[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MEQFSAFKAPJQW4D7PJFMWF":3,"skill-same:01M6MEQFSAFKAPJQW4D7PJFMWF":126},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":71,"commitSha":72,"skillDirectory":73,"forksCount":74,"repositoryHtmlUrl":75,"repositoryHomepageUrl":76,"ownerHtmlUrl":77,"ownerBlogUrl":78,"ownerDescription":79,"updatedAt":80,"install":81,"resources":93},"01M6MEQFSAFKAPJQW4D7PJFMWF","memory",null,"Find or curate supported lessons and agent rules. Use when: asked to remember, trace a corrected claim, audit instructions or write an agent rule.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1559,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fmemory\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"canonical","limits","when","page","evidence","mine","remember","path","bounded","context","agent rules","drafts","write","curate","update","support","audit","mining","change","updates","claim","2026-11-10 10:12:30",false,"---\nname: memory\ndescription: \"Find or curate supported lessons and agent rules. Use when: asked to remember, trace a corrected claim, audit instructions or write an agent rule.\"\npractices:\n- evidence-based-engineering\n- continuous-learning\nhexagonal_role: supporting\nconsumes: []\nproduces:\n- applicable-context\n- reviewed-topic-pages\n- ranked-toil-evidence\ncontext_rel: []\nskill_api_version: 1\nuser-invocable: true\nmetadata:\n  graph_root: true\n  tier: execution\n  dependencies: []\n  capabilities: [recall_applicable_context, mine_supported_observations, curate_topic_pages, toil_mining]\n  effects: [write_protected_drafts, update_authorized_topic_pages, write_requested_toil_report]\n  canonical_status: canonical\n  disposition: keep_off_path\noutput_contract: 'bounded applicable evidence or no-match; reviewed topic-page updates or no-change; ranked toil evidence with support, limits and unresolved gaps'\n---\n\n# Memory\n\nMemory keeps short notes a person checked: each one sized to its evidence,\nstating when it applies, what to do, its support, its limits and what retires\nit, and saved only after review. Use a note only when it changes an action.\nA run that worked returns a narrow, reviewed entry or says why nothing was\nsaved. Memory is optional:\nno mandatory recall at RPI entry, lesson at completion, worksheet, page quota or\nbackground mining. A trivial edit can proceed directly to implementation.\n\n## Rules for any saved lesson or rule\n\nApply these whenever a request would save or promote a lesson, including a\nrequest to turn an incident into a rule for an instruction file:\n\n1. **Look for an existing entry first.** Search the selected `.context\u002F` pages,\n   external topic pages or the target instruction file (`AGENTS.md`,\n   `CLAUDE.md`, a team rules file). Amend the entry that already covers the\n   behavior; add a new one only when none fits. If the final code, tests,\n   comments or a doc already explain the reasoning, point there rather than\n   save a copy; save only what they cannot show a later reader, such as\n   ruled-out causes, why the fix works and what brings the failure back.\n   Effort, a finished task or a large diff never qualifies a lesson. If nothing\n   qualifies, save nothing and say why.\n2. **Size the claim to its evidence.** One incident supports a narrow\n   observation scoped to the conditions it actually had. A universal rule needs\n   repeated independent occurrences and later reapplication. When a recurring\n   correction is a mechanical slip that a lint rule, test or hook could catch,\n   propose that check alongside the prose rule or in its place, as\n   [Postmortem](..\u002Fpostmortem\u002FSKILL.md) does for such a miss; a check fails\n   where a rule can only ask.\n3. **State all five fields:** applicability, action, support, limits and invalidation.\n   Use the template below; an entry with no invalidation is incomplete. For an\n   incident, applicability includes the exact error text or observable symptom,\n   the words a later search will use. An instruction file such as `AGENTS.md`\n   loads into every session, so its entry is usually one line: the action and\n   when it applies, worded as information rather than an order to read, linking\n   the project `.context\u002F` page or the doc beside the governed code (never an\n   external-bundle page from a checked-in file) that carries all five fields. A\n   line that only restates what agents already do by default earns no place.\n4. **Review before admission.** Give the draft inline in your reply unless the\n   caller named storage outside Git; never write it into the repository before\n   review. A saved note is one a person checked: the person who asked reads the\n   exact text, paths and destination and approves it before it enters\n   `.context\u002F`, an instruction file such as `AGENTS.md`, or any Git object.\n   When they ask you to save it without reading it, get one fresh read from a\n   context that did not write the draft, checking factual support and\n   disclosure; one round, and a repair does not start a second review. When\n   neither can check it, write nothing: keep the draft inline, report it as not\n   saved and name the missing check.\n   Promoting an entry into an instruction file is a separate policy change\n   owned by that file. On an explicit request to remember something, the\n   runtime's own memory store (such as Claude Code auto-memory or Codex memory)\n   is a valid destination; rules 1-3 still apply, and this review is owed only\n   when that store is shared or checked in.\n5. **Saving proves nothing.** Saved pages, retrieval counts and structural\n   checks prove no benefit. Only later work can show that reuse changed an\n   action and helped; keep failed, harmful and no-change results. Until then a\n   saved rule is an untested hypothesis.\n\n```markdown\n### \u003Cone-line claim>\n- Applies when: \u003Cthe conditions the evidence covered>\n- Action: \u003Cthe check or step to take>\n- Support: \u003Ccited sources, each with the commit or date observed; number of independent occurrences>\n- Limits: \u003Cwhere it is untested or may not hold>\n- Invalidate when: \u003Cthe change or contrary evidence that retires it, and how to check it>\n```\n\nKeep rare useful constraints; age or low frequency alone is no reason to delete\nthem. Learning may also simplify or remove rules.\n\n## Choose one operation\n\n| Need | Read on demand |\n|---|---|\n| An earlier constraint or source map may change the next action | [Find \u002F recall](references\u002Frecall.md) |\n| Draft a note from an incident, correction or source the person names | [Capture a note](references\u002Fmine-learn.md) |\n| Update, qualify, consolidate or retire a supported claim | [Curate \u002F qualify \u002F retire](references\u002Fcurate.md) |\n| Rank repeated operational friction in supplied history | [Toil evidence](references\u002Ftoil.md) |\n| Trace a corrected claim or audit the loaded instruction set | [Instruction sources](references\u002Finstruction-sources.md) |\n\nMemory owns these operations. Whether recurring evidence warrants a general\nrule is decided by [Research's pattern mode](..\u002Fresearch\u002FSKILL.md#pattern-evidence)\n(independent exemplars and a holdout). Capture drafts notes for a person to\ncheck; it does not extract lessons from history in bulk, and it is never a\nrequired completion step. Load only the selected operation's reference. The optional\n[OKF page profile](references\u002Flearn\u002Fokf-page-profile.md) checks structure only.\n\n## One authority per fact\n\nBD or the caller's tracker owns work and handoffs, Git owns content history,\nand native sessions or CASS own episodes. Reviewed topic pages in a project\n`.context\u002F` or an external bundle hold reusable claims and point to the docs,\nADRs and code that own a policy instead of copying it. Do not make one lesson\nfile per session, copy a transcript lake, or silently initialize a memory\nstore. Read a project `.context\u002F` from its `README.md` map, when present, with\n`rg` and `cat`; this needs neither BD nor AO and creates nothing. External bundles and the\n`ao config context` route are in [Find \u002F recall](references\u002Frecall.md).\n\n## Access, storage and honest limits\n\nUse only sources already authorized for the task, owner, model\u002Fprovider and\nexact destination; read permission does not imply publication or Git storage.\nThis skill **enforces no access control**, so do not route restricted material\nthrough it; `ao session read-source` grants no broader transcript access. Unavailable and\ndenied evidence remain explicit gaps; do not fetch then redact. Drafts and\nreview proof go inline in your reply or to storage outside Git that the caller\nnamed; missing routing does not authorize a workspace fallback. Preserve\nrequested legacy `.agents\u002F` proof and unique evidence under owner policy.\nNo blind TTL or delete operation is part of Memory. Labels and structural\nparsers do not prove isolation.\n[ADR-0016](https:\u002F\u002Fgithub.com\u002Fboshu2\u002Fagentops\u002Fblob\u002Fmain\u002Fdocs\u002Fadr\u002FADR-0016-state-tiers.md)\n(AgentOps source checkout only) owns these boundaries. Drafting a note cannot\ndelay an authorized change or alter its verdict.\n","# Memory\n\nMemory keeps short notes a person checked: each one sized to its evidence,\nstating when it applies, what to do, its support, its limits and what retires\nit, and saved only after review. Use a note only when it changes an action.\nA run that worked returns a narrow, reviewed entry or says why nothing was\nsaved. Memory is optional:\nno mandatory recall at RPI entry, lesson at completion, worksheet, page quota or\nbackground mining. A trivial edit can proceed directly to implementation.\n\n## Rules for any saved lesson or rule\n\nApply these whenever a request would save or promote a lesson, including a\nrequest to turn an incident into a rule for an instruction file:\n\n1. **Look for an existing entry first.** Search the selected `.context\u002F` pages,\n   external topic pages or the target instruction file (`AGENTS.md`,\n   `CLAUDE.md`, a team rules file). Amend the entry that already covers the\n   behavior; add a new one only when none fits. If the final code, tests,\n   comments or a doc already explain the reasoning, point there rather than\n   save a copy; save only what they cannot show a later reader, such as\n   ruled-out causes, why the fix works and what brings the failure back.\n   Effort, a finished task or a large diff never qualifies a lesson. If nothing\n   qualifies, save nothing and say why.\n2. **Size the claim to its evidence.** One incident supports a narrow\n   observation scoped to the conditions it actually had. A universal rule needs\n   repeated independent occurrences and later reapplication. When a recurring\n   correction is a mechanical slip that a lint rule, test or hook could catch,\n   propose that check alongside the prose rule or in its place, as\n   [Postmortem](..\u002Fpostmortem\u002FSKILL.md) does for such a miss; a check fails\n   where a rule can only ask.\n3. **State all five fields:** applicability, action, support, limits and invalidation.\n   Use the template below; an entry with no invalidation is incomplete. For an\n   incident, applicability includes the exact error text or observable symptom,\n   the words a later search will use. An instruction file such as `AGENTS.md`\n   loads into every session, so its entry is usually one line: the action and\n   when it applies, worded as information rather than an order to read, linking\n   the project `.context\u002F` page or the doc beside the governed code (never an\n   external-bundle page from a checked-in file) that carries all five fields. A\n   line that only restates what agents already do by default earns no place.\n4. **Review before admission.** Give the draft inline in your reply unless the\n   caller named storage outside Git; never write it into the repository before\n   review. A saved note is one a person checked: the person who asked reads the\n   exact text, paths and destination and approves it before it enters\n   `.context\u002F`, an instruction file such as `AGENTS.md`, or any Git object.\n   When they ask you to save it without reading it, get one fresh read from a\n   context that did not write the draft, checking factual support and\n   disclosure; one round, and a repair does not start a second review. When\n   neither can check it, write nothing: keep the draft inline, report it as not\n   saved and name the missing check.\n   Promoting an entry into an instruction file is a separate policy change\n   owned by that file. On an explicit request to remember something, the\n   runtime's own memory store (such as Claude Code auto-memory or Codex memory)\n   is a valid destination; rules 1-3 still apply, and this review is owed only\n   when that store is shared or checked in.\n5. **Saving proves nothing.** Saved pages, retrieval counts and structural\n   checks prove no benefit. Only later work can show that reuse changed an\n   action and helped; keep failed, harmful and no-change results. Until then a\n   saved rule is an untested hypothesis.\n\n```markdown\n### \u003Cone-line claim>\n- Applies when: \u003Cthe conditions the evidence covered>\n- Action: \u003Cthe check or step to take>\n- Support: \u003Ccited sources, each with the commit or date observed; number of independent occurrences>\n- Limits: \u003Cwhere it is untested or may not hold>\n- Invalidate when: \u003Cthe change or contrary evidence that retires it, and how to check it>\n```\n\nKeep rare useful constraints; age or low frequency alone is no reason to delete\nthem. Learning may also simplify or remove rules.\n\n## Choose one operation\n\n| Need | Read on demand |\n|---|---|\n| An earlier constraint or source map may change the next action | [Find \u002F recall](references\u002Frecall.md) |\n| Draft a note from an incident, correction or source the person names | [Capture a note](references\u002Fmine-learn.md) |\n| Update, qualify, consolidate or retire a supported claim | [Curate \u002F qualify \u002F retire](references\u002Fcurate.md) |\n| Rank repeated operational friction in supplied history | [Toil evidence](references\u002Ftoil.md) |\n| Trace a corrected claim or audit the loaded instruction set | [Instruction sources](references\u002Finstruction-sources.md) |\n\nMemory owns these operations. Whether recurring evidence warrants a general\nrule is decided by [Research's pattern mode](..\u002Fresearch\u002FSKILL.md#pattern-evidence)\n(independent exemplars and a holdout). Capture drafts notes for a person to\ncheck; it does not extract lessons from history in bulk, and it is never a\nrequired completion step. Load only the selected operation's reference. The optional\n[OKF page profile](references\u002Flearn\u002Fokf-page-profile.md) checks structure only.\n\n## One authority per fact\n\nBD or the caller's tracker owns work and handoffs, Git owns content history,\nand native sessions or CASS own episodes. Reviewed topic pages in a project\n`.context\u002F` or an external bundle hold reusable claims and point to the docs,\nADRs and code that own a policy instead of copying it. Do not make one lesson\nfile per session, copy a transcript lake, or silently initialize a memory\nstore. Read a project `.context\u002F` from its `README.md` map, when present, with\n`rg` and `cat`; this needs neither BD nor AO and creates nothing. External bundles and the\n`ao config context` route are in [Find \u002F recall](references\u002Frecall.md).\n\n## Access, storage and honest limits\n\nUse only sources already authorized for the task, owner, model\u002Fprovider and\nexact destination; read permission does not imply publication or Git storage.\nThis skill **enforces no access control**, so do not route restricted material\nthrough it; `ao session read-source` grants no broader transcript access. Unavailable and\ndenied evidence remain explicit gaps; do not fetch then redact. Drafts and\nreview proof go inline in your reply or to storage outside Git that the caller\nnamed; missing routing does not authorize a workspace fallback. Preserve\nrequested legacy `.agents\u002F` proof and unique evidence under owner policy.\nNo blind TTL or delete operation is part of Memory. Labels and structural\nparsers do not prove isolation.\n[ADR-0016](https:\u002F\u002Fgithub.com\u002Fboshu2\u002Fagentops\u002Fblob\u002Fmain\u002Fdocs\u002Fadr\u002FADR-0016-state-tiers.md)\n(AgentOps source checkout only) owns these boundaries. Drafting a note cannot\ndelay an authorized change or alter its verdict.\n",{"name":5,"consumes":45,"metadata":46,"produces":60,"practices":64,"context_rel":67,"description":7,"hexagonal_role":68,"user-invocable":52,"output_contract":69,"skill_api_version":70},[],{"tier":47,"effects":48,"graph_root":52,"disposition":53,"capabilities":54,"dependencies":59,"canonical_status":19},"execution",[49,50,51],"write_protected_drafts","update_authorized_topic_pages","write_requested_toil_report",true,"keep_off_path",[55,56,57,58],"recall_applicable_context","mine_supported_observations","curate_topic_pages","toil_mining",[],[61,62,63],"applicable-context","reviewed-topic-pages","ranked-toil-evidence",[65,66],"evidence-based-engineering","continuous-learning",[],"supporting","bounded applicable evidence or no-match; reviewed topic-page updates or no-change; ranked toil evidence with support, limits and unresolved gaps",1,"main","347aedf8480cd92b21f761e97b7343a45898f5fa","plugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fmemory",474,"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 14:40:14",{"source":8,"skillName":5,"commands":82,"prompt":92,"zipAvailable":52},[83,86,89],{"tool":84,"command":85},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill memory",{"tool":87,"command":88},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill memory",{"tool":90,"command":91},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill memory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fmemory\u002FSKILL.md",[94,100,104,108,112,116,120],{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fcurate.md","REFERENCE","参考文档",6470,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fmemory\u002Freferences\u002Fcurate.md",{"path":101,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Finstruction-sources.md",3043,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fmemory\u002Freferences\u002Finstruction-sources.md",{"path":105,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Flearn\u002Fokf-page-profile.md",3831,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fmemory\u002Freferences\u002Flearn\u002Fokf-page-profile.md",{"path":109,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fmine-learn.md",3169,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fmemory\u002Freferences\u002Fmine-learn.md",{"path":113,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Frecall.md",2832,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fmemory\u002Freferences\u002Frecall.md",{"path":117,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Ftoil.md",1824,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fmemory\u002Freferences\u002Ftoil.md",{"path":121,"resourceType":122,"resourceTypeDesc":123,"sizeBytes":124,"sourceHtmlUrl":125},"scripts\u002Fvalidate.sh","SCRIPT","脚本",860,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fmemory\u002Fscripts\u002Fvalidate.sh",[127,135,142,149,173,197],{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":134},"01M746ZWACVKMZ1BJXJZHYJSSX","migrate-to-e2e","Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for \u002Fmigrate-to-e2e, \"migrate our tests to e2e\", \"port these Maestro flows\", \"move our TesterArmy tests\", or when a project has an e2e config and an older suite still running.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fmigrate-to-e2e\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":134},"01M746ZPTAX1Q0FBKAB1CYND7E","e2e","Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fe2e\u002FSKILL.md",[],[],{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":134},"01M746ZJN784HVHMDP9MQGCSGG","create-verification-skill","Generate a project-local verify-\u003Capp> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for \u002Fcreate-verification-skill, \"make a verification skill for this repo\", or when a project has no scripted way to prove UI behavior.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fcreate-verification-skill\u002FSKILL.md",[],[],{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":40},"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",[],[156,157,158,159,160,5,161,162,163,164,165,21,166,167,168,169,37,170,171,172],"search","deja search","never","error","ready","re","decide","fix","design","debugging","you","done","reviewer","io","cli","merge","past",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":40},"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",[],[180,181,182,169,183,184,185,186,187,188,189,190,191,25,5,192,193,194,195,196],"deja reflect","reflect","review","with","record","github","next","https","node","Rules","decisions","brew","project rules","project","session","end","reflection",{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":214,"publishedAt":40},"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",[203,208,211],{"categoryNo":204,"categoryName":205,"taxonomyType":206,"taxonomyTypeDesc":207},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":209,"categoryName":210,"taxonomyType":206,"taxonomyTypeDesc":207},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":212,"categoryName":213,"taxonomyType":206,"taxonomyTypeDesc":207},"01JBSEEDCAT000000000000010","后端与接口",[199,215,216,217,218,219,220,193,221,161,222,223,224,225,21,226,227,228,229,230],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]