, and policy. Use symbolic search\u002Fusages across the full repository,\n   name the canonical owner and consumers, and flag a parallel owner even when\n   its implementation is not a textual clone.\n3. Select checks the DSL can execute: direct child defs,\n   `out_refs`, `in_refs`, local metrics, collection algebra, entropy,\n   mode, percentile, `cv`, and `gini`; or `workspace.group` member-line\n   distributions over the current full index.\n4. Keep out-of-scope smells out of the CLI ruleset: change-history smells,\n   clone detection, transitive message chains, reaching-defs, z-scores,\n   and arbitrary corpus projections still belong to later DSL, SQL\u002FPG, or\n   extractor work.\n5. Validate rules before running a broad review:\n   `code-moniker rules show . --profile smells`.\n6. Run the review as warnings:\n   `code-moniker check \u003Crepo-root> --profile smells --report --max-violations 50`.\n7. Triage output by smell family. Report findings as review candidates with\n   file\u002Fline evidence, not as proof of incorrectness.\n8. Report a separate `Mechanism reuse \u002F duplication` verdict with the\n   repository-wide evidence. A clean DSL result is not evidence that semantic\n   duplication is absent.\n9. For a rule that would be useful but cannot be expressed, create an\n   `evolutions\u002F` note instead of forcing an invalid or misleading TOML rule.\n\n## Rule Guidance\n\nUse shape scopes for broad polyglot checks:\n\n```toml\n[[shape.callable.where]]\nid       = \"smell-long-callable\"\nseverity = \"warn\"\nexpr     = \"lines \u003C= 240\"\n```\n\nTreat this as an emergency bound, not a refactoring target. Do not extract a\nhelper from size alone; require a concrete ownership, coupling, or control-flow\nseam. Lower thresholds encourage artificial indirection, especially in\nagent-written code.\n\nUse type scopes for local OO distribution checks:\n\n```toml\n[[shape.type.where]]\nid       = \"smell-harmonious-method-size\"\nseverity = \"warn\"\nexpr     = \"count(shape:callable) >= 5 => cv(shape:callable, lines) \u003C= 0.6\"\n```\n\nUse implication guards to avoid flagging tiny symbols:\n\n```toml\n[[shape.callable.where]]\nid       = \"smell-feature-envy-local\"\nseverity = \"warn\"\nexpr     = \"count(out_refs) >= 5 => mode(out_refs, target.parent) = source.parent\"\n```\n\nUse `workspace.group` for cross-file line-distribution candidates already\navailable in the hot inventory:\n\n```toml\n[[workspace.group.where]]\nid        = \"smell-package-size-disharmony\"\nseverity  = \"warn\"\nmembers   = \"shape = 'type'\"\ngroup_by  = [\"lang\", \"segment('package')\"]\nexpr      = \"count(member) >= 8 => gini(member, lines) \u003C= 0.65\"\nmessage   = \"Uneven type sizes in {group}: {observations}\"\n```\n\nKeep the sample-size guard. `lines` is the inclusive extracted symbol span.\nThe group evaluator requires a valid line range for every selected member and\nreports coverage instead of folding a biased subset. Boolean order does not\nchange the verdict: a decisive known `AND`\u002F`OR` operand wins, otherwise the\nunavailable statistic remains fail-closed.\n\nUse segment regexes to keep path-pattern rules compact and structural:\n\n```toml\n[aliases]\nadapter_layer = \"target ~ '**\u002F*:\u002F^(adapter|infrastructure)$\u002F**'\"\n```\n\nPrefer `*:\u002Fregex\u002F` when a rule repeats the same `source ~`, `target ~`,\n`uri ~`, or `moniker ~` path with only the segment name changing. Do not\nreplace semantically different alternatives with a regex just to shorten a\nrule.\n\nDo not write rules that rely on unsupported arithmetic, AST control-flow\nshape, arbitrary corpus projections, or history. Capture those as evolutions.\n\n## Reference\n\nRead `references\u002Flocal-smell-coverage.md` when deciding whether a smell is\ncovered by the local DSL or needs a follow-up evolution.\n",{"name":5,"description":7},"main","1232663b7cefb0b354430bcbb60fc29896bc4f64","agents\u002Fskills\u002Fcode-moniker-smell-review",0,"https:\u002F\u002Fgithub.com\u002Fng-galien\u002Fcode-moniker","https:\u002F\u002Fgithub.com\u002Fng-galien","2026-09-26 01:24:27",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add ng-galien\u002Fcode-moniker --skill code-moniker-smell-review",{"tool":37,"command":38},"bunx","bunx skills add ng-galien\u002Fcode-moniker --skill code-moniker-smell-review",{"tool":40,"command":41},"pnpm","pnpm dlx skills add ng-galien\u002Fcode-moniker --skill code-moniker-smell-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fng-galien\u002Fcode-moniker\u002Fblob\u002Fmain\u002Fagents\u002Fskills\u002Fcode-moniker-smell-review\u002FSKILL.md",true,[45,51,55],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",260,"https:\u002F\u002Fgithub.com\u002Fng-galien\u002Fcode-moniker\u002Fblob\u002Fmain\u002Fagents\u002Fskills\u002Fcode-moniker-smell-review\u002Fagents\u002Fopenai.yaml",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Flocal-smell-coverage.md",3644,"https:\u002F\u002Fgithub.com\u002Fng-galien\u002Fcode-moniker\u002Fblob\u002Fmain\u002Fagents\u002Fskills\u002Fcode-moniker-smell-review\u002Freferences\u002Flocal-smell-coverage.md",{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"scripts\u002Frun-smell-review.sh","SCRIPT","脚本",791,"https:\u002F\u002Fgithub.com\u002Fng-galien\u002Fcode-moniker\u002Fblob\u002Fmain\u002Fagents\u002Fskills\u002Fcode-moniker-smell-review\u002Fscripts\u002Frun-smell-review.sh",[62,68],{"skillNo":63,"name":64,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7235S1QTZCADFX6NSGA8C7G","code-moniker","https:\u002F\u002Fgithub.com\u002Fng-galien\u002Fcode-moniker\u002Fblob\u002Fmain\u002Fcrates\u002Fcli\u002Fassets\u002Fagent\u002Fcode-moniker\u002FSKILL.md",[],[],{"skillNo":69,"name":64,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7235P9DEG2RMGHVF6JSE2AD","Use Code Moniker to onboard into an unfamiliar project, develop with indexed structural evidence, guard executable architectural memory after a change, or review relationships and change impact. Use it when callers, callees, coupling, ownership, project rules, or workspace-wide structure matter. Do not invoke it for routine Git, tests, exact-string lookup, or small known-file edits whose contract is already visible.","https:\u002F\u002Fgithub.com\u002Fng-galien\u002Fcode-moniker\u002Fblob\u002Fmain\u002Fagents\u002Fskills\u002Fcode-moniker\u002FSKILL.md",[],[]]