[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CW0ZGX14X9PMYBFKH3CECP":3,"skill-same:01M7CW0ZGX14X9PMYBFKH3CECP":45},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7CW0ZGX14X9PMYBFKH3CECP","dsh-archive-agent-notes",null,"Use when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, classifies implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting fallacy, and applies the frozen archived\u002F{kind} triplet and manifest rules.","ryasrk\u002Fdsh-expert-agents","ryasrk","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F115061102?v=4","01M7CW079PK1VJJZPP5KXWFRXN","Ryas Rafi Karim","01M7CW07AKNEJV8913PZB163JK",0,"MIT","https:\u002F\u002Fgithub.com\u002Fryasrk\u002Fdsh-expert-agents\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fdsh-archive-agent-notes\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dsh-archive-agent-notes\ndescription: Use when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, classifies implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting fallacy, and applies the frozen archived\u002F{kind} triplet and manifest rules.\n---\n\n# Archive DeepSeek Harness Agent Notes\n\nReduce the active decision corpus without erasing history that can still guide work. Judge every note semantically; word count and age are discovery aids, never archive criteria.\n\n## Read the contracts\n\nRead [the Agent Note rules](..\u002F..\u002Fnotes\u002FREADME.md), [the archive instructions](..\u002F..\u002Fnotes\u002Farchived\u002FAGENTS.md), and the applicable active lifecycle instructions before classifying. Use current code, configuration, package docs, generated catalogs, newer Agent Notes, and inbound links to establish whether a rationale still owns or constrains anything.\n\n## Check supersession when adding a note\n\nEvery new Agent Note triggers a scoped audit of active notes covering the same decision, mechanism, or rejected alternative. Classify each full or partial supersession while writing the new note: archive qualifying implemented triplets in the same PR, retain and cross-link partial supersessions or independently useful rationale, reject obsolete proposals, and delete rejected notes that no longer prevent a plausible mistake. Apply the Agent Note consolidation rule when the new owner absorbs every unique proposition; do not defer a known match to a later corpus audit.\n\n## Classify by future value\n\nApply these lifecycle-specific outcomes:\n\n- **Implemented — keep active:** retain a note when its rationale, alternatives, negative guarantees, durable\u002Fwire semantics, ownership boundary, security rule, or reintroduction condition is likely to guide a future change. Length does not matter.\n- **Implemented — archive:** archive a note when the shipped decision is complete and its body is unlikely to guide future work, such as one-off UI chrome, a narrow adapter, a minor closed bug, superseded implementation detail, or process history whose current behavior is obvious elsewhere.\n- **Proposed — never archive:** keep a live proposal active; if it is no longer worth pursuing, reject it with an honest reason and satisfy the rejected lifecycle format.\n- **Rejected — keep only as a guardrail:** retain a rejection only when the losing proposal remains a tempting, meaningful mistake and the note explains why it loses.\n- **Rejected — delete:** delete the whole triplet when the rejected idea is obsolete, superseded, no longer plausible, or unlikely to prevent re-litigation. Repair or delete inbound links.\n\nDo not archive toward a quota. Inspect every note in scope, classify analogous groups under one principle, use best judgment for close cases, and record genuinely borderline decisions for the handoff.\n\n## Calibrated examples\n\nThese examples set the bar; the word counts demonstrate that size is not the test.\n\nArchive implemented notes such as:\n\n- collapsed sidebar control rail — 533 words: closed, minor UI behavior;\n- Commander argument adapter — 1,498 words: substantial implementation detail with little future design leverage;\n- documentation graph atlas — 920 words: completed documentation machinery whose current generators are authoritative.\n\nKeep implemented notes such as:\n\n- event-sourced sessions — 248 words: foundational authority and durability boundary;\n- single Harness-home resolver — 596 words: cross-product ownership rule;\n- project session directories — 628 words: durable storage and identity policy;\n- parallel pre-push gates — 400 words: borderline, but still guides gate scheduling and resource tuning;\n- dropped image content block — 334 words: keep until multimodal support lands, because it states the coordinated reintroduction condition.\n\nFor rejected notes:\n\n- keep folding the compaction package split — 426 words: the temptation to merge the packages remains meaningful;\n- delete streaming workflow progress through tool calls — 972 words: its ACP\u002FUI premise is obsolete;\n- delete dropping ACP terminal metadata — 362 words: the later automation-only ACP decision resolved the question.\n\n## Archive one implemented triplet\n\n1. Move the complete `foo.md`, `foo.zh.md`, and `foo.i18n.yaml` triplet from `implemented\u002F\u003Ckind>\u002F` to `archived\u002F\u003Ckind>\u002F`; `implemented` is deliberately absent from the archive path.\n2. Make no body edits. Insert only `Archived: YYYY-MM-DD` immediately below `Status: implemented` in both language files, using the archival date and the same value on both sides.\n3. Re-record the sidecar hashes mechanically for the two metadata-only edits. Do not translate, reformat, update facts, or repair links inside the note.\n4. Search for inbound links from active prose. Redirect them to current authority, retarget them to the archived path only when the historical snapshot is intentionally cited, or delete them. Never verify or repair links out of the archived note.\n5. Run `pnpm run verify-archived-agent-notes --write`. Its append-only mode first proves every existing seal still matches, then adds only the new triplet hashes. Run the normal verifier afterward.\n\nAfter the triplet is sealed, never edit, move, translate, reformat, or delete it. Archived notes remain valid inbound-link targets but are historical snapshots, not authority for current behavior.\n\n## Validate and report\n\nRun the archive verifier's focused test, `pnpm run verify-archived-agent-notes`, `pnpm run doc-sync`, `pnpm run lint`, and `git diff --check`; select any additional evidence through [dsh-pre-push-checks](..\u002Fdsh-pre-push-checks\u002FSKILL.md).\n\nReport active implemented notes kept, implemented notes archived, rejected notes kept\u002Fdeleted, proposed notes rejected if any, and every genuinely borderline case with its word count and chosen outcome. Do not claim archived outbound links are valid: the archive verifier intentionally never checks them.\n","# Archive DeepSeek Harness Agent Notes\n\nReduce the active decision corpus without erasing history that can still guide work. Judge every note semantically; word count and age are discovery aids, never archive criteria.\n\n## Read the contracts\n\nRead [the Agent Note rules](..\u002F..\u002Fnotes\u002FREADME.md), [the archive instructions](..\u002F..\u002Fnotes\u002Farchived\u002FAGENTS.md), and the applicable active lifecycle instructions before classifying. Use current code, configuration, package docs, generated catalogs, newer Agent Notes, and inbound links to establish whether a rationale still owns or constrains anything.\n\n## Check supersession when adding a note\n\nEvery new Agent Note triggers a scoped audit of active notes covering the same decision, mechanism, or rejected alternative. Classify each full or partial supersession while writing the new note: archive qualifying implemented triplets in the same PR, retain and cross-link partial supersessions or independently useful rationale, reject obsolete proposals, and delete rejected notes that no longer prevent a plausible mistake. Apply the Agent Note consolidation rule when the new owner absorbs every unique proposition; do not defer a known match to a later corpus audit.\n\n## Classify by future value\n\nApply these lifecycle-specific outcomes:\n\n- **Implemented — keep active:** retain a note when its rationale, alternatives, negative guarantees, durable\u002Fwire semantics, ownership boundary, security rule, or reintroduction condition is likely to guide a future change. Length does not matter.\n- **Implemented — archive:** archive a note when the shipped decision is complete and its body is unlikely to guide future work, such as one-off UI chrome, a narrow adapter, a minor closed bug, superseded implementation detail, or process history whose current behavior is obvious elsewhere.\n- **Proposed — never archive:** keep a live proposal active; if it is no longer worth pursuing, reject it with an honest reason and satisfy the rejected lifecycle format.\n- **Rejected — keep only as a guardrail:** retain a rejection only when the losing proposal remains a tempting, meaningful mistake and the note explains why it loses.\n- **Rejected — delete:** delete the whole triplet when the rejected idea is obsolete, superseded, no longer plausible, or unlikely to prevent re-litigation. Repair or delete inbound links.\n\nDo not archive toward a quota. Inspect every note in scope, classify analogous groups under one principle, use best judgment for close cases, and record genuinely borderline decisions for the handoff.\n\n## Calibrated examples\n\nThese examples set the bar; the word counts demonstrate that size is not the test.\n\nArchive implemented notes such as:\n\n- collapsed sidebar control rail — 533 words: closed, minor UI behavior;\n- Commander argument adapter — 1,498 words: substantial implementation detail with little future design leverage;\n- documentation graph atlas — 920 words: completed documentation machinery whose current generators are authoritative.\n\nKeep implemented notes such as:\n\n- event-sourced sessions — 248 words: foundational authority and durability boundary;\n- single Harness-home resolver — 596 words: cross-product ownership rule;\n- project session directories — 628 words: durable storage and identity policy;\n- parallel pre-push gates — 400 words: borderline, but still guides gate scheduling and resource tuning;\n- dropped image content block — 334 words: keep until multimodal support lands, because it states the coordinated reintroduction condition.\n\nFor rejected notes:\n\n- keep folding the compaction package split — 426 words: the temptation to merge the packages remains meaningful;\n- delete streaming workflow progress through tool calls — 972 words: its ACP\u002FUI premise is obsolete;\n- delete dropping ACP terminal metadata — 362 words: the later automation-only ACP decision resolved the question.\n\n## Archive one implemented triplet\n\n1. Move the complete `foo.md`, `foo.zh.md`, and `foo.i18n.yaml` triplet from `implemented\u002F\u003Ckind>\u002F` to `archived\u002F\u003Ckind>\u002F`; `implemented` is deliberately absent from the archive path.\n2. Make no body edits. Insert only `Archived: YYYY-MM-DD` immediately below `Status: implemented` in both language files, using the archival date and the same value on both sides.\n3. Re-record the sidecar hashes mechanically for the two metadata-only edits. Do not translate, reformat, update facts, or repair links inside the note.\n4. Search for inbound links from active prose. Redirect them to current authority, retarget them to the archived path only when the historical snapshot is intentionally cited, or delete them. Never verify or repair links out of the archived note.\n5. Run `pnpm run verify-archived-agent-notes --write`. Its append-only mode first proves every existing seal still matches, then adds only the new triplet hashes. Run the normal verifier afterward.\n\nAfter the triplet is sealed, never edit, move, translate, reformat, or delete it. Archived notes remain valid inbound-link targets but are historical snapshots, not authority for current behavior.\n\n## Validate and report\n\nRun the archive verifier's focused test, `pnpm run verify-archived-agent-notes`, `pnpm run doc-sync`, `pnpm run lint`, and `git diff --check`; select any additional evidence through [dsh-pre-push-checks](..\u002Fdsh-pre-push-checks\u002FSKILL.md).\n\nReport active implemented notes kept, implemented notes archived, rejected notes kept\u002Fdeleted, proposed notes rejected if any, and every genuinely borderline case with its word count and chosen outcome. Do not claim archived outbound links are valid: the archive verifier intentionally never checks them.\n",{"name":5,"description":7},"main","b608340412f02546f13b1b29976daf33bec72bef","assets\u002Fskills\u002Fdsh-archive-agent-notes","https:\u002F\u002Fgithub.com\u002Fryasrk\u002Fdsh-expert-agents","https:\u002F\u002Fgithub.com\u002Fryasrk","Passionate about Machine Learning, Deep Learning, and LLMs. Skilled in Computer Vision, NLP, and AI model development.","2026-09-29 12:47:36",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add ryasrk\u002Fdsh-expert-agents --skill dsh-archive-agent-notes",{"tool":37,"command":38},"bunx","bunx skills add ryasrk\u002Fdsh-expert-agents --skill dsh-archive-agent-notes",{"tool":40,"command":41},"pnpm","pnpm dlx skills add ryasrk\u002Fdsh-expert-agents --skill dsh-archive-agent-notes","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fryasrk\u002Fdsh-expert-agents\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fdsh-archive-agent-notes\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7CW5A9FJK1C6BQKKMYHKWBD","writing-shape","Writing, exploit: shape raw material into an article, paragraph by paragraph.","https:\u002F\u002Fgithub.com\u002Fryasrk\u002Fdsh-expert-agents\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fwriting-shape\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7CW58T8BYGMCTKQW60DFM7K","writing-fragments","Writing, explore: mine raw fragments, no structure yet.","https:\u002F\u002Fgithub.com\u002Fryasrk\u002Fdsh-expert-agents\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fwriting-fragments\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7CW56PXKJ31Y8AGJ31W1SHT","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fryasrk\u002Fdsh-expert-agents\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7CW54P3DQJKVA9GBQBMXE00","writing-beats","Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.","https:\u002F\u002Fgithub.com\u002Fryasrk\u002Fdsh-expert-agents\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fwriting-beats\u002FSKILL.md",[],[],{"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":19},"01M7CW50RQRS31BHTKJ7JZM21A","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fryasrk\u002Fdsh-expert-agents\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7CW4Y3E85C06AZD2VANK40Q","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fryasrk\u002Fdsh-expert-agents\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[]]