[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JGJ0T24P2G2K8J4FNH99PH":3,"skill-same:01M6JGJ0T24P2G2K8J4FNH99PH":73},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M6JGJ0T24P2G2K8J4FNH99PH","scope-guard",null,"Enforce user-defined task boundaries to prevent scope creep and over-implementation. Use after receiving a task with explicit constraints (\"only X\", \"don't do Y\", \"focus on Z\"), before starting each new sub-step during execution, or when tempted to add helpful work not explicitly requested.","muratovv\u002Fai-hats","muratovv","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F7502801?v=4","01M6JGCBN4KEJX012GPJVSH04T","Fedor Muratov","01M6JGCBSNMN7CW3RGTPPE0MN2",3,"MIT","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fcore\u002Fskills\u002Fscope-guard\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35],"scope guard","guard","scope","do","scope creep","with","add","focus","enforce","task","execution","implementation","only","use","user","work","constraints","2026-11-10 10:12:30",false,"---\nname: scope-guard\ndescription: >-\n  Enforce user-defined task boundaries to prevent scope creep and\n  over-implementation. Use after receiving a task with explicit\n  constraints (\"only X\", \"don't do Y\", \"focus on Z\"), before starting each\n  new sub-step during execution, or when tempted to add helpful work not\n  explicitly requested.\nlicense: MIT\n---\n\n# Scope Guard\n\nEnforce user-defined task boundaries. Prevent scope creep and over-implementation.\n\n## When to Use\n\nExecution-time guard against doing *more* than the user asked. Its sibling at\nplan stage is **design-minimalism**, which strips speculative primitives from a\nplan before any code exists; scope-guard instead holds the line on explicit user\nconstraints (\"only X\", \"don't touch Y\") *while* you execute. If you're weighing\nwhether an abstraction is justified, that's design-minimalism; if you're tempted\nto bolt on unrequested \"helpful\" work, that's this skill.\n\n## Checklist\n\n### Before Starting Execution\n\n1. **Extract constraints:** List every explicit limitation from the user's request\n   (e.g., \"signatures only\", \"no tests\", \"just the plan\")\n2. **Record constraints** in plan.md under a `## Scope Constraints` section\n3. **Define \"done\":** What is the minimum deliverable that satisfies the request?\n\n### Before Each Action\n\n4. **Scope check:** Is this action within the recorded constraints?\n   - YES → proceed\n   - NO → go to step 5\n5. **Escalate, don't decide:** If you believe a constraint should be violated\n   (e.g., minimal implementation needed to compile), ASK the user first.\n   Never silently expand scope.\n\n### Execution Checkpoints\n\n6. **Checkpoint rule:** After every **5 significant tool calls** (Edit, Write, Bash that changes state),\n   pause and deliver a brief status:\n   - What was done so far (1-2 lines)\n   - What's next (1-2 lines)\n   - Any deviations from plan\n7. **Large task threshold:** If executing 10+ tool calls in a single response,\n   STOP after 5 and checkpoint. Do not continue silently.\n8. **Plan revision: prefer Write over many Edits.** When revising a plan file\n   (`\u003Cai_hats_dir>\u002Ftracker\u002Fbacklog\u002Ftasks\u002F*\u002Fplan.md` — the one canonical plan\n   home): if more than 2 distinct sections of the\n   plan need to change, use a single `Write` to rewrite the whole file rather\n   than 3+ sequential `Edit` calls. Plan files are short enough that a full\n   rewrite costs the same as the diffs but avoids per-edit permission and\n   round-trip overhead for the supervisor.\n9. **\"discuss before implement\" gate:** On non-trivial tasks, present the approach\n   before executing. One paragraph, not a wall of text. Wait for confirmation.\n\n### After Completing Work\n\n6. **Scope audit:** Compare what you delivered against the original constraints.\n   Did you do more than asked? Flag it.\n\n## Completion\n\n- Constraints recorded in plan.md\n- Every action within recorded constraints, or user approved the deviation\n- No unrequested work delivered without explicit approval\n\n## Rationalization red-flags\n\nScope creep arrives as a thought you tell yourself *before* the action. Catch\nthe rationalization, not just the regret:\n\n| Rationalization (what you tell yourself)            | Why it's wrong                                                                                                         |\n| --------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- |\n| \"I'll just add this helper while I'm here\"          | Not requested — the user scopes, your convenience doesn't                                                              |\n| \"Skeleton\u002Finfra obviously means wire up everything\" | Defaults to *only what was named*; ask with a concrete enumeration (switched 4 handlers, user rolled back 3) |\n| \"It won't compile without this extra bit\"           | Maybe — but that is an escalation (\"ASK first\"), not a licence to expand silently                                      |\n| \"Faster to do it all now than to ask\"               | The ask round-trip is cheaper than the rollback                                                                        |\n\n**Red-flag words in your own reasoning:** \"while I'm here\", \"just also\", \"might\nas well\", \"obviously they'd want\", \"to be safe\". Any of these → re-run the scope\ncheck (step 4) and escalate (step 5) instead of proceeding.\n\n**Forbidden workaround:** expanding scope and \"flagging it\" in the final summary\nis *not* consent — flagging after the fact does not substitute for asking\nbefore the action. (Rationalization-table discipline adapted from\nobra\u002Fsuperpowers, MIT.)\n\n## Anti-Patterns\n\n- \"I'll just add this helper since I'm here\" — scope creep\n- Justifying scope expansion internally without asking — the user decides, not you\n- Writing full implementations when asked for signatures\u002Finterfaces\n- Writing tests when asked for design only\n- 30+ tool calls in a single response without a checkpoint — the user loses visibility\n- Skipping \"discuss approach\" on tasks with multiple implementation options\n- **\"Skeleton \u002F infrastructure \u002F framework\" signal misread.** When the user\n  says \"make a skeleton of X\" or \"set up the infrastructure for Y\" or\n  \"wire up the framework call for Z\" — interpret as **minimum viable demo +\n  ask before expanding**, NOT as \"wire up all related entry-points\". A\n  one-liner answer about scope without an explicit \"everything\" defaults to\n  \"only what was specifically named\". Worked example — user said\n  \"нужен скелет вызова ai-hats\", agent switched 4 CLI handlers via\n  pipeline-presets; user rolled back 3 of them. The correct ask is: \"only X,\n  X and Y, or all four?\" with a concrete enumeration.\n","# Scope Guard\n\nEnforce user-defined task boundaries. Prevent scope creep and over-implementation.\n\n## When to Use\n\nExecution-time guard against doing *more* than the user asked. Its sibling at\nplan stage is **design-minimalism**, which strips speculative primitives from a\nplan before any code exists; scope-guard instead holds the line on explicit user\nconstraints (\"only X\", \"don't touch Y\") *while* you execute. If you're weighing\nwhether an abstraction is justified, that's design-minimalism; if you're tempted\nto bolt on unrequested \"helpful\" work, that's this skill.\n\n## Checklist\n\n### Before Starting Execution\n\n1. **Extract constraints:** List every explicit limitation from the user's request\n   (e.g., \"signatures only\", \"no tests\", \"just the plan\")\n2. **Record constraints** in plan.md under a `## Scope Constraints` section\n3. **Define \"done\":** What is the minimum deliverable that satisfies the request?\n\n### Before Each Action\n\n4. **Scope check:** Is this action within the recorded constraints?\n   - YES → proceed\n   - NO → go to step 5\n5. **Escalate, don't decide:** If you believe a constraint should be violated\n   (e.g., minimal implementation needed to compile), ASK the user first.\n   Never silently expand scope.\n\n### Execution Checkpoints\n\n6. **Checkpoint rule:** After every **5 significant tool calls** (Edit, Write, Bash that changes state),\n   pause and deliver a brief status:\n   - What was done so far (1-2 lines)\n   - What's next (1-2 lines)\n   - Any deviations from plan\n7. **Large task threshold:** If executing 10+ tool calls in a single response,\n   STOP after 5 and checkpoint. Do not continue silently.\n8. **Plan revision: prefer Write over many Edits.** When revising a plan file\n   (`\u003Cai_hats_dir>\u002Ftracker\u002Fbacklog\u002Ftasks\u002F*\u002Fplan.md` — the one canonical plan\n   home): if more than 2 distinct sections of the\n   plan need to change, use a single `Write` to rewrite the whole file rather\n   than 3+ sequential `Edit` calls. Plan files are short enough that a full\n   rewrite costs the same as the diffs but avoids per-edit permission and\n   round-trip overhead for the supervisor.\n9. **\"discuss before implement\" gate:** On non-trivial tasks, present the approach\n   before executing. One paragraph, not a wall of text. Wait for confirmation.\n\n### After Completing Work\n\n6. **Scope audit:** Compare what you delivered against the original constraints.\n   Did you do more than asked? Flag it.\n\n## Completion\n\n- Constraints recorded in plan.md\n- Every action within recorded constraints, or user approved the deviation\n- No unrequested work delivered without explicit approval\n\n## Rationalization red-flags\n\nScope creep arrives as a thought you tell yourself *before* the action. Catch\nthe rationalization, not just the regret:\n\n| Rationalization (what you tell yourself)            | Why it's wrong                                                                                                         |\n| --------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- |\n| \"I'll just add this helper while I'm here\"          | Not requested — the user scopes, your convenience doesn't                                                              |\n| \"Skeleton\u002Finfra obviously means wire up everything\" | Defaults to *only what was named*; ask with a concrete enumeration (switched 4 handlers, user rolled back 3) |\n| \"It won't compile without this extra bit\"           | Maybe — but that is an escalation (\"ASK first\"), not a licence to expand silently                                      |\n| \"Faster to do it all now than to ask\"               | The ask round-trip is cheaper than the rollback                                                                        |\n\n**Red-flag words in your own reasoning:** \"while I'm here\", \"just also\", \"might\nas well\", \"obviously they'd want\", \"to be safe\". Any of these → re-run the scope\ncheck (step 4) and escalate (step 5) instead of proceeding.\n\n**Forbidden workaround:** expanding scope and \"flagging it\" in the final summary\nis *not* consent — flagging after the fact does not substitute for asking\nbefore the action. (Rationalization-table discipline adapted from\nobra\u002Fsuperpowers, MIT.)\n\n## Anti-Patterns\n\n- \"I'll just add this helper since I'm here\" — scope creep\n- Justifying scope expansion internally without asking — the user decides, not you\n- Writing full implementations when asked for signatures\u002Finterfaces\n- Writing tests when asked for design only\n- 30+ tool calls in a single response without a checkpoint — the user loses visibility\n- Skipping \"discuss approach\" on tasks with multiple implementation options\n- **\"Skeleton \u002F infrastructure \u002F framework\" signal misread.** When the user\n  says \"make a skeleton of X\" or \"set up the infrastructure for Y\" or\n  \"wire up the framework call for Z\" — interpret as **minimum viable demo +\n  ask before expanding**, NOT as \"wire up all related entry-points\". A\n  one-liner answer about scope without an explicit \"everything\" defaults to\n  \"only what was specifically named\". Worked example — user said\n  \"нужен скелет вызова ai-hats\", agent switched 4 CLI handlers via\n  pipeline-presets; user rolled back 3 of them. The correct ask is: \"only X,\n  X and Y, or all four?\" with a concrete enumeration.\n",{"name":5,"license":15,"description":7},"master","b4819add93efbaf4d80627118ec34680406b309b","packages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fcore\u002Fskills\u002Fscope-guard",1,"https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats","https:\u002F\u002Fgithub.com\u002Fmuratovv","2026-11-05 20:59:10",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add muratovv\u002Fai-hats --skill scope-guard",{"tool":54,"command":55},"bunx","bunx skills add muratovv\u002Fai-hats --skill scope-guard",{"tool":57,"command":58},"pnpm","pnpm dlx skills add muratovv\u002Fai-hats --skill scope-guard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fcore\u002Fskills\u002Fscope-guard\u002FSKILL.md",true,[62,67],{"path":63,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"LICENSE","许可证",1070,"https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fcore\u002Fskills\u002Fscope-guard\u002FLICENSE",{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"metadata.yaml","REFERENCE","参考文档",881,"https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fcore\u002Fskills\u002Fscope-guard\u002Fmetadata.yaml",[74,100,124,147,171,185],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":36},"01M6PVFB1SM738R2SRSRSF7CY6","tool-evaluation-protocol","Time-bounded protocol for evaluating new tools, libraries, or methodologies before adoption. Use when evaluating a candidate dependency for the project, researching a methodology (e.g. ML\u002FLLM frameworks, testing approaches), or following up on a hype-driven recommendation.","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Ftool-evaluation-protocol\u002FSKILL.md",[],[81,82,83,84,85,86,87,88,89,90,32,91,92,93,94,95,96,97,98,99],"protocol","Evaluation","tool","tool evaluation protocol","testing","ml","libraries","adoption","methodology","Tools","dependency","up","frameworks","time","project","recommendation","for","bounded","candidate",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":36},"01M6PVF7HATBEX1G7N50E2QT57","systematic-debugging","4-phase bug-fix protocol (evidence, pattern, hypothesis, verify). Use when investigating any error, failure, or unexpected behavior, handling bug reports from users or monitoring, or diagnosing test failures with non-obvious causes.","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[107,108,109,110,81,111,112,113,114,115,32,116,117,118,119,120,121,24,122,123],"systematic debugging","debugging","systematic","test","monitoring","hypothesis","verify","behavior","fix","evidence","bug","reports","pattern","users","error","bug-fix","phase",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":135,"publishedAt":36},"01M6PVF3MTQN3RPF73AN34856J","skill-template","Canonical template and validation guide for ai-hats skills. Use when creating a new skill, reviewing an existing one for structural compliance, or deciding which pattern fits a new behavior.","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Fskill-template\u002FSKILL.md",[130],{"categoryNo":131,"categoryName":132,"taxonomyType":133,"taxonomyTypeDesc":134},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[136,137,138,139,140,114,141,32,142,119,143,144,145,97,146],"template","skill template","validation","compliance","hats","guide","new skill","structural","canonical","which","Existing",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":154,"publishedAt":36},"01M6PVF06SCV28QARM5MQPANC9","skill-optimization","Audit and refactor library components to eliminate redundancy and staleness. Use during periodic library maintenance, after adding multiple new skills or rules, when a role's token budget is too high, or after retrospectives identify component issues.","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Fskill-optimization\u002FSKILL.md",[153],{"categoryNo":131,"categoryName":132,"taxonomyType":133,"taxonomyTypeDesc":134},[155,156,157,158,159,160,161,162,163,164,32,165,166,167,168,169,170],"Optimization","skill optimization","components","component","issues","library","audit","refactor","Budget","Rules","periodic","maintenance","token","token budget","role","high",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":36},"01M6PVEXM9717016T9MW82HDCT","silent-fallback-gate","PreToolUse hook — refuses an Edit or Write that adds an inert broad except. Use when a Python edit was blocked for a silent fallback.","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Fsilent-fallback-gate\u002FSKILL.md",[],[178,179,180,181,182,183,32,184,97],"gate","fallback","silent fallback gate","python","write","edit","hook",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":192,"publishedAt":36},"01M6PVESM49C5NT7SB7N3F76VS","retro-to-framework","Convert an observation about agent behavior — from a retrospective or from a single incident — into a framework-level change (hook, rule, skill, skill update). Use after a retrospective identifies problems that are not project-specific, after an incident where an agent misapplied a component it had read, when CLAUDE.md band-aids accumulate (more than 3 per-project rules that could be generic), or when the same problem recurs across multiple projects.","https:\u002F\u002Fgithub.com\u002Fmuratovv\u002Fai-hats\u002Fblob\u002Fmaster\u002Fpackages\u002Fai-hats-library\u002Fsrc\u002Fai_hats_library\u002Fexperimental\u002Fusage\u002Fskills\u002Fretro-to-framework\u002FSKILL.md",[191],{"categoryNo":131,"categoryName":132,"taxonomyType":133,"taxonomyTypeDesc":134},[193,194,195,196,158,197,198,199,164,114,32,200,201,95,202,203,204,205,206,207],"framework","retro","retro to framework","change","retrospective","projects","convert","incident","across","problem","about","more","skill update","single","generic"]