[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BVHNXH1JQJDSH5QPCN3ZP3":3,"skill-same:01M7BVHNXH1JQJDSH5QPCN3ZP3":45},{"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7BVHNXH1JQJDSH5QPCN3ZP3","python-fact-grounded-coding",null,"Use when the user explicitly asks for the Python fact-grounded coding skill, or when a Python coding, debugging, explanation, or bug-fix task should be grounded in verified Pylance facts, runtime values, diagnostics, selected interpreter state, tests, or debugger evidence before changing code or reporting a conclusion.","nguyenhungtran18\u002Fskill-and-tool-tracker","nguyenhungtran18","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F297063550?v=4","01M7BV0BFPRRFP84F2ME0FYZ9D","01M7BV0BG83FA5P22NJV0GR0A5",1,"MIT","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fpython-fact-grounded-coding\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: python-fact-grounded-coding\ndescription: 'Use when the user explicitly asks for the Python fact-grounded coding skill, or when a Python coding, debugging, explanation, or bug-fix task should be grounded in verified Pylance facts, runtime values, diagnostics, selected interpreter state, tests, or debugger evidence before changing code or reporting a conclusion.'\n---\n\n# Python Fact-Grounded Coding\n\nTreat reasoning as a source of hypotheses, not proof. Before explaining behavior or changing code, collect enough observable facts to support the answer.\n\n## Pylance Tool Routing\n\nWhen Pylance MCP tools are available, use them for facts that generic file reading cannot reliably prove.\n\n-   Use `pylanceLSP` for diagnostics, hover\u002Ftype facts, definitions, references, signatures, call hierarchy, document symbols, and workspace symbols.\n-   Use `pylanceSemanticContext` when a cursor position needs related imports, base classes, overrides, usages, call sites, or dependency context.\n-   Use `pylanceCheckSignatureCompatibility` before or after changing a function signature to verify existing callers.\n-   Use `pylanceImports` plus `pylanceInstalledTopLevelModules` for dependency and unresolved-import questions; do not infer the editor environment from terminal `python`.\n-   Use `pylanceDocuments`, `pylanceSettings`, `pylancePythonEnvironments`, or `pylanceWorkspaceRoots` for Pylance behavior, configuration, workspace, or selected-interpreter claims when those tools are available.\n-   Use `pylanceRunCodeSnippet` for a focused runtime value, return value, parser result, or small input\u002Foutput check.\n-   Use `pylancePythonDebug` when the answer depends on a branch, exception, loop iteration, closure, subprocess, mutable state, or frame-local value.\n-   Use `pylanceSyntaxErrors` or `pylanceFileSyntaxErrors` to validate generated Python syntax before treating code as ready.\n\n## Evidence Ladder\n\nUse the lightest reliable evidence that settles the question. Escalate when the current evidence leaves uncertainty.\n\n1. **Language facts**: Use Pylance code intelligence for symbol meaning, types, diagnostics, references, signatures, base classes, overrides, and call sites.\n2. **Product and workspace facts**: Use Pylance docs, settings, workspace, import, and environment tools for claims about Pylance behavior or editor-selected Python state.\n3. **Execution facts**: Use a focused snippet or test when the answer depends on runtime values, return values, parsing behavior, or a concrete input\u002Foutput case.\n4. **Debugger facts**: Use the debugger when the issue depends on a branch, exception, loop iteration, closure, subprocess, mutable state, or frame-local value.\n\n## Example Workflows\n\n-   **Explain or fix a diagnostic**: call `pylanceLSP` for `textDocument\u002Fdiagnostic` or `workspace\u002Fdiagnostic`, keep the exact diagnostic code\u002Fmessage in mind, then inspect only the code needed to explain or fix that rule.\n-   **Change Python API behavior**: use `pylanceLSP` references or `pylanceCheckSignatureCompatibility` to find real call sites, patch the producer, then run the focused test or snippet that proves the changed behavior.\n-   **Debug dynamic runtime behavior**: inspect the relevant test and source, run a focused snippet or test, and escalate to `pylancePythonDebug` if the important value is produced inside a branch, loop, callback, or mutable context.\n-   **Audit imports or requirements**: compare `pylanceImports` with `pylanceInstalledTopLevelModules`; use diagnostics only when locations, severities, or report codes matter.\n\n## Working Rules\n\n-   Name assumptions explicitly as hypotheses until verified.\n-   Verify the exact symbol, type, diagnostic code, call path, or runtime value that the task depends on.\n-   For bug fixes, prefer a repro test, failing command, snippet, or debug session before patching behavior.\n-   Fix the producer of the wrong behavior after the facts identify it; avoid patching a downstream symptom because it looks plausible.\n-   After changing code, run the focused validation that would have caught the original mistake.\n-   If a needed verification tool is unavailable, say what remains uncertain and keep the change narrow.\n\n## Common Traps\n\n-   Do not patch from a familiar bug pattern until observed values confirm this code is taking that path.\n-   Do not treat text search as proof of semantic relationships such as overrides, re-exports, aliases, or call compatibility.\n-   Do not infer the editor\u002FPylance interpreter from terminal `python` or PATH.\n-   Do not explain a diagnostic from wording alone when the exact Pylance rule code is available.\n-   Do not say a test, breakpoint, or tool would prove something; run it or label the result as unverified.\n\n## Minimal Good Answer Shape\n\nWhen reporting the result, include the facts that changed the decision: the diagnostic code, type, call site, runtime value, failing input, debugger frame, or test result. Keep speculation out of the conclusion.\n","# Python Fact-Grounded Coding\n\nTreat reasoning as a source of hypotheses, not proof. Before explaining behavior or changing code, collect enough observable facts to support the answer.\n\n## Pylance Tool Routing\n\nWhen Pylance MCP tools are available, use them for facts that generic file reading cannot reliably prove.\n\n-   Use `pylanceLSP` for diagnostics, hover\u002Ftype facts, definitions, references, signatures, call hierarchy, document symbols, and workspace symbols.\n-   Use `pylanceSemanticContext` when a cursor position needs related imports, base classes, overrides, usages, call sites, or dependency context.\n-   Use `pylanceCheckSignatureCompatibility` before or after changing a function signature to verify existing callers.\n-   Use `pylanceImports` plus `pylanceInstalledTopLevelModules` for dependency and unresolved-import questions; do not infer the editor environment from terminal `python`.\n-   Use `pylanceDocuments`, `pylanceSettings`, `pylancePythonEnvironments`, or `pylanceWorkspaceRoots` for Pylance behavior, configuration, workspace, or selected-interpreter claims when those tools are available.\n-   Use `pylanceRunCodeSnippet` for a focused runtime value, return value, parser result, or small input\u002Foutput check.\n-   Use `pylancePythonDebug` when the answer depends on a branch, exception, loop iteration, closure, subprocess, mutable state, or frame-local value.\n-   Use `pylanceSyntaxErrors` or `pylanceFileSyntaxErrors` to validate generated Python syntax before treating code as ready.\n\n## Evidence Ladder\n\nUse the lightest reliable evidence that settles the question. Escalate when the current evidence leaves uncertainty.\n\n1. **Language facts**: Use Pylance code intelligence for symbol meaning, types, diagnostics, references, signatures, base classes, overrides, and call sites.\n2. **Product and workspace facts**: Use Pylance docs, settings, workspace, import, and environment tools for claims about Pylance behavior or editor-selected Python state.\n3. **Execution facts**: Use a focused snippet or test when the answer depends on runtime values, return values, parsing behavior, or a concrete input\u002Foutput case.\n4. **Debugger facts**: Use the debugger when the issue depends on a branch, exception, loop iteration, closure, subprocess, mutable state, or frame-local value.\n\n## Example Workflows\n\n-   **Explain or fix a diagnostic**: call `pylanceLSP` for `textDocument\u002Fdiagnostic` or `workspace\u002Fdiagnostic`, keep the exact diagnostic code\u002Fmessage in mind, then inspect only the code needed to explain or fix that rule.\n-   **Change Python API behavior**: use `pylanceLSP` references or `pylanceCheckSignatureCompatibility` to find real call sites, patch the producer, then run the focused test or snippet that proves the changed behavior.\n-   **Debug dynamic runtime behavior**: inspect the relevant test and source, run a focused snippet or test, and escalate to `pylancePythonDebug` if the important value is produced inside a branch, loop, callback, or mutable context.\n-   **Audit imports or requirements**: compare `pylanceImports` with `pylanceInstalledTopLevelModules`; use diagnostics only when locations, severities, or report codes matter.\n\n## Working Rules\n\n-   Name assumptions explicitly as hypotheses until verified.\n-   Verify the exact symbol, type, diagnostic code, call path, or runtime value that the task depends on.\n-   For bug fixes, prefer a repro test, failing command, snippet, or debug session before patching behavior.\n-   Fix the producer of the wrong behavior after the facts identify it; avoid patching a downstream symptom because it looks plausible.\n-   After changing code, run the focused validation that would have caught the original mistake.\n-   If a needed verification tool is unavailable, say what remains uncertain and keep the change narrow.\n\n## Common Traps\n\n-   Do not patch from a familiar bug pattern until observed values confirm this code is taking that path.\n-   Do not treat text search as proof of semantic relationships such as overrides, re-exports, aliases, or call compatibility.\n-   Do not infer the editor\u002FPylance interpreter from terminal `python` or PATH.\n-   Do not explain a diagnostic from wording alone when the exact Pylance rule code is available.\n-   Do not say a test, breakpoint, or tool would prove something; run it or label the result as unverified.\n\n## Minimal Good Answer Shape\n\nWhen reporting the result, include the facts that changed the decision: the diagnostic code, type, call site, runtime value, failing input, debugger frame, or test result. Keep speculation out of the conclusion.\n",{"name":5,"description":7},"main","900ea3c9eb045fd5b0317dc1103777ecf3ea4aeb","skills\u002Fpython-fact-grounded-coding",0,"https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker","https:\u002F\u002Fnguyenhungtran18.github.io\u002Fskill-and-tool-tracker\u002F","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18","2026-08-31 18:36:09",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add nguyenhungtran18\u002Fskill-and-tool-tracker --skill python-fact-grounded-coding",{"tool":37,"command":38},"bunx","bunx skills add nguyenhungtran18\u002Fskill-and-tool-tracker --skill python-fact-grounded-coding",{"tool":40,"command":41},"pnpm","pnpm dlx skills add nguyenhungtran18\u002Fskill-and-tool-tracker --skill python-fact-grounded-coding","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fpython-fact-grounded-coding\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M7BVP4P83TK60JZ4P8RP9VP7","xcode-project-setup","Safely modifies Xcode projects (.pbxproj) to add Swift Packages and link files. Use this skill whenever an iOS project needs dependencies installed (e.g. Firebase, Alamofire).","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fxcode_project_setup\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M7BVP01K4CSJJ8G90FT8S2D5","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M7BVNY22GXD871GYTSH599F1","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"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},"01M7BVNQWF24RNKA8A4KM2HJ3T","workflow-skill-creator","Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say \"make this a skill\", \"create a skill from what we just did\", \"package this workflow\" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow_skill_creator\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},"01M7BVNNY67XPCQAQHY3FBKDGC","verify-and-stop","Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fverify-and-stop\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},"01M7BVNKB4Z7SZT85B73ZZ90Y6","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fnguyenhungtran18\u002Fskill-and-tool-tracker\u002Fblob\u002Fmain\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[]]