[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7704GPJRPS2FPFTZGHN6B3R":3,"skill-same:01M7704GPJRPS2FPFTZGHN6B3R":49},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7704GPJRPS2FPFTZGHN6B3R","ber",null,"Better Every Run: turn explicit \u002Fber corrections into preferred future outcomes through a small fix, remember, and report flow.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fb\u002Fbetter-every-run\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: ber\ndescription: \"Better Every Run: turn explicit \u002Fber corrections into preferred future outcomes through a small fix, remember, and report flow.\"\nuser-invocable: true\nmetadata:\n  version: \"0.5.5\"\n---\n# Better Every Run\n\nUse this skill only when the user explicitly invokes `\u002Fber`, names Better Every Run, or directly asks to persist a lesson for future runs. Do not auto-capture ordinary corrections, casual preferences, or words like \"remember\", \"always\", \"never\", or \"next time\" unless the user clearly wants durable learning.\n\nThe human path is deliberately small:\n\n```text\n\u002Fber fix bad outcome -> desired outcome\n\u002Fber remember simple rule\n\u002Fber report\n```\n\nThe agent runs the bundled local helper and reports the result in chat. `fix` and `remember` record only to the local `.better-every-run\u002F` evidence store. Durable memory\u002Fskill changes require the reviewed `card` + `promote` flow; eval regression cases require `eval-fixture`.\n\n## When To Use\n\n- The user explicitly types `\u002Fber fix ... -> ...`.\n- The user explicitly types `\u002Fber remember ...`.\n- The user explicitly asks for a Better Every Run report.\n- The user asks the agent to record a reusable correction as durable memory.\n\n## Human Commands\n\n```text\n\u002Fber fix agent wrote vague status -> agent gives exact command output and next action\n\u002Fber remember use the approved development host for active code work\n\u002Fber report\n```\n\n## Rules\n\n- Report CLI output back in chat; do not build web pages or dashboards.\n- Do not silently edit `MEMORY.md`, `AGENTS.md`, `SOUL.md`, or other durable instruction files.\n- Do not pass `--target` to `\u002Fber fix` or `\u002Fber remember`; direct durable writes are disabled and must refuse.\n- Only promote to durable memory or skill files after an explicit review decision using `card` then `promote`.\n- Memory promotions must target an existing `memory\u002F*.md` file.\n- Skill promotions must target `SKILL.md` in the current skill project.\n- Eval fixtures must use `eval-fixture` and target `.json` or `.jsonl` under `tests\u002F` or `evals\u002F`.\n- Scanner hard blocks and warnings both block promotion. Adjust, quarantine, or supersede the lesson instead of forcing it through.\n- Keep corrections factual: bad outcome, desired outcome, and scope.\n- Use scope metadata when it helps decide whether a lesson belongs only to this run, the project, the workspace, a skill, memory, or an eval.\n- Avoid private data unless the user explicitly wants it captured.\n- Keep the user-facing flow short, but disclose persistence: local store, durable target file if promoted, and how it was reviewed.\n- Design for the shortest path to the user's outcome.\n- Never publish `.better-every-run\u002F` state, local lessons, event logs, or private corrections.\n\n## Workflow\n\nFor normal chat use, keep the visible flow to one command:\n\n```text\n\u002Fber fix bad outcome -> desired outcome\n```\n\nFor simple one-line preferences:\n\n```text\n\u002Fber remember simple rule\n```\n\nUse `\u002Fber report` to show what was learned, including open proposals and promotion suggestions.\n\n## Agent Implementation\n\nKeep low-level helper commands out of normal chat unless debugging, but never hide persistence. A normal answer should say whether the lesson was recorded only in `.better-every-run\u002F` or promoted to a named durable file through a lesson card.\n\nRead `references\u002Fworkflow.md` for the full workflow.\nRead `references\u002Freport-template.md` for expected chat output shape.\n\nBefore publishing or packaging, verify:\n- `.better-every-run\u002F` is excluded\n- `make test` passes\n- direct `fix --target`, `remember --target`, and `apply-memory-patch` attempts refuse without changing target files\n- lesson-card, lifecycle, and eval-fixture demos are generic and contain no private workspace paths, chat IDs, tokens, or hostnames\n- examples contain no private workspace paths, chat IDs, tokens, or hostnames\n- docs say activation is explicit-only and persistence is disclosed\n","# Better Every Run\n\nUse this skill only when the user explicitly invokes `\u002Fber`, names Better Every Run, or directly asks to persist a lesson for future runs. Do not auto-capture ordinary corrections, casual preferences, or words like \"remember\", \"always\", \"never\", or \"next time\" unless the user clearly wants durable learning.\n\nThe human path is deliberately small:\n\n```text\n\u002Fber fix bad outcome -> desired outcome\n\u002Fber remember simple rule\n\u002Fber report\n```\n\nThe agent runs the bundled local helper and reports the result in chat. `fix` and `remember` record only to the local `.better-every-run\u002F` evidence store. Durable memory\u002Fskill changes require the reviewed `card` + `promote` flow; eval regression cases require `eval-fixture`.\n\n## When To Use\n\n- The user explicitly types `\u002Fber fix ... -> ...`.\n- The user explicitly types `\u002Fber remember ...`.\n- The user explicitly asks for a Better Every Run report.\n- The user asks the agent to record a reusable correction as durable memory.\n\n## Human Commands\n\n```text\n\u002Fber fix agent wrote vague status -> agent gives exact command output and next action\n\u002Fber remember use the approved development host for active code work\n\u002Fber report\n```\n\n## Rules\n\n- Report CLI output back in chat; do not build web pages or dashboards.\n- Do not silently edit `MEMORY.md`, `AGENTS.md`, `SOUL.md`, or other durable instruction files.\n- Do not pass `--target` to `\u002Fber fix` or `\u002Fber remember`; direct durable writes are disabled and must refuse.\n- Only promote to durable memory or skill files after an explicit review decision using `card` then `promote`.\n- Memory promotions must target an existing `memory\u002F*.md` file.\n- Skill promotions must target `SKILL.md` in the current skill project.\n- Eval fixtures must use `eval-fixture` and target `.json` or `.jsonl` under `tests\u002F` or `evals\u002F`.\n- Scanner hard blocks and warnings both block promotion. Adjust, quarantine, or supersede the lesson instead of forcing it through.\n- Keep corrections factual: bad outcome, desired outcome, and scope.\n- Use scope metadata when it helps decide whether a lesson belongs only to this run, the project, the workspace, a skill, memory, or an eval.\n- Avoid private data unless the user explicitly wants it captured.\n- Keep the user-facing flow short, but disclose persistence: local store, durable target file if promoted, and how it was reviewed.\n- Design for the shortest path to the user's outcome.\n- Never publish `.better-every-run\u002F` state, local lessons, event logs, or private corrections.\n\n## Workflow\n\nFor normal chat use, keep the visible flow to one command:\n\n```text\n\u002Fber fix bad outcome -> desired outcome\n```\n\nFor simple one-line preferences:\n\n```text\n\u002Fber remember simple rule\n```\n\nUse `\u002Fber report` to show what was learned, including open proposals and promotion suggestions.\n\n## Agent Implementation\n\nKeep low-level helper commands out of normal chat unless debugging, but never hide persistence. A normal answer should say whether the lesson was recorded only in `.better-every-run\u002F` or promoted to a named durable file through a lesson card.\n\nRead `references\u002Fworkflow.md` for the full workflow.\nRead `references\u002Freport-template.md` for expected chat output shape.\n\nBefore publishing or packaging, verify:\n- `.better-every-run\u002F` is excluded\n- `make test` passes\n- direct `fix --target`, `remember --target`, and `apply-memory-patch` attempts refuse without changing target files\n- lesson-card, lifecycle, and eval-fixture demos are generic and contain no private workspace paths, chat IDs, tokens, or hostnames\n- examples contain no private workspace paths, chat IDs, tokens, or hostnames\n- docs say activation is explicit-only and persistence is disclosed\n",{"name":5,"metadata":24,"description":7,"user-invocable":26},{"version":25},"0.5.5",true,"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fb\u002Fbetter-every-run",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":26},[38,41,44],{"tool":39,"command":40},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill ber",{"tool":42,"command":43},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill ber",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill ber","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fb\u002Fbetter-every-run\u002FSKILL.md",[],[50,58,65,72,79,86],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":57},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":57},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":57},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":57},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":57},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":57},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]