[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6K5P0MCNF1NM1XVEE8TC7SN":3,"skill-same:01M6K5P0MCNF1NM1XVEE8TC7SN":64},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":46,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":49,"updatedAt":50,"install":51,"resources":63},"01M6K5P0MCNF1NM1XVEE8TC7SN","learn",null,"Use when you want to review the current session for skills that misfired (skipped, invoked-but-ignored, or triggered user corrections) and update them — scans the active transcript, classifies findings, and delegates fixes to \u002Flets-make-a-skill with per-finding approval","laurac8r\u002Fclaude-damn","laurac8r","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F23003243?v=4","01M6K5HCAJJR4Q5BCBRRZF8E5D","Laura Kaminskiy","01M6K5HCEQRFFJFK32A0VR7AS3",3,"MIT","https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Flearn\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"but","fixes","for","delegates","true","you","with","make","active","review","use","approval","session","user","transcript","update","2026-11-10 10:12:30",false,"---\nname: learn\ndescription:\n   \"Use when you want to review the current session for skills that misfired\n   (skipped, invoked-but-ignored, or triggered user corrections) and update them\n   — scans the active transcript, classifies findings, and delegates fixes to\n   \u002Flets-make-a-skill with per-finding approval\"\nuser-invocable: true\n---\n\n# Learn From This Session\n\nInvoked at the end of (or partway through) a session. `\u002Flearn` reviews the\nactive transcript, identifies skills that **misfired**, and delegates fixes to\n`\u002Flets-make-a-skill` — with a per-finding approval gate between detection and\nedit.\n\n**First action:** Invoke `\u002Flisten` with this argument:\n\n> `\u002Flets-make-a-skill update any skill that misfired in the current session, following the analysis playbook below.`\n\n`\u002Flisten`'s enforcement layer guarantees `\u002Flets-make-a-skill` is invoked for\neach approved finding. The playbook below is the work content `\u002Flisten` carries\nforward.\n\n## Analysis Playbook\n\n### 1. Locate the transcript\n\nCurrent session = most recently modified `*.jsonl` file in\n`~\u002F.claude\u002Fprojects\u002F\u003Cslug>\u002F`, where `\u003Cslug>` is the current working directory\nwith `\u002F` replaced by `-`, then any leading `-` stripped.\n\nIf the directory is missing or the newest file is ambiguous (multiple files\ntouched within the last second), ask the user to confirm or paste the session\nID.\n\n### 2. Scan for misfire signals\n\nReview the transcript in two passes:\n\n1. For each `Skill` tool-call in the transcript, inspect the invocation, its\n   output, and the next ~3 user\u002Fassistant turns.\n2. Also scan the surrounding user requests and Claude actions for places where a\n   skill _should_ have been invoked based on its description, but was never\n   called at all — this is how **Skipped** findings surface, since by definition\n   they leave no tool-call to iterate over.\n\n| Signal                                           | What it looks like                                                                                                                    |\n| ------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------- |\n| **Skipped**                                      | A skill's description clearly matched the task, but the skill was never invoked                                                       |\n| **Invoked-but-ignored**                          | The skill was invoked, and Claude's next action directly contradicts its instructions                                                 |\n| **User correction**                              | User writes \"wait\", \"hold up\", \"hmm\", \"double check\", \"no\", \"don't\", \"stop\", \"that's wrong\", \"why did you…\" within 3 turns of a skill |\n| **User invokes another skill to course-correct** | User invokes another skill to double-check output, logic, consistency, security, actions, or tool use in this session                 |\n| **Discarded output**                             | User reverts or overrides the artifact the skill produced                                                                             |\n| **Hook-rejection loop**                          | A blocked action is retried after rejection — a skill should have prevented the first try                                             |\n| **Re-prompt**                                    | User restates or clarifies the same request — skill interpreted it wrongly                                                            |\n\nAlso capture the **rationalization verbatim** — the sentence Claude used to\njustify the misfire. `\u002Flets-make-a-skill` needs this to add a specific counter.\n\n### 3. Classify each finding\n\n- **Misfire** — the skill's text is wrong, incomplete, or its triggers don't\n  match the scenario. Fixable via `\u002Flets-make-a-skill`.\n- **Preference shift** — the skill followed its text faithfully; the user simply\n  wants different behavior going forward. Report separately; **do not\n  auto-update**.\n\nDecision rule: \"would a careful reading of this skill have produced the user's\npreferred behavior?\" Yes → preference shift. No → misfire.\n\n### 4. Present findings\n\nOne row per finding:\n\n```\nskill · signal · evidence (line refs) · classification · proposed-fix\n```\n\nFor each row ask: **approve**, **skip**, or **reclassify**.\n\n### 5. Apply approved fixes\n\nFor each approved misfire, invoke `\u002Flets-make-a-skill` with:\n\n- the skill's file path,\n- the observed rationalization\u002Fgap (verbatim),\n- enough context for a pressure scenario.\n\n`\u002Flets-make-a-skill` carries its own TDD discipline — do not bypass it.\n\n### 6. Update scope\n\nEdits are allowed in:\n\n- `~\u002F.claude\u002Fskills\u002F` (user skills)\n- `\u003Ccwd>\u002F.claude\u002Fskills\u002F` (project skills, if the directory exists)\n\nPlugin-cache skills under `~\u002F.claude\u002Fplugins\u002Fcache\u002F**` are **read-only** —\nplugin updates overwrite local edits. If a misfire lives there, surface the\nfinding but do not edit.\n\n## What This Skill Does NOT Do\n\n- Does not edit skills in the plugin cache.\n- Does not apply fixes without per-finding approval.\n- Does not analyze sessions other than the current one.\n- Does not treat every user correction as a skill bug — preference shifts are\n  filtered out and reported separately.\n- Does not summarize or moralize about Claude's performance — output is a\n  findings table, not a retrospective.\n\n## Edge Cases\n\n- **No skills used** → report \"no skill invocations found\" and exit.\n- **All skills used correctly** → report \"no misfires detected\".\n- **All findings are preference shifts** → surface as a design-question list, do\n  not call `\u002Flets-make-a-skill`.\n- **Misfire lives in plugin cache** → surface, note it cannot be edited, suggest\n  filing upstream.\n- **Transcript unreadable \u002F JSONL corrupt** → report the error; do not proceed\n  blindly.\n","# Learn From This Session\n\nInvoked at the end of (or partway through) a session. `\u002Flearn` reviews the\nactive transcript, identifies skills that **misfired**, and delegates fixes to\n`\u002Flets-make-a-skill` — with a per-finding approval gate between detection and\nedit.\n\n**First action:** Invoke `\u002Flisten` with this argument:\n\n> `\u002Flets-make-a-skill update any skill that misfired in the current session, following the analysis playbook below.`\n\n`\u002Flisten`'s enforcement layer guarantees `\u002Flets-make-a-skill` is invoked for\neach approved finding. The playbook below is the work content `\u002Flisten` carries\nforward.\n\n## Analysis Playbook\n\n### 1. Locate the transcript\n\nCurrent session = most recently modified `*.jsonl` file in\n`~\u002F.claude\u002Fprojects\u002F\u003Cslug>\u002F`, where `\u003Cslug>` is the current working directory\nwith `\u002F` replaced by `-`, then any leading `-` stripped.\n\nIf the directory is missing or the newest file is ambiguous (multiple files\ntouched within the last second), ask the user to confirm or paste the session\nID.\n\n### 2. Scan for misfire signals\n\nReview the transcript in two passes:\n\n1. For each `Skill` tool-call in the transcript, inspect the invocation, its\n   output, and the next ~3 user\u002Fassistant turns.\n2. Also scan the surrounding user requests and Claude actions for places where a\n   skill _should_ have been invoked based on its description, but was never\n   called at all — this is how **Skipped** findings surface, since by definition\n   they leave no tool-call to iterate over.\n\n| Signal                                           | What it looks like                                                                                                                    |\n| ------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------- |\n| **Skipped**                                      | A skill's description clearly matched the task, but the skill was never invoked                                                       |\n| **Invoked-but-ignored**                          | The skill was invoked, and Claude's next action directly contradicts its instructions                                                 |\n| **User correction**                              | User writes \"wait\", \"hold up\", \"hmm\", \"double check\", \"no\", \"don't\", \"stop\", \"that's wrong\", \"why did you…\" within 3 turns of a skill |\n| **User invokes another skill to course-correct** | User invokes another skill to double-check output, logic, consistency, security, actions, or tool use in this session                 |\n| **Discarded output**                             | User reverts or overrides the artifact the skill produced                                                                             |\n| **Hook-rejection loop**                          | A blocked action is retried after rejection — a skill should have prevented the first try                                             |\n| **Re-prompt**                                    | User restates or clarifies the same request — skill interpreted it wrongly                                                            |\n\nAlso capture the **rationalization verbatim** — the sentence Claude used to\njustify the misfire. `\u002Flets-make-a-skill` needs this to add a specific counter.\n\n### 3. Classify each finding\n\n- **Misfire** — the skill's text is wrong, incomplete, or its triggers don't\n  match the scenario. Fixable via `\u002Flets-make-a-skill`.\n- **Preference shift** — the skill followed its text faithfully; the user simply\n  wants different behavior going forward. Report separately; **do not\n  auto-update**.\n\nDecision rule: \"would a careful reading of this skill have produced the user's\npreferred behavior?\" Yes → preference shift. No → misfire.\n\n### 4. Present findings\n\nOne row per finding:\n\n```\nskill · signal · evidence (line refs) · classification · proposed-fix\n```\n\nFor each row ask: **approve**, **skip**, or **reclassify**.\n\n### 5. Apply approved fixes\n\nFor each approved misfire, invoke `\u002Flets-make-a-skill` with:\n\n- the skill's file path,\n- the observed rationalization\u002Fgap (verbatim),\n- enough context for a pressure scenario.\n\n`\u002Flets-make-a-skill` carries its own TDD discipline — do not bypass it.\n\n### 6. Update scope\n\nEdits are allowed in:\n\n- `~\u002F.claude\u002Fskills\u002F` (user skills)\n- `\u003Ccwd>\u002F.claude\u002Fskills\u002F` (project skills, if the directory exists)\n\nPlugin-cache skills under `~\u002F.claude\u002Fplugins\u002Fcache\u002F**` are **read-only** —\nplugin updates overwrite local edits. If a misfire lives there, surface the\nfinding but do not edit.\n\n## What This Skill Does NOT Do\n\n- Does not edit skills in the plugin cache.\n- Does not apply fixes without per-finding approval.\n- Does not analyze sessions other than the current one.\n- Does not treat every user correction as a skill bug — preference shifts are\n  filtered out and reported separately.\n- Does not summarize or moralize about Claude's performance — output is a\n  findings table, not a retrospective.\n\n## Edge Cases\n\n- **No skills used** → report \"no skill invocations found\" and exit.\n- **All skills used correctly** → report \"no misfires detected\".\n- **All findings are preference shifts** → surface as a design-question list, do\n  not call `\u002Flets-make-a-skill`.\n- **Misfire lives in plugin cache** → surface, note it cannot be edited, suggest\n  filing upstream.\n- **Transcript unreadable \u002F JSONL corrupt** → report the error; do not proceed\n  blindly.\n",{"name":5,"description":7,"user-invocable":40},true,"main","9635fb649979617cf684ea860dcaeb4eb272aa7d","skills\u002Flearn",1,"https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn","https:\u002F\u002Flaurac8r.github.io\u002Fclaude-damn\u002F","https:\u002F\u002Fgithub.com\u002Flaurac8r","https:\u002F\u002Fwww.webcatgirl.com\u002F","SWE | Python, Java, Typescript, Cloud, AI, ML | Open-source, large-language model, and decision model enthusiast","2026-09-10 01:18:30",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":40},[53,56,59],{"tool":54,"command":55},"npx","npx skills add laurac8r\u002Fclaude-damn --skill learn",{"tool":57,"command":58},"bunx","bunx skills add laurac8r\u002Fclaude-damn --skill learn",{"tool":60,"command":61},"pnpm","pnpm dlx skills add laurac8r\u002Fclaude-damn --skill learn","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Flearn\u002FSKILL.md",[],[65,103,123,140,158,173],{"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":82,"publishedAt":35},"01M6K5V5PPEYZGPW80S9QAF7WZ","visual-aid","Use when the user asks for a quick visual aid, visual explainer, concept card, one-pager, poster, cheat sheet, infographic, visual summary, summary card, or mini explainer page — especially from input like a block of text, attached images, an attached song (lyrics\u002Faudio), a web link, a CSV\u002Fdataset, a math formula, a code snippet to walk through, a tutorial's steps, a timeline, or an A-vs-B comparison. Triggers include \"make me a quick visual aid\", \"turn this into a one-pager \u002F cheat sheet \u002F explainer\", \"summarize this visually\", \"give me a visual of\", \"explain this on a single page\", \"make a concept card for\", \"whip up a page about\", \"build a mini page that shows\", \"something I can paste into a doc explaining X\", or any request to render a topic\u002Ftext\u002Flink\u002Fimage-set\u002Fsong\u002Fdata into a standalone page. Prefer this skill over frontend-design when the ask is an explanatory single-file page (not a production UI), over playground when the output is static information display (not an interactive configurator), and over a Markdown\u002Fcode answer when the user explicitly wants a *page* (HTML). Produces a single self-contained HTML file that opens on double-click without a server.","https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-aid\u002FSKILL.md",[71,76,79],{"categoryNo":72,"categoryName":73,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",{"categoryNo":77,"categoryName":78,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":80,"categoryName":81,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000016","图像与多媒体",[83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102],"visual","visual aid","frontend","design","SET","Audio","visual explainer","up","images","formula","infographic","click","card","render","information","quick","song","standalone","frontend-design","static",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":35},"01M6K5TZZ34SBMQMN2EX11XMYS","tesseract","Use when you've been poking at the same file, concept, or problem across many sessions and want to step outside time to see its whole arc — or when you want to leave a note for next-session-you. Triggers: 'I've been going in circles on X', 'what have I learned about X', 'what did past-me say about X', 'I keep rediscovering this'.","https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Ftesseract\u002FSKILL.md",[],[105,110,111,31,29,112,113,114,83,115,116,117,118,119,120,24,121,23,122,21],"sessions","file","say","me","time","across","anchor","triggers","learned","problem","keep","morse","concept",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":35},"01M6K5TSVWXGRFMQTSM8VFSRDS","tdd","Invoke test-driven development as an explicit one-at-a-time micro-cycle — one test, one piece of functionality, refactor, then repeat for the next behavior","https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002FSKILL.md",[],[125,130,131,132,133,134,135,136,114,137,138,23,139,21],"test","development","micro","refactor","behavior","cycle","next","as","driven","at",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":35},"01M6K5TP1KX237V9FDZ8PMNXH5","tdd-cat","TDD workflow with subagent-driven-development — \u002Ftdd composed with \u002Fcat, plus the A\u002FB TDD execution-mode axis (split-phase vs micro-cycle) asked as a third question in \u002Fcat's combined pre-dispatch question","https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Ftdd-cat\u002FSKILL.md",[],[125,147,148,149,131,132,150,151,152,153,154,155,135,137,138,25,156,23,157],"cat","tdd cat","workflow","execution","tdd workflow","subagent","question","dispatch","task","split","mode",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":35},"01M6K5TGDERXT82MS7SB3ZGA3V","task-list","TaskCreate \u002F TaskUpdate \u002F render the current TaskList in response to `\u002Ftask-list` (with or without flags). The skill body executes immediately on the syntax — no permission-seeking, no echoing the list back as plain text.","https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Ftask-list\u002FSKILL.md",[],[165,155,166,34,167,168,169,170,171,137,96,25,23,172],"list","task list","text","syntax","flags","back","permission","display",{"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":35},"01M6K5T8CER0BAPJVJDG5F5GD0","sync","Sync files between two local directories, repos, or git worktrees. Five modes (plan\u002Finteractive\u002Fpush\u002Fpull\u002Fmirror), .gitignore-aware, Claude-workflow allowlist via --claude, dropbox-restore-style per-directory prompts.","https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Fsync\u002FSKILL.md",[],[175,149,180,181,182,183,184,185,186,187,188,189,190,191,192,193,23,157,194,195],"delete","pull","push","plan","interactive","git worktrees","files","restore","gitignore","local","dry","directories","yes","limit","mirror","modes"]