[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6WM81AJS3M3DZ97W7NFE19H":3,"skill-same:01M6WM81AJS3M3DZ97W7NFE19H":56},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":41,"install":42,"resources":55},"01M6WM81AJS3M3DZ97W7NFE19H","repro-twin-clone-evidence",null,"Canonical \u002Frepro workflow for copy+targeted bug repro, twin clones, evidence exports, same-symptom verdicts, and red\u002Fgreen provenance.","jleechanorg\u002Fjleechan-skills","jleechanorg","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F221404966?v=4","01M6C1VJ99XG950X1DWPEBCBGX","01M6C1VJDK5YVDNT3362RT5WSB",6,"MIT","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fworldarchitect\u002Fskills\u002Frepro-twin-clone-evidence\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28,29],"evidence","repro twin clone evidence","repro","clone","workflow","provenance","bug","green","red","copy","canonical","for","2026-11-10 10:12:30",false,"---\nname: repro-twin-clone-evidence\ndescription: Canonical \u002Frepro workflow for copy+targeted bug repro, twin clones, evidence exports, same-symptom verdicts, and red\u002Fgreen provenance.\n---\n\n# Repro evidence (canonical)\n\nThis `.claude` skill is the source of truth. Codex mirrors must point here rather than duplicating workflow rules.\n\n## 0.5. Campaign ID extraction — do this first\n\n**If the user pastes any URL matching `*\u002Fgame\u002F\u003Cid>` (e.g. `https:\u002F\u002Fmvp-site-*.run.app\u002Fgame\u002F\u003Ccampaign-id>`), extract `\u003Cid>` as the campaign ID immediately.** Go directly to §2 twin copy. Do NOT:\n- Read the PR body or comments looking for a campaign ID\n- Query Firestore indexes or list campaigns\n- Use `get_campaign_state` before copying\n- Ask the user what campaign they mean\n\nThe `\u002Fgame\u002F` path segment is the Firestore campaign ID. Take the first non-empty segment immediately after `\u002Fgame\u002F` and strip any `?`\u002F`#` suffix (handles `\u002Fgame\u002F\u003Cid>\u002F`, `\u002Fgame\u002F\u003Cid>?x=1`, `\u002Fgame\u002F\u003Cid>#frag`).\n\n## 0. Routing\n\n| User intent | Run |\n|-------------|-----|\n| `\u002Frepro`, `\u002Frepro \u003Ccampaign_id>`, or \"copy and reproduce this bug\" | Default copy + targeted repro in section 2 |\n| \"first copy read-only, second copy gets actions\" | Twin baseline + test subject in section 5 |\n| \"repro_copy\", canonical+variant replay | copy to \u003Ctest-user-email> (`--dest-email \u003Ctest-user-email>`); `scripts\u002Frepro_copy_campaign.py` only when that exact workflow is requested |\n| \"five-class\", \"level-up suite\", or all `test_level_up_class_*` | Heavy level-up suite only when explicitly requested |\n\nDo not silently substitute a broader or easier harness for the requested repro.\n\n## 1. Required environment\n\nUse real services for evidence-bearing repros. Typical env:\n\n```bash\nexport WORLDAI_DEV_MODE=true\nexport TESTING_AUTH_BYPASS=true\nexport ALLOW_TEST_AUTH_BYPASS=true\nexport MCP_TEST_MODE=real\nexport MOCK_SERVICES_MODE=false\nexport GOOGLE_APPLICATION_CREDENTIALS=\"\u003Cpath-to-service-account-key>\"\nexport WORLDAI_GOOGLE_APPLICATION_CREDENTIALS=\"$GOOGLE_APPLICATION_CREDENTIALS\"\n```\n\nFor `\u003Ctest-user-email>`, use `--dest-email \u003Ctest-user-email>` — the UID is resolved automatically by `copy_campaign.py`.\n\n## 2. Default: copy campaign + targeted bug repro\n\nGoal: create a safe Firestore copy under the test user, then reproduce one reported bug with the narrowest faithful path.\n\n1. Resolve source with `scripts\u002Fcopy_campaign.py --find-by-id \u003CCAMPAIGN_ID>`. Do not guess source UID.\n2. Copy to the test user, usually `--dest-email \u003Ctest-user-email>`.\n3. For destructive replays, create two copies: read-only baseline and test subject.\n4. Align the test subject to the reported bug instant without mutating the baseline.\n5. Replay only the exact user action\u002Finput needed for the reported bug.\n6. Export the test subject after replay with `scripts\u002Fdownload_campaign.py`.\n7. Save raw request\u002Fresponse or streaming payloads and Firestore pre\u002Fpost snapshots when the repro touches LLM\u002Fruntime state.\n\n### 2.1 First-touch state proof for stale persisted-state bugs\n\nWhen the bug is a stale persisted Firestore condition, orphaned session, legacy\nflag, migration, cleanup, or routing loop:\n\n1. Capture the copied campaign's pre-state with a direct Firestore document read\n   before any app API call that could clean, migrate, normalize, or project state.\n2. Do not call `get_campaign_state`, preview APIs, export endpoints, or UI loads\n   before the evidence-bearing action unless the claim explicitly includes those\n   first-touch paths.\n3. Run the exact production ingress being validated (for gameplay, prefer\n   `\u002Fapi\u002Fcampaigns\u002F\u003Cid>\u002Finteraction\u002Fstream`) as the first app touch.\n4. Capture post-state with another direct Firestore read.\n5. Record selected agent\u002Frouting evidence when the claim is \"not stuck on an\n   agent\" or \"routes back to gameplay\".\n\nIf a pre-action observer can mutate or seal the state, the evidence is only proof\nthat cleanup exists somewhere; it is not proof that the reported gameplay path is\nfixed.\n\n## 3. Red\u002Fgreen code provenance requirement\n\nA red repro must not run against the candidate fix codepath. Before calling any run RED, record the code\u002Fenvironment provenance:\n\n- RED replay: pre-fix checkout, pre-fix deployment, or explicitly human-approved origin-main red environment.\n- GREEN replay: candidate fix checkout\u002Fdeployment.\n- Unknown remote deployment version is not valid RED evidence. Label it `AMBIGUOUS ENVIRONMENT` until the deployed SHA\u002Fconfig is proven or the human explicitly approves it as the red lane.\n- If only the original production\u002Fsource campaign artifact shows the failure, label it `HISTORICAL RED ARTIFACT`, not a fresh red replay.\n\nDo not compare a fixed-branch replay against a fixed-branch replay and call the first one red.\n\n## 4. Same-symptom requirement (fail closed)\n\nBefore running a repro, write the exact observable bug phenotype in concrete terms:\n\n- Source campaign \u002F URL and source account.\n- Exact scene \u002F turn \u002F input being replayed.\n- Exact user-visible symptom required for success.\n- Prior artifact(s) that must be repeated, omitted, contradicted, or otherwise reproduced.\n- Evidence that would falsify the repro claim.\n\nDo not call a related internal signal a reproduction unless the same observable symptom appears in the copied\u002Fnew run.\n\nExamples:\n\n- If the reported bug is \"old scene text repeated\", a successful repro must show visible repeated old narrative in the new copied campaign, with earlier source scene\u002Fdoc IDs and matching text spans.\n- A stale `action_resolution.player_input`, stale location, wrong planning block, or wrong narrative thread is only a related finding unless the reported user-visible repeated narrative also appears.\n- If the new run produces fresh prose from stale context, label it `RELATED STALE-CONTEXT FAILURE`, not `ORIGINAL BUG REPRO`.\n- If the new run has the right internal stale field but not the user-visible symptom, label it `NON-REPRO FOR ORIGINAL PHENOTYPE`.\n\nFor every claimed repro, add a verdict table:\n\n| Original required symptom | New copied-run observation | Evidence file \u002F doc ID | Verdict |\n|---------------------------|----------------------------|------------------------|---------|\n| | | | `REPRO` \u002F `RELATED` \u002F `NON-REPRO` |\n\nOnly `REPRO` satisfies `\u002Frepro`. `RELATED` and `NON-REPRO` are useful evidence, but they do not complete the repro task and must not be described as the original bug reproduced.\n\n## 5. Twin baseline + test subject\n\nWhen the first copy must stay read-only:\n\n1. Create two independent copies with `scripts\u002Fcopy_campaign.py --find-by-id \u003CSOURCE>`.\n2. Name one `baseline read-only` and one `test subject`.\n3. Never send actions, god-mode edits, or destructive state changes to the baseline.\n4. Perform alignment, deletes, state resets, and replay only on the test subject.\n5. Export both only when comparison is needed; otherwise export the test subject plus raw evidence.\n\n## 6. Save state after repro\n\nExport the post-replay state and execution artifacts to a discoverable directory on the dedicated Scratch volume resolved dynamically via the canonical scratch skill the `scratch-space` skill (`diskm scratch-new \u003Crepo-path> \u003Cpurpose> --kind evidence` or `${CLAUDE_HOME:-$HOME\u002F.claude}\u002Fskills\u002Fscratch-space\u002Fscripts\u002Fscratch-dir.sh`):\n\nNote: The inline subcommand below uses `copy_campaign.py` with `--format json` to perform an early-exit email-to-UID lookup (it exits immediately and does not perform a copy).\n\n```bash\n# Resolve canonical evidence directory via ${CLAUDE_HOME:-$HOME\u002F.claude}\u002Fskills\u002Fscratch-space\u002FSKILL.md\nEVIDENCE_DIR=\"$(${CLAUDE_HOME:-$HOME\u002F.claude}\u002Fskills\u002Fscratch-space\u002Fscripts\u002Fscratch-dir.sh \"\u003Crepo-name>\u002Frepro-exports\u002F\u003Cslug>\")\"\n# Or allocate a managed lease:\n# EVIDENCE_DIR=\"$(diskm scratch-new \u003Crepo-path> repro-export --kind evidence)\"\n\n.\u002Fvenv\u002Fbin\u002Fpython scripts\u002Fdownload_campaign.py \\\n  --uid \"$(.\u002Fvenv\u002Fbin\u002Fpython scripts\u002Fcopy_campaign.py --dest-email \u003Ctest-user-email> --format json 2>\u002Fdev\u002Fnull | python3 -c \"import sys, json; print(json.load(sys.stdin)['dest_uid'])\")\" \\\n  --campaign-id \u003CTEST_CAMPAIGN_ID> \\\n  --output-dir \"$EVIDENCE_DIR\" \\\n  --format txt\n```\n\nOr, if you already know the resolved UID from the copy step output, pass it directly via `--uid \u003CUID>` (or utilize a dedicated resolver script like `resolve_uid.py` in the future for clearer maintenance).\n\n## 7. Checklist\n\n| Step | Done? |\n|------|-------|\n| Source campaign resolved with `--find-by-id` | |\n| Red\u002Fgreen provenance recorded | |\n| Same-symptom criteria written before replay | |\n| Baseline\u002Ftest clone separation preserved | |\n| Exact input\u002Faction replayed | |\n| First-touch direct Firestore pre-state captured for stale persisted-state bugs | |\n| Production ingress under test was the first app API touch | |\n| Full campaign export saved | |\n| Raw captures\u002Fsnapshots saved | |\n| Verdict table filled with `REPRO`, `RELATED`, or `NON-REPRO` | |\n","# Repro evidence (canonical)\n\nThis `.claude` skill is the source of truth. Codex mirrors must point here rather than duplicating workflow rules.\n\n## 0.5. Campaign ID extraction — do this first\n\n**If the user pastes any URL matching `*\u002Fgame\u002F\u003Cid>` (e.g. `https:\u002F\u002Fmvp-site-*.run.app\u002Fgame\u002F\u003Ccampaign-id>`), extract `\u003Cid>` as the campaign ID immediately.** Go directly to §2 twin copy. Do NOT:\n- Read the PR body or comments looking for a campaign ID\n- Query Firestore indexes or list campaigns\n- Use `get_campaign_state` before copying\n- Ask the user what campaign they mean\n\nThe `\u002Fgame\u002F` path segment is the Firestore campaign ID. Take the first non-empty segment immediately after `\u002Fgame\u002F` and strip any `?`\u002F`#` suffix (handles `\u002Fgame\u002F\u003Cid>\u002F`, `\u002Fgame\u002F\u003Cid>?x=1`, `\u002Fgame\u002F\u003Cid>#frag`).\n\n## 0. Routing\n\n| User intent | Run |\n|-------------|-----|\n| `\u002Frepro`, `\u002Frepro \u003Ccampaign_id>`, or \"copy and reproduce this bug\" | Default copy + targeted repro in section 2 |\n| \"first copy read-only, second copy gets actions\" | Twin baseline + test subject in section 5 |\n| \"repro_copy\", canonical+variant replay | copy to \u003Ctest-user-email> (`--dest-email \u003Ctest-user-email>`); `scripts\u002Frepro_copy_campaign.py` only when that exact workflow is requested |\n| \"five-class\", \"level-up suite\", or all `test_level_up_class_*` | Heavy level-up suite only when explicitly requested |\n\nDo not silently substitute a broader or easier harness for the requested repro.\n\n## 1. Required environment\n\nUse real services for evidence-bearing repros. Typical env:\n\n```bash\nexport WORLDAI_DEV_MODE=true\nexport TESTING_AUTH_BYPASS=true\nexport ALLOW_TEST_AUTH_BYPASS=true\nexport MCP_TEST_MODE=real\nexport MOCK_SERVICES_MODE=false\nexport GOOGLE_APPLICATION_CREDENTIALS=\"\u003Cpath-to-service-account-key>\"\nexport WORLDAI_GOOGLE_APPLICATION_CREDENTIALS=\"$GOOGLE_APPLICATION_CREDENTIALS\"\n```\n\nFor `\u003Ctest-user-email>`, use `--dest-email \u003Ctest-user-email>` — the UID is resolved automatically by `copy_campaign.py`.\n\n## 2. Default: copy campaign + targeted bug repro\n\nGoal: create a safe Firestore copy under the test user, then reproduce one reported bug with the narrowest faithful path.\n\n1. Resolve source with `scripts\u002Fcopy_campaign.py --find-by-id \u003CCAMPAIGN_ID>`. Do not guess source UID.\n2. Copy to the test user, usually `--dest-email \u003Ctest-user-email>`.\n3. For destructive replays, create two copies: read-only baseline and test subject.\n4. Align the test subject to the reported bug instant without mutating the baseline.\n5. Replay only the exact user action\u002Finput needed for the reported bug.\n6. Export the test subject after replay with `scripts\u002Fdownload_campaign.py`.\n7. Save raw request\u002Fresponse or streaming payloads and Firestore pre\u002Fpost snapshots when the repro touches LLM\u002Fruntime state.\n\n### 2.1 First-touch state proof for stale persisted-state bugs\n\nWhen the bug is a stale persisted Firestore condition, orphaned session, legacy\nflag, migration, cleanup, or routing loop:\n\n1. Capture the copied campaign's pre-state with a direct Firestore document read\n   before any app API call that could clean, migrate, normalize, or project state.\n2. Do not call `get_campaign_state`, preview APIs, export endpoints, or UI loads\n   before the evidence-bearing action unless the claim explicitly includes those\n   first-touch paths.\n3. Run the exact production ingress being validated (for gameplay, prefer\n   `\u002Fapi\u002Fcampaigns\u002F\u003Cid>\u002Finteraction\u002Fstream`) as the first app touch.\n4. Capture post-state with another direct Firestore read.\n5. Record selected agent\u002Frouting evidence when the claim is \"not stuck on an\n   agent\" or \"routes back to gameplay\".\n\nIf a pre-action observer can mutate or seal the state, the evidence is only proof\nthat cleanup exists somewhere; it is not proof that the reported gameplay path is\nfixed.\n\n## 3. Red\u002Fgreen code provenance requirement\n\nA red repro must not run against the candidate fix codepath. Before calling any run RED, record the code\u002Fenvironment provenance:\n\n- RED replay: pre-fix checkout, pre-fix deployment, or explicitly human-approved origin-main red environment.\n- GREEN replay: candidate fix checkout\u002Fdeployment.\n- Unknown remote deployment version is not valid RED evidence. Label it `AMBIGUOUS ENVIRONMENT` until the deployed SHA\u002Fconfig is proven or the human explicitly approves it as the red lane.\n- If only the original production\u002Fsource campaign artifact shows the failure, label it `HISTORICAL RED ARTIFACT`, not a fresh red replay.\n\nDo not compare a fixed-branch replay against a fixed-branch replay and call the first one red.\n\n## 4. Same-symptom requirement (fail closed)\n\nBefore running a repro, write the exact observable bug phenotype in concrete terms:\n\n- Source campaign \u002F URL and source account.\n- Exact scene \u002F turn \u002F input being replayed.\n- Exact user-visible symptom required for success.\n- Prior artifact(s) that must be repeated, omitted, contradicted, or otherwise reproduced.\n- Evidence that would falsify the repro claim.\n\nDo not call a related internal signal a reproduction unless the same observable symptom appears in the copied\u002Fnew run.\n\nExamples:\n\n- If the reported bug is \"old scene text repeated\", a successful repro must show visible repeated old narrative in the new copied campaign, with earlier source scene\u002Fdoc IDs and matching text spans.\n- A stale `action_resolution.player_input`, stale location, wrong planning block, or wrong narrative thread is only a related finding unless the reported user-visible repeated narrative also appears.\n- If the new run produces fresh prose from stale context, label it `RELATED STALE-CONTEXT FAILURE`, not `ORIGINAL BUG REPRO`.\n- If the new run has the right internal stale field but not the user-visible symptom, label it `NON-REPRO FOR ORIGINAL PHENOTYPE`.\n\nFor every claimed repro, add a verdict table:\n\n| Original required symptom | New copied-run observation | Evidence file \u002F doc ID | Verdict |\n|---------------------------|----------------------------|------------------------|---------|\n| | | | `REPRO` \u002F `RELATED` \u002F `NON-REPRO` |\n\nOnly `REPRO` satisfies `\u002Frepro`. `RELATED` and `NON-REPRO` are useful evidence, but they do not complete the repro task and must not be described as the original bug reproduced.\n\n## 5. Twin baseline + test subject\n\nWhen the first copy must stay read-only:\n\n1. Create two independent copies with `scripts\u002Fcopy_campaign.py --find-by-id \u003CSOURCE>`.\n2. Name one `baseline read-only` and one `test subject`.\n3. Never send actions, god-mode edits, or destructive state changes to the baseline.\n4. Perform alignment, deletes, state resets, and replay only on the test subject.\n5. Export both only when comparison is needed; otherwise export the test subject plus raw evidence.\n\n## 6. Save state after repro\n\nExport the post-replay state and execution artifacts to a discoverable directory on the dedicated Scratch volume resolved dynamically via the canonical scratch skill the `scratch-space` skill (`diskm scratch-new \u003Crepo-path> \u003Cpurpose> --kind evidence` or `${CLAUDE_HOME:-$HOME\u002F.claude}\u002Fskills\u002Fscratch-space\u002Fscripts\u002Fscratch-dir.sh`):\n\nNote: The inline subcommand below uses `copy_campaign.py` with `--format json` to perform an early-exit email-to-UID lookup (it exits immediately and does not perform a copy).\n\n```bash\n# Resolve canonical evidence directory via ${CLAUDE_HOME:-$HOME\u002F.claude}\u002Fskills\u002Fscratch-space\u002FSKILL.md\nEVIDENCE_DIR=\"$(${CLAUDE_HOME:-$HOME\u002F.claude}\u002Fskills\u002Fscratch-space\u002Fscripts\u002Fscratch-dir.sh \"\u003Crepo-name>\u002Frepro-exports\u002F\u003Cslug>\")\"\n# Or allocate a managed lease:\n# EVIDENCE_DIR=\"$(diskm scratch-new \u003Crepo-path> repro-export --kind evidence)\"\n\n.\u002Fvenv\u002Fbin\u002Fpython scripts\u002Fdownload_campaign.py \\\n  --uid \"$(.\u002Fvenv\u002Fbin\u002Fpython scripts\u002Fcopy_campaign.py --dest-email \u003Ctest-user-email> --format json 2>\u002Fdev\u002Fnull | python3 -c \"import sys, json; print(json.load(sys.stdin)['dest_uid'])\")\" \\\n  --campaign-id \u003CTEST_CAMPAIGN_ID> \\\n  --output-dir \"$EVIDENCE_DIR\" \\\n  --format txt\n```\n\nOr, if you already know the resolved UID from the copy step output, pass it directly via `--uid \u003CUID>` (or utilize a dedicated resolver script like `resolve_uid.py` in the future for clearer maintenance).\n\n## 7. Checklist\n\n| Step | Done? |\n|------|-------|\n| Source campaign resolved with `--find-by-id` | |\n| Red\u002Fgreen provenance recorded | |\n| Same-symptom criteria written before replay | |\n| Baseline\u002Ftest clone separation preserved | |\n| Exact input\u002Faction replayed | |\n| First-touch direct Firestore pre-state captured for stale persisted-state bugs | |\n| Production ingress under test was the first app API touch | |\n| Full campaign export saved | |\n| Raw captures\u002Fsnapshots saved | |\n| Verdict table filled with `REPRO`, `RELATED`, or `NON-REPRO` | |\n",{"name":5,"description":7},"main","8144f00ebafc4306264c63239e4b9fa42e48a90e","plugins\u002Fworldarchitect\u002Fskills\u002Frepro-twin-clone-evidence",0,"https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills","https:\u002F\u002Fgithub.com\u002Fjleechanorg","2026-11-11 22:19:36",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add jleechanorg\u002Fjleechan-skills --skill repro-twin-clone-evidence",{"tool":48,"command":49},"bunx","bunx skills add jleechanorg\u002Fjleechan-skills --skill repro-twin-clone-evidence",{"tool":51,"command":52},"pnpm","pnpm dlx skills add jleechanorg\u002Fjleechan-skills --skill repro-twin-clone-evidence","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fworldarchitect\u002Fskills\u002Frepro-twin-clone-evidence\u002FSKILL.md",true,[],[57,75,95,109,121,137],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":30},"01M716Y5MTJ6GYJZ2ATXCJK8G4","instinct","Use when the user invokes \u002Finstinct or \u002Fin, or asks to \"message Instinct\", \"ask Instinct\", \"tell Instinct\", \"check Instinct\", or read replies from the configured peer assistant. iMessage first, WhatsApp Web as fallback.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Finstinct\u002FSKILL.md",[],[59,64,65,66,67,68,69,70,71,72,73,74],"user","when","replies","check","use","identity","whatsapp","gmail","read","message","ask",{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":86,"publishedAt":30},"01M716Y4HF7FVVMJSA2CCVN5VF","hr","Compatibility alias for history-resume; produce the same fresh-state, provenance-aware resume briefing.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhr\u002FSKILL.md",[81],{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[77,87,88,23,29,89,90,91,92,93,94],"resume","compatibility","history","produce","alias","briefing","state","fresh",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":102,"publishedAt":30},"01M716Y1FFNFKFJYYKF8HQA6T8","history-resume","Resume briefing for the current repository branch or worktree using fresh state and admitted history sources.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhistory-resume\u002FSKILL.md",[101],{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},[89,87,103,104,64,105,92,106,29,107,108,93,94],"history resume","branch","analysis","repository","worktree","sources",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":30},"01M716XWXJ8EPHK4RH9T14TR85","grok","Alias for the canonical grokbot browser conversation workflow; \u002Fgrok talks to the Grok bot the same way \u002Fdot talks to Dot.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgrok\u002FSKILL.md",[],[111,116,117,22,29,28,91,118,119,120],"dot","bot","conversation","browser","grokbot",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":30},"01M70N9Q07DTE0EW5KFXMMMSJ0","codexa-bench","Compare `codexa` and normal `codex` on a fair split of comparable work by default; use `--strict` for duplicate runs of the exact same task.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcodexa-bench\u002FSKILL.md",[],[128,129,130,68,131,29,132,133,134,135,136],"codexa bench","work","split","default","duplicate","task","compare","normal","codex",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":141,"licenseFileUrl":142,"sourceHtmlUrl":143,"categories":144,"keywords":156,"publishedAt":30},"01M6C24S2X60SP8BBFGAEKPEGW","frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML\u002FCSS layouts, or when styling\u002Fbeautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ffrontend-design\u002FSKILL.md",[145,150,153],{"categoryNo":146,"categoryName":147,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",{"categoryNo":151,"categoryName":152,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":154,"categoryName":155,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000032","设计师",[157,158,159,68,160,161,162,64,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,65,181],"frontend","design","frontend design","generic","ui design","react","html","components","code","artifacts","ui","aesthetics","Production","web components","landing","applications","quality","web","css","create","examples","with","react components","web ui","pages"]