[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MERBPSVB7Q6DPRKM1ZBYAX":3,"skill-same:01M6MERBPSVB7Q6DPRKM1ZBYAX":96},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":67,"commitSha":68,"skillDirectory":69,"forksCount":70,"repositoryHtmlUrl":71,"repositoryHomepageUrl":72,"ownerHtmlUrl":73,"ownerBlogUrl":74,"ownerDescription":75,"updatedAt":76,"install":77,"resources":89},"01M6MERBPSVB7Q6DPRKM1ZBYAX","refactor",null,"Restructure or clean up code with no behavior change, proved by before-and-after checks. Use when: asked to clean up, extract, dedupe or simplify, even one function.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1554,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Frefactor\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"canonical","when","Legacy","use","execution","true","repo","evidence","context","patterns","source","refactoring","change","code","simplify","files","design","clean","up","regression","2026-11-10 10:12:30",false,"---\nname: refactor\ndescription: 'Restructure or clean up code with no behavior change, proved by before-and-after checks. Use when: asked to clean up, extract, dedupe or simplify, even one function.'\npractices:\n- refactoring\n- legacy-code-seams\n- design-patterns\nhexagonal_role: supporting\nconsumes:\n- repo-context\nproduces:\n- code-changes\ncontext_rel: []\nskill_api_version: 1\nuser-invocable: true\nmetadata:\n  capabilities: [refactor]\n  effects: [modify_source_files]\n  canonical_status: canonical\n  disposition: keep_specialist\n  tier: execution\n  dependencies: []\noutput_contract: code changes with regression evidence\n---\n# Refactor — one structural experiment\n\nRefactor changes structure while preserving observable behavior. It performs one\ncaller-selected transformation and reports the result. \"Behavior-preserving\" is\na claim to prove with before\u002Fafter checks, never to assert. A user sees it\nworked when the report shows the same checks run before and after with\nidentical results, and any suspected bug listed unfixed.\n\n## What counts as behavior\n\nUnless the caller explicitly excluded a surface, all of these must survive:\n\n- **Messages and exit codes.** Error and output text compares byte-for-byte;\n  exit codes, error types and which input raises which error stay the same.\n  Scripts and callers parse them. Preserve an inconsistent message and report\n  it; normalizing it is a behavior change.\n- **Differences between near-duplicates.** When merging duplicated branches,\n  carry every difference (constants, comparisons, messages, extra steps) as a\n  parameter or a branch. Do not unify a difference the caller has not declared\n  accidental.\n- **Interfaces.** Public signatures, defaults, return types, persisted field\n  names, protocol values and CLI flags. Renaming one is a compatibility change\n  unless the accepted scope provides for it.\n- **Order and coverage.** Branch priority, default handling, evaluation count,\n  side-effect order, and the set of tests that run. A pre-existing red that\n  vanishes, or a test that stops running, is a behavior change.\n- **Protective checks.** Trust-boundary validation, data-loss guards, security\n  controls and accessibility affordances stay, even when another layer,\n  upstream or downstream, duplicates one or no test reaches it. The neutrality\n  gates cannot see their removal, so looking redundant is no reason to delete\n  one.\n\n## Procedure\n\n1. Name the preserved behavior, the focused acceptance surface and the concrete\n   structural problem for its callers, in the caller's domain terms.\n2. Run the focused check and the smallest regression check the changed surface\n   justifies, error paths included, and record that honest baseline, including\n   reproducible ambient failures. Add any characterization test the\n   transformation needs now, before the edit, so it is part of the baseline.\n   For output-producing surfaces (generators, serializers, formatters,\n   reports), hash the output over fixed inputs. When the caller's evaluation\n   compares the built program before and after the change, pin the starting\n   source, build its baseline before edits and keep that binary and the\n   comparison inputs.\n3. Apply one bounded transformation: extract, move, rename, inline, simplify a\n   conditional, reduce parameters, encapsulate, substitute existing code, or\n   delete dead code; the\n   [refactoring catalog](references\u002Fbehavior-preserving-simplification.md#refactoring-catalog)\n   holds per-pattern safety checks. Judge it by what callers must\n   understand and where a domain rule must change, not by file size.\n4. A bug or suspicious inconsistency found on the way is reported separately\n   (location, why it looks wrong) and left unfixed. Fixing it inside the\n   refactor hides a behavior change the caller did not authorize.\n5. Rerun exactly the step-2 checks over the same inputs and compare any\n   output hashes byte-for-byte.\n6. Report, then stop. A red result is evidence for the caller; this skill does\n   not revert, narrow, retry, commit, validate, or route subsequent work.\n\nWhen nothing can be executed (no runtime, no tests, code supplied in a\nmessage), neutrality is unproven: give the exact before\u002Fafter commands and\ninputs the caller must run, error paths included, and list every surface under\n`not checked`.\n\n```text\ntransformation: \u003Cthe one change>\npreserved:      \u003Cbehavior and surfaces from step 1>\nchecks:         \u003Ccommand>: before -> \u003Cresult>; after -> \u003Cresult>   (or \"not run\")\noutputs:        \u003Cbefore\u002Fafter hashes when the surface produces output>\nabstraction:    \u003Ca new one and the second use or contract that justifies it, or \"none\">\ndiff:           \u003Cfiles touched>; only those the transformation names, plus tests added before the change\nsuspected bugs: \u003Cfile:line, why>; reported, not fixed\nnot checked:    \u003Csurfaces no check covered>; present even when empty\n```\n\n## Neutrality gates\n\nThe checks from step 2 give the same result after as before: no new red, no\nvanished red, identical output hashes. A mismatch is a behavior diff to surface\nand explain, never to shrug at; the caller decides whether to keep, narrow, or\nreverse it. A gate skipped or narrowed after the fact is the **post-hoc\nneutrality** failure mode — the diff decides what got tested. Name any surface\nthe gates did not cover under `not checked`.\n\n## Boundaries and tests\n\nRefactoring after a check goes green is the step of test-driven development\nthat held for agents\n([practice ledger](https:\u002F\u002Fgithub.com\u002Fboshu2\u002Fagentops\u002Fblob\u002Fmain\u002Fdocs\u002Fpractice-ledger.md#holds-in-a-different-shape)).\n\n- Use [Implement](..\u002Fimplement\u002FSKILL.md) to change behavior; it tidies its own\n  fresh change under its acceptance checks.\n- Use Refactor when restructuring is the request, or reaches code the behavior\n  change did not touch; that green result is the baseline.\n- Use [Architecture](..\u002Farchitecture\u002FSKILL.md#procedure) to choose where to\n  restructure or a new module boundary; this skill executes one transformation\n  in the area the caller selected.\n\nReject a wrapper that only adds another name or pushes the same coordination into its callers. Keep\ninternal test seams private when callers need no substitution. Exercise the\npreserved behavior through the caller-facing boundary; retain existing tests\nuntil equivalent coverage of their distinct cases is demonstrated. Moving a\ntest is not permission to delete the behavior it protected.\n\nUse the caller's vocabulary for extracted operations and types. A naming\nambiguity that changes behavior belongs with the existing domain definition;\nconsult [Domain](..\u002Fdomain\u002FSKILL.md) only when that distinction needs work.\n\nWhen the caller-chosen transformation can be cut more than one way (which\nlines an extraction takes, where a chosen interface sits), probe before you\ncut. A choice between module boundaries the caller has not made goes to\nArchitecture first.\nRun the probe in disposable isolation (a scratch branch, worktree, or copied\ntree the caller's policy allows): rough in the seam, see what it forces —\nsignature churn, import cycles, test rewrites — then discard the probe and\nkeep only the knowledge. Stop condition: at most two probes; if the second\ncandidate seam also fights back, report both findings to the caller instead of\ntrying a third. Cutting the first imaginable seam directly into the working\ntree is the **premature seam** failure mode: the wrong boundary calcifies\nbecause reverting it now costs more than living with it.\n\n## References\n\n- [Behavior-preserving simplification](references\u002Fbehavior-preserving-simplification.md) — refactoring catalog and per-pattern safety checks\n- [Codebase design](https:\u002F\u002Fgithub.com\u002Fmattpocock\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fcodebase-design\u002FSKILL.md) — Matt Pocock; the wrapper and test-seam rules under Boundaries and tests adapt it.\n","# Refactor — one structural experiment\n\nRefactor changes structure while preserving observable behavior. It performs one\ncaller-selected transformation and reports the result. \"Behavior-preserving\" is\na claim to prove with before\u002Fafter checks, never to assert. A user sees it\nworked when the report shows the same checks run before and after with\nidentical results, and any suspected bug listed unfixed.\n\n## What counts as behavior\n\nUnless the caller explicitly excluded a surface, all of these must survive:\n\n- **Messages and exit codes.** Error and output text compares byte-for-byte;\n  exit codes, error types and which input raises which error stay the same.\n  Scripts and callers parse them. Preserve an inconsistent message and report\n  it; normalizing it is a behavior change.\n- **Differences between near-duplicates.** When merging duplicated branches,\n  carry every difference (constants, comparisons, messages, extra steps) as a\n  parameter or a branch. Do not unify a difference the caller has not declared\n  accidental.\n- **Interfaces.** Public signatures, defaults, return types, persisted field\n  names, protocol values and CLI flags. Renaming one is a compatibility change\n  unless the accepted scope provides for it.\n- **Order and coverage.** Branch priority, default handling, evaluation count,\n  side-effect order, and the set of tests that run. A pre-existing red that\n  vanishes, or a test that stops running, is a behavior change.\n- **Protective checks.** Trust-boundary validation, data-loss guards, security\n  controls and accessibility affordances stay, even when another layer,\n  upstream or downstream, duplicates one or no test reaches it. The neutrality\n  gates cannot see their removal, so looking redundant is no reason to delete\n  one.\n\n## Procedure\n\n1. Name the preserved behavior, the focused acceptance surface and the concrete\n   structural problem for its callers, in the caller's domain terms.\n2. Run the focused check and the smallest regression check the changed surface\n   justifies, error paths included, and record that honest baseline, including\n   reproducible ambient failures. Add any characterization test the\n   transformation needs now, before the edit, so it is part of the baseline.\n   For output-producing surfaces (generators, serializers, formatters,\n   reports), hash the output over fixed inputs. When the caller's evaluation\n   compares the built program before and after the change, pin the starting\n   source, build its baseline before edits and keep that binary and the\n   comparison inputs.\n3. Apply one bounded transformation: extract, move, rename, inline, simplify a\n   conditional, reduce parameters, encapsulate, substitute existing code, or\n   delete dead code; the\n   [refactoring catalog](references\u002Fbehavior-preserving-simplification.md#refactoring-catalog)\n   holds per-pattern safety checks. Judge it by what callers must\n   understand and where a domain rule must change, not by file size.\n4. A bug or suspicious inconsistency found on the way is reported separately\n   (location, why it looks wrong) and left unfixed. Fixing it inside the\n   refactor hides a behavior change the caller did not authorize.\n5. Rerun exactly the step-2 checks over the same inputs and compare any\n   output hashes byte-for-byte.\n6. Report, then stop. A red result is evidence for the caller; this skill does\n   not revert, narrow, retry, commit, validate, or route subsequent work.\n\nWhen nothing can be executed (no runtime, no tests, code supplied in a\nmessage), neutrality is unproven: give the exact before\u002Fafter commands and\ninputs the caller must run, error paths included, and list every surface under\n`not checked`.\n\n```text\ntransformation: \u003Cthe one change>\npreserved:      \u003Cbehavior and surfaces from step 1>\nchecks:         \u003Ccommand>: before -> \u003Cresult>; after -> \u003Cresult>   (or \"not run\")\noutputs:        \u003Cbefore\u002Fafter hashes when the surface produces output>\nabstraction:    \u003Ca new one and the second use or contract that justifies it, or \"none\">\ndiff:           \u003Cfiles touched>; only those the transformation names, plus tests added before the change\nsuspected bugs: \u003Cfile:line, why>; reported, not fixed\nnot checked:    \u003Csurfaces no check covered>; present even when empty\n```\n\n## Neutrality gates\n\nThe checks from step 2 give the same result after as before: no new red, no\nvanished red, identical output hashes. A mismatch is a behavior diff to surface\nand explain, never to shrug at; the caller decides whether to keep, narrow, or\nreverse it. A gate skipped or narrowed after the fact is the **post-hoc\nneutrality** failure mode — the diff decides what got tested. Name any surface\nthe gates did not cover under `not checked`.\n\n## Boundaries and tests\n\nRefactoring after a check goes green is the step of test-driven development\nthat held for agents\n([practice ledger](https:\u002F\u002Fgithub.com\u002Fboshu2\u002Fagentops\u002Fblob\u002Fmain\u002Fdocs\u002Fpractice-ledger.md#holds-in-a-different-shape)).\n\n- Use [Implement](..\u002Fimplement\u002FSKILL.md) to change behavior; it tidies its own\n  fresh change under its acceptance checks.\n- Use Refactor when restructuring is the request, or reaches code the behavior\n  change did not touch; that green result is the baseline.\n- Use [Architecture](..\u002Farchitecture\u002FSKILL.md#procedure) to choose where to\n  restructure or a new module boundary; this skill executes one transformation\n  in the area the caller selected.\n\nReject a wrapper that only adds another name or pushes the same coordination into its callers. Keep\ninternal test seams private when callers need no substitution. Exercise the\npreserved behavior through the caller-facing boundary; retain existing tests\nuntil equivalent coverage of their distinct cases is demonstrated. Moving a\ntest is not permission to delete the behavior it protected.\n\nUse the caller's vocabulary for extracted operations and types. A naming\nambiguity that changes behavior belongs with the existing domain definition;\nconsult [Domain](..\u002Fdomain\u002FSKILL.md) only when that distinction needs work.\n\nWhen the caller-chosen transformation can be cut more than one way (which\nlines an extraction takes, where a chosen interface sits), probe before you\ncut. A choice between module boundaries the caller has not made goes to\nArchitecture first.\nRun the probe in disposable isolation (a scratch branch, worktree, or copied\ntree the caller's policy allows): rough in the seam, see what it forces —\nsignature churn, import cycles, test rewrites — then discard the probe and\nkeep only the knowledge. Stop condition: at most two probes; if the second\ncandidate seam also fights back, report both findings to the caller instead of\ntrying a third. Cutting the first imaginable seam directly into the working\ntree is the **premature seam** failure mode: the wrong boundary calcifies\nbecause reverting it now costs more than living with it.\n\n## References\n\n- [Behavior-preserving simplification](references\u002Fbehavior-preserving-simplification.md) — refactoring catalog and per-pattern safety checks\n- [Codebase design](https:\u002F\u002Fgithub.com\u002Fmattpocock\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fcodebase-design\u002FSKILL.md) — Matt Pocock; the wrapper and test-seam rules under Boundaries and tests adapt it.\n",{"name":5,"consumes":49,"metadata":51,"produces":57,"practices":59,"context_rel":62,"description":7,"hexagonal_role":63,"user-invocable":64,"output_contract":65,"skill_api_version":66},[50],"repo-context",{"tier":28,"effects":52,"disposition":54,"capabilities":55,"dependencies":56,"canonical_status":24},[53],"modify_source_files","keep_specialist",[5],[],[58],"code-changes",[35,60,61],"legacy-code-seams","design-patterns",[],"supporting",true,"code changes with regression evidence",1,"main","347aedf8480cd92b21f761e97b7343a45898f5fa","plugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Frefactor",468,"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.","2026-11-11 02:22:54",{"source":8,"skillName":5,"commands":78,"prompt":88,"zipAvailable":64},[79,82,85],{"tool":80,"command":81},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill refactor",{"tool":83,"command":84},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill refactor",{"tool":86,"command":87},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill refactor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Frefactor\u002FSKILL.md",[90],{"path":91,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fbehavior-preserving-simplification.md","REFERENCE","参考文档",6214,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Frefactor\u002Freferences\u002Fbehavior-preserving-simplification.md",[97,121,146,178,198,212],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":44},"01M716A6ETNB9B1SQ3GXZC75VR","deja-search","deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-search\u002FSKILL.md",[],[104,105,106,107,108,109,110,111,112,40,113,25,114,115,116,117,36,118,119,120],"search","deja search","error","ready","never","memory","re","decide","fix","debugging","you","done","reviewer","io","cli","merge","past",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":44},"01M716A3J2W5SENSE9VGMXB375","deja-reflect","End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-reflect\u002FSKILL.md",[],[128,129,130,131,109,132,133,134,135,136,137,138,139,117,140,141,142,143,144,145],"reflect","deja reflect","brew","remember","project rules","project","session","end","reflection","Rules","decisions","review","with","record","github","next","https","node",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":161,"publishedAt":44},"01M715T3RR4BAYSR57HPPTJ0PF","revid","Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftmakersas\u002Frevid-skills\u002Fskills\u002Frevid\u002FSKILL.md",[152,155,158],{"categoryNo":153,"categoryName":154,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":156,"categoryName":157,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":159,"categoryName":160,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[148,162,163,164,165,166,133,167,110,168,169,170,171,25,172,173,174,175,176,177],"Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","URL","image","mcp server","schedule","api","publish",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":44},"01M71569ZM2X3H5RBFK8PVKMK2","review-study","Review a QuestionPunk survey before launch for wording, answer choices, branching, and missing settings. Use for check my survey or review this draft before publishing.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fquestionpunk\u002Fcodex-plugin\u002Fskills\u002Freview-study\u002FSKILL.md",[],[185,186,139,187,188,189,190,191,27,192,193,194,195,196,197],"study","review study","for","answer","missing","survey","publishing","check","draft","settings","launch","my","branching",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":204,"publishedAt":44},"01M71567GV0C35YQBY0DPGR86B","manage-study","Find QuestionPunk studies, check status, publish an explicitly requested draft, or retrieve its participant link. Use for find my survey, publish this study, or how many people responded.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fquestionpunk\u002Fcodex-plugin\u002Fskills\u002Fmanage-study\u002FSKILL.md",[],[205,185,206,187,190,27,207,192,193,177,208,209,210,211,196],"manage study","manage","people","how","find","link","status",{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":216,"categories":217,"keywords":218,"publishedAt":44},"01M71565A8TCA01AZQZRGRYMFZ","create-study","Create a saved QuestionPunk survey draft from a research brief or edit specified questions. Use for requests such as make a customer feedback survey or shorten my onboarding study.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fquestionpunk\u002Fcodex-plugin\u002Fskills\u002Fcreate-study\u002FSKILL.md",[],[219,185,220,221,222,223,187,224,190,225,27,226,227,193,228,229,230,231,232,196],"create study","create","brief","as","feedback","customer feedback","research brief","shorten","saved","research","requests","customer","questions","edit"]