[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7923KGCMXT25Y7XVC6G1ERX":3,"skill-same:01M7923KGCMXT25Y7XVC6G1ERX":54},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7923KGCMXT25Y7XVC6G1ERX","unpack",null,"Explain an unfamiliar thing plainly and from first principles, structured so the reader sees why it is true. Use when someone is trying to understand something — a dense or jargon-heavy passage, a baffling error, an unfamiliar mechanism, a codebase, or a document — asks to break something down (\"walk me through this\", \"what does this actually mean\"), or wants their intent turned into a precise instruction for another agent. Trigger on confusion or a request to understand, not on difficulty alone; technical or long content is not itself a signal.","dotlas\u002Fskills","dotlas","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F88832003?v=4","01M791ZCS9BAQ40PZ8ADG8TCR1","Dotlas","01M791ZCT18PGXY969S8EZ1MVV",2,"MIT","https:\u002F\u002Fgithub.com\u002Fdotlas\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcustom\u002Fcommon\u002Funpack\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: unpack\ndescription: Explain an unfamiliar thing plainly and from first principles, structured so the reader sees why it is true. Use when someone is trying to understand something — a dense or jargon-heavy passage, a baffling error, an unfamiliar mechanism, a codebase, or a document — asks to break something down (\"walk me through this\", \"what does this actually mean\"), or wants their intent turned into a precise instruction for another agent. Trigger on confusion or a request to understand, not on difficulty alone; technical or long content is not itself a signal.\n---\n# Unpack — Plain, First-Principles Explanations\n\n* * *\n\n## When To Use\n\nUse this when the user wants to **understand** something — a codebase, a document, a\ndecision, a process, any unfamiliar mechanism — build intuition, decode an error, or\ntranslate intent into precise instructions for another agent.\n\n- The user may already be an expert elsewhere; they just don’t know *this* thing yet.\n- Don’t assume the topic is technical.\n\n* * *\n\n## Procedures\n\nPick the situation first, then apply the principles below as the craft underneath it.\n\n| Situation | Approach |\n| --- | --- |\n| **Default** | Read what’s needed, then answer directly; don’t ask for context the source already gives. |\n| **Overview requested** | 4–6 sentences: what it’s for, the main pieces, how control\u002Fdata moves end to end, how it’s validated. Discover this from the source. |\n| **Debugging (code)** | Read the error yourself, state what broke in one sentence, explain the mechanism that produced it, give a concrete fix. |\n| **Directing another agent (code)** | Translate intent into a precise instruction — name the exact files\u002Ftests to attach and the exact change to make, not a vague pointer. |\n| **Summarize requested** | Distil agent output or a findings dump into a structured brief — see [summarize.md](summarize.md). |\n\n## Output format\n\n- **Open with the answer** — first sentence is the answer, not a windup.\n- **Prose by default** — connected reasoning flows as prose; one idea per paragraph.\n- **Table** when comparing things across shared dimensions (e.g. *this vs that*).\n- **Bullets** for genuinely parallel, non-sequential items.\n- Never use structure to look thorough — reach for it only when the shape calls for it.\n\n* * *\n\n## Not The Same Axis As Compression\n\nCompression and this skill operate on different axes and can both run at once — they\ndon’t compete.\n\n|  | Compression mode (e.g. terse\u002Fcaveman) | This skill |\n| --- | --- | --- |\n| Changes | the **phrasing** — same facts, order | the **shape** — order, what’s earned |\n| Goal | fewer words | less confusion |\n\n* * *\n\n## Core Principles — Always On\n\nApply these to every explanation, in roughly this order — it follows the arc of\ncomposing one: find what’s being asked, nail what the thing is, frame the problem it\nsolves, pitch it to a capable reader, anchor it to the source, then write it lean and\nclear.\n\n### 1. Answer What Was Actually Unclear\n\nBefore answering, read the recent conversation — that’s what triggered the invocation.\nSomething there was unclear; the first answer covers *that* specific confusion, not a\ngeneral overview of the topic.\n\n- **“Satisfying” means** the thing that was unclear is now clear — not every branch and\n  edge case, but not a generic summary either.\n- **Go deeper only on the part the user pulls on next.**\n- **Don’t close with empty filler** like “let me know if you want more” — stop when the\n  confusion’s cleared.\n\n### 2. Pin Down What It Actually Is\n\nThe one-line core the rest of the explanation hangs on has to cut cleanly.\nA wrong characterization is worse than none — it feels like understanding while sending\nthe reader confidently wrong.\n\n| The definition is… | …when it |\n| --- | --- |\n| Too broad | fits things that aren’t the thing |\n| Too narrow | excludes real cases |\n| Empty | is so loose it says nothing |\n\n> “A trust is a legal arrangement for managing assets” is **too broad** — that also fits\n> a will, a power of attorney, an escrow.\n> The clean version names the one thing that’s only true of a trust.\n\nSometimes two or more things in the material overlap so closely they read as one.\nThe fix isn’t more explanation — it’s pulling them apart and showing *this, not that*.\nName each one, say how they differ — one difference or several — and point out which\napplies here.\n\n### 3. Start With The Problem, Support With Analogy\n\nEvery mechanism exists because something was awkward, risky, or unclear without it.\nOpen there — the problem, then the plain explanation of how the mechanism addresses it.\n\n- **Analogy never opens** — state the mechanism first.\n- **Analogy only illustrates** — never let it carry what a plain statement could have\n  said. An analogy doing a direct explanation’s job is a crutch.\n- **One analogy per idea** — needing a second means it’s two ideas; give them their own\n  paragraphs.\n\n### 4. Assume Capability, Not Context\n\nThe reader is sharp, just not steeped in this specific thing.\n\n- **Adapt to capability, not credentials** — don’t ask about their background.\n- **Don’t talk down to a child** — don’t explain what a function or a term is unless\n  that’s the actual question.\n- **Explain the why** — why the mechanism needs to do what it does; name the underlying\n  tool only as the thing that makes it possible.\n\n### 5. Let The Source Anchor The Explanation\n\nRead the code, docs, thread, or data before describing it — but the finished explanation\nshould read like someone who already knows the answer telling you plainly, not a\nresearch report with a citation on every clause.\n\n- State the fact; **name the source once**, at the end of the point, only if the user\n  needs to verify it or hand it to another agent — not woven through every sentence.\n\n### 6. Write Lean And Clear\n\nGoal: reduce cognitive load.\nEach sentence sets up the next, so the reader moves forward without backtracking — not\nbecause anything’s simplified, but because the order is right.\n\n- **Open with the answer.**\n- **Don’t tour the vocabulary** — define a term in the sentence where it first appears,\n  if at all.\n- **One idea per paragraph** — if a sentence needs three em-dashes or two “which means”\n  clauses, that’s two ideas; split it.\n- **Keep language compact** — cut filler, hedges, and adjectives that don’t carry\n  information.\n- **Prefer the checkable over the taken-on-trust** — “the same call failed the same way\n  on two different days” beats “the failure is remarkably stable.”\n- **Brevity comes from tighter phrasing, never from dropping a real point** — compress\n  the words around an idea, not the idea.\n  If shortening loses a step the reader needs, it wasn’t fluff.\n- **Match the format to the shape of the content** — a table for comparing things across\n  shared dimensions, bullets for genuinely parallel items, prose for connected\n  reasoning. Prose is the default; reach for a table or bullets only when the shape calls\n  for it. A comparison table is especially sharp when separating things that look alike\n  (see *Pin Down What It Actually Is*).\n\n* * *\n\n## Situational Moves\n\nFire these only when the situation calls for them — not every explanation needs them.\n\n### 7. Narrate Elimination, Don’t List Conclusions\n\nWhen the question is “why *this*, and not the obvious simpler thing,” walk through each\nsimpler option in the order it’d be tried, and state plainly why it failed before\nlanding on what’s left.\nEach “doesn’t work” should rest on a reason the reader could check — *why* it can’t\nwork, in terms they could confirm — so the elimination is earned, not asserted.\n\n> “Coordinates aren’t recoverable; triangulation’s impossible; hence geocoding” lists\n> three facts with no thread.\n> Walk each option in order and say why it failed — then what’s left is earned, not\n> announced.\n\n### 8. Show The Journey When It Helps\n\nWhen something moves through several steps and the order matters, a tiny flow can do\nmore work than a paragraph.\nBuild it from what actually happens, not a template.\n\n```text\nidea -> draft -> review -> ship\n```\n","# Unpack — Plain, First-Principles Explanations\n\n* * *\n\n## When To Use\n\nUse this when the user wants to **understand** something — a codebase, a document, a\ndecision, a process, any unfamiliar mechanism — build intuition, decode an error, or\ntranslate intent into precise instructions for another agent.\n\n- The user may already be an expert elsewhere; they just don’t know *this* thing yet.\n- Don’t assume the topic is technical.\n\n* * *\n\n## Procedures\n\nPick the situation first, then apply the principles below as the craft underneath it.\n\n| Situation | Approach |\n| --- | --- |\n| **Default** | Read what’s needed, then answer directly; don’t ask for context the source already gives. |\n| **Overview requested** | 4–6 sentences: what it’s for, the main pieces, how control\u002Fdata moves end to end, how it’s validated. Discover this from the source. |\n| **Debugging (code)** | Read the error yourself, state what broke in one sentence, explain the mechanism that produced it, give a concrete fix. |\n| **Directing another agent (code)** | Translate intent into a precise instruction — name the exact files\u002Ftests to attach and the exact change to make, not a vague pointer. |\n| **Summarize requested** | Distil agent output or a findings dump into a structured brief — see [summarize.md](summarize.md). |\n\n## Output format\n\n- **Open with the answer** — first sentence is the answer, not a windup.\n- **Prose by default** — connected reasoning flows as prose; one idea per paragraph.\n- **Table** when comparing things across shared dimensions (e.g. *this vs that*).\n- **Bullets** for genuinely parallel, non-sequential items.\n- Never use structure to look thorough — reach for it only when the shape calls for it.\n\n* * *\n\n## Not The Same Axis As Compression\n\nCompression and this skill operate on different axes and can both run at once — they\ndon’t compete.\n\n|  | Compression mode (e.g. terse\u002Fcaveman) | This skill |\n| --- | --- | --- |\n| Changes | the **phrasing** — same facts, order | the **shape** — order, what’s earned |\n| Goal | fewer words | less confusion |\n\n* * *\n\n## Core Principles — Always On\n\nApply these to every explanation, in roughly this order — it follows the arc of\ncomposing one: find what’s being asked, nail what the thing is, frame the problem it\nsolves, pitch it to a capable reader, anchor it to the source, then write it lean and\nclear.\n\n### 1. Answer What Was Actually Unclear\n\nBefore answering, read the recent conversation — that’s what triggered the invocation.\nSomething there was unclear; the first answer covers *that* specific confusion, not a\ngeneral overview of the topic.\n\n- **“Satisfying” means** the thing that was unclear is now clear — not every branch and\n  edge case, but not a generic summary either.\n- **Go deeper only on the part the user pulls on next.**\n- **Don’t close with empty filler** like “let me know if you want more” — stop when the\n  confusion’s cleared.\n\n### 2. Pin Down What It Actually Is\n\nThe one-line core the rest of the explanation hangs on has to cut cleanly.\nA wrong characterization is worse than none — it feels like understanding while sending\nthe reader confidently wrong.\n\n| The definition is… | …when it |\n| --- | --- |\n| Too broad | fits things that aren’t the thing |\n| Too narrow | excludes real cases |\n| Empty | is so loose it says nothing |\n\n> “A trust is a legal arrangement for managing assets” is **too broad** — that also fits\n> a will, a power of attorney, an escrow.\n> The clean version names the one thing that’s only true of a trust.\n\nSometimes two or more things in the material overlap so closely they read as one.\nThe fix isn’t more explanation — it’s pulling them apart and showing *this, not that*.\nName each one, say how they differ — one difference or several — and point out which\napplies here.\n\n### 3. Start With The Problem, Support With Analogy\n\nEvery mechanism exists because something was awkward, risky, or unclear without it.\nOpen there — the problem, then the plain explanation of how the mechanism addresses it.\n\n- **Analogy never opens** — state the mechanism first.\n- **Analogy only illustrates** — never let it carry what a plain statement could have\n  said. An analogy doing a direct explanation’s job is a crutch.\n- **One analogy per idea** — needing a second means it’s two ideas; give them their own\n  paragraphs.\n\n### 4. Assume Capability, Not Context\n\nThe reader is sharp, just not steeped in this specific thing.\n\n- **Adapt to capability, not credentials** — don’t ask about their background.\n- **Don’t talk down to a child** — don’t explain what a function or a term is unless\n  that’s the actual question.\n- **Explain the why** — why the mechanism needs to do what it does; name the underlying\n  tool only as the thing that makes it possible.\n\n### 5. Let The Source Anchor The Explanation\n\nRead the code, docs, thread, or data before describing it — but the finished explanation\nshould read like someone who already knows the answer telling you plainly, not a\nresearch report with a citation on every clause.\n\n- State the fact; **name the source once**, at the end of the point, only if the user\n  needs to verify it or hand it to another agent — not woven through every sentence.\n\n### 6. Write Lean And Clear\n\nGoal: reduce cognitive load.\nEach sentence sets up the next, so the reader moves forward without backtracking — not\nbecause anything’s simplified, but because the order is right.\n\n- **Open with the answer.**\n- **Don’t tour the vocabulary** — define a term in the sentence where it first appears,\n  if at all.\n- **One idea per paragraph** — if a sentence needs three em-dashes or two “which means”\n  clauses, that’s two ideas; split it.\n- **Keep language compact** — cut filler, hedges, and adjectives that don’t carry\n  information.\n- **Prefer the checkable over the taken-on-trust** — “the same call failed the same way\n  on two different days” beats “the failure is remarkably stable.”\n- **Brevity comes from tighter phrasing, never from dropping a real point** — compress\n  the words around an idea, not the idea.\n  If shortening loses a step the reader needs, it wasn’t fluff.\n- **Match the format to the shape of the content** — a table for comparing things across\n  shared dimensions, bullets for genuinely parallel items, prose for connected\n  reasoning. Prose is the default; reach for a table or bullets only when the shape calls\n  for it. A comparison table is especially sharp when separating things that look alike\n  (see *Pin Down What It Actually Is*).\n\n* * *\n\n## Situational Moves\n\nFire these only when the situation calls for them — not every explanation needs them.\n\n### 7. Narrate Elimination, Don’t List Conclusions\n\nWhen the question is “why *this*, and not the obvious simpler thing,” walk through each\nsimpler option in the order it’d be tried, and state plainly why it failed before\nlanding on what’s left.\nEach “doesn’t work” should rest on a reason the reader could check — *why* it can’t\nwork, in terms they could confirm — so the elimination is earned, not asserted.\n\n> “Coordinates aren’t recoverable; triangulation’s impossible; hence geocoding” lists\n> three facts with no thread.\n> Walk each option in order and say why it failed — then what’s left is earned, not\n> announced.\n\n### 8. Show The Journey When It Helps\n\nWhen something moves through several steps and the order matters, a tiny flow can do\nmore work than a paragraph.\nBuild it from what actually happens, not a template.\n\n```text\nidea -> draft -> review -> ship\n```\n",{"name":5,"description":7},"main","44a7c5d185b1020f689d2129547d7470c3715e76","skills\u002Fcustom\u002Fcommon\u002Funpack",0,"https:\u002F\u002Fgithub.com\u002Fdotlas\u002Fskills","https:\u002F\u002Fwww.skills.sh\u002Fdotlas\u002Fskills","https:\u002F\u002Fgithub.com\u002Fdotlas","www.dotlas.com","A platform to help companies make better city-level decisions and improve the bottom line of their retail footprint.","2026-10-27 22:40:58",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add dotlas\u002Fskills --skill unpack",{"tool":40,"command":41},"bunx","bunx skills add dotlas\u002Fskills --skill unpack",{"tool":43,"command":44},"pnpm","pnpm dlx skills add dotlas\u002Fskills --skill unpack","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdotlas\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcustom\u002Fcommon\u002Funpack\u002FSKILL.md",true,[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"summarize.md","REFERENCE","参考文档",1300,"https:\u002F\u002Fgithub.com\u002Fdotlas\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcustom\u002Fcommon\u002Funpack\u002Fsummarize.md",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M792400972AXPY3XESVHRFRA","where-were-we","Provide the user with a refresher of existing chat turns. Useful when the user wants to understand where we stand in the conversation.","https:\u002F\u002Fgithub.com\u002Fdotlas\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcustom\u002Fcommon\u002Fwhere-were-we\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7923T58GM9G9TVAZB9TGTWE","update-global-dotlas-skills","Sync the globally-installed dotlas\u002Fskills catalog and prune stale remnants. Runs the documented global install command, then detects skills that were installed from dotlas\u002Fskills but no longer exist in the catalog and removes them (with confirmation). Use when the user wants to update, refresh, or clean up their global Dotlas skills, or invokes \u002Fupdate-global-dotlas-skills.","https:\u002F\u002Fgithub.com\u002Fdotlas\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcustom\u002Fcommon\u002Fupdate-global-dotlas-skills\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7923HNVVHRKRVQ5M0P7TXZA","sum","Use when the previous response is too technical, complex, or jargon-heavy and needs a clear, plain-language explanation","https:\u002F\u002Fgithub.com\u002Fdotlas\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcustom\u002Fcommon\u002Fsum\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7923CY3FR71VPKBYRHZNNVH","slack","Compose a Slack message, or digest a Slack thread into compact context. Use when the user asks to reply to a person or channel, write a Slack post, or catch up on a thread without reading the whole transcript. This skill covers how to write well for Slack — both jobs share the same standard.","https:\u002F\u002Fgithub.com\u002Fdotlas\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcustom\u002Fcommon\u002Fslack\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M79234W72RKWYV2S38G2B0SY","plan-with-me","Collaborative, human-in-the-loop planning for something new that spans several parts and needs human judgement at each fork. A brainstorming partner that funnels — each fork opens up the real options, then narrows to a decision, surfacing caveats and breaking points, and co-authoring the plan instead of guessing alone. Fits any domain where you plan something new against existing context. Resolves one decision at a time, each with a recommendation, then emits a lightweight plan to hand off for implementation. Use when planning alone would make wrong assumptions, or the user wants to shape something new together.","https:\u002F\u002Fgithub.com\u002Fdotlas\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcustom\u002Fcommon\u002Fplan-with-me\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7922ZHHS3XB2YBBD92BYPWB","multi-agent-chat","Open a chatroom — a plain .txt log on disk — so agents in separate sessions (Claude, Codex, others) whose work has collided or become correlated can talk to each other: resolve the conflict, trade the context each is missing, and settle who owns what. The agent that opens the room moderates it; the operator relays the room path to the other agents. Use when two sessions are stepping on each other or one needs what the other knows, or when handed a room path and asked to join.","https:\u002F\u002Fgithub.com\u002Fdotlas\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcustom\u002Fcommon\u002Fmulti-agent-chat\u002FSKILL.md",[],[]]