[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CQMHQYDDCSDR04GS03SMXR":3,"skill-same:01M7CQMHQYDDCSDR04GS03SMXR":73},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"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":26,"commitSha":27,"skillDirectory":28,"forksCount":13,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":44},"01M7CQMHQYDDCSDR04GS03SMXR","goal-create",null,"Create a session goal prompt or draft repository purpose. This skill never fires on its own; it must be invoked by name. Can synthesize a prompt from confirmed intent or spec and activate it through an available native host goal tool; does not operate the Loom workflow.","kouko\u002Floom-plugins","kouko","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1480254?v=4","01M7CQCPAJR9C92XDGR0QDCQ98","01M7CQCPB8FTVY1BT26ENK1YP4",0,"MIT","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Fgoal-create\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: goal-create\nversion: 0.2.0\ndescription: |\n  Create a session goal prompt or draft repository purpose. This skill never fires on its own; it must be invoked by name. Can synthesize a prompt from confirmed intent or spec and activate it through an available native host goal tool; does not operate the Loom workflow.\nuser-invocable: true\n---\n\n# Goal Create\n\nOne skill, two named modes: **SESSION** and **ARC**. Which mode runs is\nchosen by what the user asks for — a goal for this run, or a purpose for\nthe repository — never by the agent guessing from context.\n\n`\u003Cskill-dir>` is this skill's folder: `${CLAUDE_SKILL_DIR}` on Claude Code;\non any other host, the directory that holds this SKILL.md.\n\n## SESSION mode\n\nSESSION emits the four-field goal condition defined in\n`references\u002Fgoal-shape.md`. Read that file for the field order and each\nfield's definition before drafting; do not reconstruct the shape from\nmemory.\n\nBefore drafting, read `references\u002Finput-floor.md` for the two input slots\na goal is drafted from, the refusal rule when a slot is empty, the\nprovenance tag every field must carry, and the citation boundary between\nquoting a recorded purpose and a user's own decision.\n\nOnce a draft is ready, run the mechanical floor:\n\n```\npython3 \u003Cskill-dir>\u002Fscripts\u002Fgoal_lint.py \u003Cgoal-file>\n```\n\n(or pipe the goal text on stdin with no argument). This checker enforces\nstructure only — a field label present with content, a backticked command\ninside `Verification`, the character limit — never whether the prose\nactually reads as decidable, already-false, or free of a person. The bar\nin `references\u002Finput-floor.md` §4 stays a judgement call the agent makes\neach time; no script can pass or fail it on the agent's behalf.\n\nThe script exits 1 on any hard failure and 0 otherwise. On exit 1, the\ndraft is rewritten to fix what it flagged and the checker is re-run — a\ndraft is never shown to the user until it exits 0.\n\n\u003C!-- gate: goal-create.session-activation -->\nThis skill ends after presenting the prompt and reporting host activation\nor recovery below. It does not invoke Loom stations or change their workflow\nrules. The prompt may refer its executor to an existing workflow; executing\nthat prompt is outside this skill.\n\nAfter exit 0, show the complete four-field condition in one copyable code block,\nthen use the capability actually exposed by the current host. Invoking the\nnamed `goal-create SESSION` mode is explicit authorization to replace any\nactive Goal with this condition, without a separate replacement confirmation.\nConfirmation is only for content: when the Outcome was inferred or materially\nchanged from the user's words, use the host's confirmation path.\n\n### Codex activation\n\nWhen the current session exposes `create_goal`, call it with the complete\nfour-field condition as its objective. If `create_goal` is unavailable, say\nthe Goal is not active and keep the complete prompt available for manual use;\ndo not emulate activation through another process or tool.\nThe authoritative schema and unfinished-Goal refusal are in OpenAI Codex's\n[`spec.rs`](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex\u002Fblob\u002Fmain\u002Fcodex-rs\u002Fext\u002Fgoal\u002Fsrc\u002Fspec.rs)\nand [`tool.rs`](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex\u002Fblob\u002Fmain\u002Fcodex-rs\u002Fext\u002Fgoal\u002Fsrc\u002Ftool.rs).\nCall the Goal active only after host-provided success. On any failure, report\nthe host's reason and say the new Goal is not active. In particular, when an\nunfinished Goal makes `create_goal` refuse replacement, preserve it and tell\nthe user to run `\u002Fgoal clear`, then run `goal-create SESSION` again.\n\n### Claude Code activation\n\n`\u002Fgoal` availability does not imply that `ProposeGoal` is exposed to the\nagent. Use the native proposal path only when the current session's tools\nactually include it. Otherwise go directly to the manual fallback below.\nDo not ask the user to change internal settings or feature flags to expose\nthe tool, or infer availability from SDK types or installed package code.\n\nWhen the interactive session exposes `ProposeGoal`, derive a proposal of at\nmost 500 characters from the complete condition just shown. It preserves the\nOutcome, every behavior-changing Constraint, the decisive Verification, and\nthe Stop-when bound, either inline or through an exact reference to that\nimmediately preceding condition. A generic phrase such as \"the goal above\"\nis not an exact reference. If the faithful proposal cannot fit, skip\n`ProposeGoal` and use the manual fallback below.\n\nAnthropic's published Claude Code package defines the `condition`, its\n500-character maximum, `ask_user` default and direct-set path, and the result\nshape in\n[`sdk-tools.d.ts`](https:\u002F\u002Funpkg.com\u002F@anthropic-ai\u002Fclaude-code@2.1.227\u002Fsdk-tools.d.ts).\n\nCall `ProposeGoal` with `ask_user: false` only when the user's own words state\nthe exact Outcome. Otherwise use its confirmation path and report the Goal as\npending, not active, until the host confirms kickoff. An existing Goal does\nnot change this content-confirmation rule: the SESSION invocation already\nauthorizes replacing it without a separate replacement confirmation.\n\nWhen the current session does not expose `ProposeGoal`, or native activation\nreturns a non-success result, say the Goal is not active and user action is\nrequired. Emit one copyable `\u002Fgoal \u003Ccondition>` command in a code block containing the\ncomplete condition, not the compact proposal, and disclose that submitting it\nreplaces any active Goal. Do not invoke `claude -p`, inject keystrokes, launch\nanother process, or install a custom Stop hook.\n\nFor either host, an attempted call, displayed prose, pending confirmation, or\nmanual command is not activation evidence. Report active only from the host's\nsuccessful result, and keep its recoverable reason visible otherwise.\n\u003C!-- \u002Fgate -->\n\n## ARC mode\n\nARC drafts a `Why` and a `Done when` for the repository's purpose artifact\nat `docs\u002Floom\u002FPURPOSE.md` — see that file for its exact two-field format;\nthis skill does not restate it. ARC never writes that file itself; the\ndraft is only ever landed by the user's own confirmation.\n\nARC is conditional. When the repository has no `docs\u002Floom\u002F` store and no\n`docs\u002Floom\u002FPURPOSE.md` file — nothing yet scaffolded to hold one — ARC\nreports itself not applicable, names the reason, and scaffolds nothing —\ncreating the store is `loom-init`'s job, not this skill's.\n\n## Invocation\n\nThis skill never fires on its own — the description above makes no\nauto-fire claim. It is named as an available\noption at exactly one point where the need for a goal is already\nvisible: `loom-workflow:handoff`'s Prepare mode, when a user closes a\nsession without capturing an explicit goal. That surface names this\nskill as an option the user can invoke; it never invokes it. loom 1.0\ndeleted the other two offer sites with the skills that carried them.\n\nWhen `loom-design:capture-intent` is already running for the same work,\nthat station keeps discovery and this skill runs only after its intent\nexists, rather than competing for the same turn.\n\nA user may also invoke this skill by name later in a run — after a\nconfirmed intent or spec — to synthesize the prompt from those artifacts\nand attempt native host activation. That is the same manual\ninvocation, not a new offer site: this skill is still never invoked by\nanything other than a user.\n\n## See also\n\n- `references\u002Fgoal-shape.md` — the four-field goal shape, SESSION's SSOT.\n- `references\u002Finput-floor.md` — the two input slots, the refusal rule, the\n  bar, and provenance tags.\n- `scripts\u002Fgoal_lint.py` — the mechanical floor SESSION's draft is run\n  through before it is presented.\n","# Goal Create\n\nOne skill, two named modes: **SESSION** and **ARC**. Which mode runs is\nchosen by what the user asks for — a goal for this run, or a purpose for\nthe repository — never by the agent guessing from context.\n\n`\u003Cskill-dir>` is this skill's folder: `${CLAUDE_SKILL_DIR}` on Claude Code;\non any other host, the directory that holds this SKILL.md.\n\n## SESSION mode\n\nSESSION emits the four-field goal condition defined in\n`references\u002Fgoal-shape.md`. Read that file for the field order and each\nfield's definition before drafting; do not reconstruct the shape from\nmemory.\n\nBefore drafting, read `references\u002Finput-floor.md` for the two input slots\na goal is drafted from, the refusal rule when a slot is empty, the\nprovenance tag every field must carry, and the citation boundary between\nquoting a recorded purpose and a user's own decision.\n\nOnce a draft is ready, run the mechanical floor:\n\n```\npython3 \u003Cskill-dir>\u002Fscripts\u002Fgoal_lint.py \u003Cgoal-file>\n```\n\n(or pipe the goal text on stdin with no argument). This checker enforces\nstructure only — a field label present with content, a backticked command\ninside `Verification`, the character limit — never whether the prose\nactually reads as decidable, already-false, or free of a person. The bar\nin `references\u002Finput-floor.md` §4 stays a judgement call the agent makes\neach time; no script can pass or fail it on the agent's behalf.\n\nThe script exits 1 on any hard failure and 0 otherwise. On exit 1, the\ndraft is rewritten to fix what it flagged and the checker is re-run — a\ndraft is never shown to the user until it exits 0.\n\n\u003C!-- gate: goal-create.session-activation -->\nThis skill ends after presenting the prompt and reporting host activation\nor recovery below. It does not invoke Loom stations or change their workflow\nrules. The prompt may refer its executor to an existing workflow; executing\nthat prompt is outside this skill.\n\nAfter exit 0, show the complete four-field condition in one copyable code block,\nthen use the capability actually exposed by the current host. Invoking the\nnamed `goal-create SESSION` mode is explicit authorization to replace any\nactive Goal with this condition, without a separate replacement confirmation.\nConfirmation is only for content: when the Outcome was inferred or materially\nchanged from the user's words, use the host's confirmation path.\n\n### Codex activation\n\nWhen the current session exposes `create_goal`, call it with the complete\nfour-field condition as its objective. If `create_goal` is unavailable, say\nthe Goal is not active and keep the complete prompt available for manual use;\ndo not emulate activation through another process or tool.\nThe authoritative schema and unfinished-Goal refusal are in OpenAI Codex's\n[`spec.rs`](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex\u002Fblob\u002Fmain\u002Fcodex-rs\u002Fext\u002Fgoal\u002Fsrc\u002Fspec.rs)\nand [`tool.rs`](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex\u002Fblob\u002Fmain\u002Fcodex-rs\u002Fext\u002Fgoal\u002Fsrc\u002Ftool.rs).\nCall the Goal active only after host-provided success. On any failure, report\nthe host's reason and say the new Goal is not active. In particular, when an\nunfinished Goal makes `create_goal` refuse replacement, preserve it and tell\nthe user to run `\u002Fgoal clear`, then run `goal-create SESSION` again.\n\n### Claude Code activation\n\n`\u002Fgoal` availability does not imply that `ProposeGoal` is exposed to the\nagent. Use the native proposal path only when the current session's tools\nactually include it. Otherwise go directly to the manual fallback below.\nDo not ask the user to change internal settings or feature flags to expose\nthe tool, or infer availability from SDK types or installed package code.\n\nWhen the interactive session exposes `ProposeGoal`, derive a proposal of at\nmost 500 characters from the complete condition just shown. It preserves the\nOutcome, every behavior-changing Constraint, the decisive Verification, and\nthe Stop-when bound, either inline or through an exact reference to that\nimmediately preceding condition. A generic phrase such as \"the goal above\"\nis not an exact reference. If the faithful proposal cannot fit, skip\n`ProposeGoal` and use the manual fallback below.\n\nAnthropic's published Claude Code package defines the `condition`, its\n500-character maximum, `ask_user` default and direct-set path, and the result\nshape in\n[`sdk-tools.d.ts`](https:\u002F\u002Funpkg.com\u002F@anthropic-ai\u002Fclaude-code@2.1.227\u002Fsdk-tools.d.ts).\n\nCall `ProposeGoal` with `ask_user: false` only when the user's own words state\nthe exact Outcome. Otherwise use its confirmation path and report the Goal as\npending, not active, until the host confirms kickoff. An existing Goal does\nnot change this content-confirmation rule: the SESSION invocation already\nauthorizes replacing it without a separate replacement confirmation.\n\nWhen the current session does not expose `ProposeGoal`, or native activation\nreturns a non-success result, say the Goal is not active and user action is\nrequired. Emit one copyable `\u002Fgoal \u003Ccondition>` command in a code block containing the\ncomplete condition, not the compact proposal, and disclose that submitting it\nreplaces any active Goal. Do not invoke `claude -p`, inject keystrokes, launch\nanother process, or install a custom Stop hook.\n\nFor either host, an attempted call, displayed prose, pending confirmation, or\nmanual command is not activation evidence. Report active only from the host's\nsuccessful result, and keep its recoverable reason visible otherwise.\n\u003C!-- \u002Fgate -->\n\n## ARC mode\n\nARC drafts a `Why` and a `Done when` for the repository's purpose artifact\nat `docs\u002Floom\u002FPURPOSE.md` — see that file for its exact two-field format;\nthis skill does not restate it. ARC never writes that file itself; the\ndraft is only ever landed by the user's own confirmation.\n\nARC is conditional. When the repository has no `docs\u002Floom\u002F` store and no\n`docs\u002Floom\u002FPURPOSE.md` file — nothing yet scaffolded to hold one — ARC\nreports itself not applicable, names the reason, and scaffolds nothing —\ncreating the store is `loom-init`'s job, not this skill's.\n\n## Invocation\n\nThis skill never fires on its own — the description above makes no\nauto-fire claim. It is named as an available\noption at exactly one point where the need for a goal is already\nvisible: `loom-workflow:handoff`'s Prepare mode, when a user closes a\nsession without capturing an explicit goal. That surface names this\nskill as an option the user can invoke; it never invokes it. loom 1.0\ndeleted the other two offer sites with the skills that carried them.\n\nWhen `loom-design:capture-intent` is already running for the same work,\nthat station keeps discovery and this skill runs only after its intent\nexists, rather than competing for the same turn.\n\nA user may also invoke this skill by name later in a run — after a\nconfirmed intent or spec — to synthesize the prompt from those artifacts\nand attempt native host activation. That is the same manual\ninvocation, not a new offer site: this skill is still never invoked by\nanything other than a user.\n\n## See also\n\n- `references\u002Fgoal-shape.md` — the four-field goal shape, SESSION's SSOT.\n- `references\u002Finput-floor.md` — the two input slots, the refusal rule, the\n  bar, and provenance tags.\n- `scripts\u002Fgoal_lint.py` — the mechanical floor SESSION's draft is run\n  through before it is presented.\n",{"name":5,"version":23,"description":24,"user-invocable":25},"0.2.0","Create a session goal prompt or draft repository purpose. This skill never fires on its own; it must be invoked by name. Can synthesize a prompt from confirmed intent or spec and activate it through an available native host goal tool; does not operate the Loom workflow.\n",true,"main","3b1a9972644517911454530dc1876f88525b1f37","loom-workflow\u002Fskills\u002Fgoal-create","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins","https:\u002F\u002Fgithub.com\u002Fkouko","2026-11-15 00:45:02",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":25},[34,37,40],{"tool":35,"command":36},"npx","npx skills add kouko\u002Floom-plugins --skill goal-create",{"tool":38,"command":39},"bunx","bunx skills add kouko\u002Floom-plugins --skill goal-create",{"tool":41,"command":42},"pnpm","pnpm dlx skills add kouko\u002Floom-plugins --skill goal-create","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Fgoal-create\u002FSKILL.md",[45,51,55,59,63,67],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"README.ja.md","REFERENCE","参考文档",4045,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Fgoal-create\u002FREADME.ja.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"README.md",3372,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Fgoal-create\u002FREADME.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"README.zh-TW.md",3164,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Fgoal-create\u002FREADME.zh-TW.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fgoal-shape.md",6443,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Fgoal-create\u002Freferences\u002Fgoal-shape.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Finput-floor.md",5858,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Fgoal-create\u002Freferences\u002Finput-floor.md",{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"scripts\u002Fgoal_lint.py","SCRIPT","脚本",9938,"https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Fgoal-create\u002Fscripts\u002Fgoal_lint.py",[74,81,88,95,102,109],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M7CQNVD2W5MP7PKX3MD0YSQE","using-loom-workflow","Route broad Loom workflow-tool requests to the right skill. Use when the request spans tools or the right workflow skill is unclear.","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Fusing-loom-workflow\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M7CQNNTPVG52CS2C6Q9HJ2E2","skill-retro","Review selected past or current Claude Code or Codex sessions against readable target skill sources and related integration. Produce source-linked proposals without applying changes.","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Fskill-retro\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M7CQNHR1BDKJ63CC4R1RY9GE","recap-state","Give an in-session recap of current progress for 'where were we', '我們剛剛在幹嘛', '剛剛講到哪', '我跟丟了', 'ちょっと振り返って', '今どこだっけ', or '振り返り'. The built-in \u002Frecap is an away-summary.","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Frecap-state\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M7CQNE1A9272WPRE1MM3JRFK","project-retro","Review one current or specified coding session for source-backed project\ndevelopment improvements. Use for a requested retrospective, including\n振り返り seeking improvements; not for current-progress recaps or recurring skill mining.","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Fproject-retro\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":18},"01M7CQNACJB36T0A039HT89P38","loom-visualization","Show comparisons, flows, decisions, states or reasoning chains as tables, ASCII or Mermaid in coding chat, including when a Loom station reports to the user (intent restatement, choices, acceptance test results); not Obsidian notes.","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-visualization\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":18},"01M7CQN7TVS0XF44JXQBWA32Z1","loom-memory","Record repo-wide lessons when saving to your own memory or asked to remember; recall, reconcile, or forget them when a task needs it.","https:\u002F\u002Fgithub.com\u002Fkouko\u002Floom-plugins\u002Fblob\u002Fmain\u002Floom-workflow\u002Fskills\u002Floom-memory\u002FSKILL.md",[],[]]