[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MD04KAM427YNZB3KTXK0QQ":3,"skill-same:01M6MD04KAM427YNZB3KTXK0QQ":70},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6MD04KAM427YNZB3KTXK0QQ","unslop-reasoning",null,"Strip AI-slop patterns from reasoning traces (chain-of-thought, extended thinking, agent decomposition) — not final prose. Reasoning text has its own slop catalog that regular unslop doesn't target: over-explaining the question, over-hedging, over-decomposing trivial problems into 6-bullet substeps, infinite-loop rationalization. Trigger: \u002Funslop-reasoning, \"clean up my reasoning\", \"fix this chain of thought\", \"this CoT sounds robotic\". Applies to reasoning output; does not override regular \u002Funslop mode.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FMohamedAbdallah-14\u002Funslop\u002Fskills\u002Funslop-reasoning\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"unslop","reasoning","unslop reasoning","rationalization","robotic","traces","slop","mode","cot","output","chain-of-thought","chain","trigger","decomposition","thinking","clean","up","catalog","fix","question","text","loop","2026-11-10 10:12:30",false,"---\nname: unslop-reasoning\ndescription: >\n  Strip AI-slop patterns from reasoning traces (chain-of-thought, extended\n  thinking, agent decomposition) — not final prose. Reasoning text has its\n  own slop catalog that regular unslop doesn't target: over-explaining the\n  question, over-hedging, over-decomposing trivial problems into 6-bullet\n  substeps, infinite-loop rationalization.\n  Trigger: \u002Funslop-reasoning, \"clean up my reasoning\", \"fix this chain of\n  thought\", \"this CoT sounds robotic\". Applies to reasoning output; does\n  not override regular \u002Funslop mode.\n---\n\n# unslop-reasoning\n\n## Purpose\n\nThe regular unslop skill targets prose. Chain-of-thought output has a\nseparate failure mode — AI-slop patterns that appear in *reasoning*, not in\nthe final answer. These patterns have no equivalent in the prose catalog\nbecause nobody hand-edits a thinking trace. The research in docs\u002Fresearch\u002F\ncalls this gap out explicitly: \"no AI-slop reasoning pattern catalog\" (Cat\n19). This skill fills it.\n\nApply when the user pastes a reasoning trace — an internal chain of\nthought, an agent's decomposition, or extended-thinking output — and asks\nfor it to read less robotic.\n\n## Signals of reasoning slop\n\nSix canonical patterns, each with an example and a tighter rewrite.\n\n### 1. Restating the question\n\n**AI:**\n\n> The user is asking how to fix the auth middleware bug. They want me to\n> identify the root cause and propose a fix.\n\n**Human:**\n\n> Auth middleware bug. Find cause, propose fix.\n\nThe model often spends a paragraph paraphrasing the input back to itself.\nHumans don't. They read, maybe underline, and move.\n\n### 2. Over-hedging the plan\n\n**AI:**\n\n> There are several factors to consider when approaching this problem.\n> First, we should think about the scope. It's also important to consider\n> the context. There are many potential approaches.\n\n**Human:**\n\n> Three options: A, B, C. A is fastest. B is safest. Picking A unless\n> something looks wrong.\n\nHedging in reasoning inflates the trace without narrowing the problem.\nReal thinking commits to a direction early, then revises.\n\n### 3. Over-decomposing\n\n**AI (for a two-line fix):**\n\n> Step 1: Identify the file.\n> Step 2: Find the function.\n> Step 3: Read the function.\n> Step 4: Identify the bug.\n> Step 5: Plan the change.\n> Step 6: Write the change.\n> Step 7: Verify the change.\n\n**Human:**\n\n> Open auth.py. Token expiry uses `\u003C`, should be `\u003C=`. Fix line 42.\n\nTrivial problems don't need a 7-step decomposition. A flat \"here's the\nanswer\" is more honest than a ceremonial march.\n\n### 4. Infinite-loop rationalization\n\n**AI:**\n\n> Option A could work, but it has drawback X. Option B avoids X but has\n> drawback Y. Option A's drawback X might be acceptable if we consider\n> that Y is also a concern. But B's drawback Y could be addressed by...\n\n**Human:**\n\n> A or B. A has X, B has Y. Picking A because X is reversible and Y is not.\n\nWhen the same two options keep re-appearing with reshuffled pros and cons,\nthe reasoning is circling, not progressing. Commit. Name the tiebreaker.\n\n### 5. Performative exhaustiveness\n\n**AI:**\n\n> Let me consider all possibilities. It could be a network issue. It could\n> be a DNS issue. It could be a routing issue. It could be a firewall\n> issue. It could be a permission issue. It could be...\n\n**Human:**\n\n> Looks like DNS or firewall. Checking DNS first because the logs show\n> resolution errors.\n\nHuman reasoning filters. It doesn't enumerate. Listing every possibility\nwithout prioritizing reads as AI performing rigor rather than doing it.\n\n### 6. Unmotivated confidence-then-retraction\n\n**AI:**\n\n> I am certain the bug is in the cache layer. Wait, let me reconsider.\n> Actually, it might be in the middleware. Although, on reflection, I\n> believe I was right the first time. The cache layer is the most likely\n> cause.\n\n**Human:**\n\n> Probably the cache. Middleware is also possible — check logs before\n> committing to one.\n\nSwinging between \"I am certain\" and \"let me reconsider\" three times in\none paragraph is not thinking. It is simulated humility.\n\n## Application\n\nWhen the user asks you to clean up a reasoning trace:\n\n1. Read the trace once.\n2. Mark which of the six patterns appear.\n3. Rewrite the trace so each marked section becomes a single sentence that\n   commits to a direction. Keep facts, cut ceremony.\n4. Preserve every concrete detail — file names, line numbers, error\n   strings, specific numbers. Only the meta-reasoning gets trimmed.\n5. If the cleaned trace is \u003C 30% of the original, flag it: \"This trace\n   was mostly hedging. The actual content is X.\"\n\n## Boundaries\n\n- Do NOT use this on the FINAL answer. Final answers have their own voice\n  targets handled by the regular `\u002Funslop` skill. This is for the visible\n  thinking that precedes the answer.\n- Do NOT remove a correction. If the trace genuinely reconsidered and\n  changed its mind based on a concrete finding, preserve that beat — it's\n  a real reasoning move, not simulated humility.\n- Do NOT over-compress. A 40-line thinking trace compressed to one line\n  is as suspicious as the original. Human reasoning has surface area.\n  Aim for the shape of human thinking, not for word-count minimalism.\n- Code, commands, error messages, file paths, numbers: preserved exactly.\n\n## Research basis\n\nCat 19 (Agentic Autonomous Thinking) names the missing-catalog gap\ndirectly: \"there are well-documented blacklists for AI-slop prose (stock\nphrases, sycophancy, hedging stacks — Cat 01, 16). There is no equivalent\nlist for AI-slop reasoning patterns: over-explaining, over-hedging, over-\ndecomposing, and the infinite-loop rationalization visible mid-agent-run.\"\nThis skill is the first pass at that catalog. It is a starting point, not\na final answer.\n\nCat 06 (Chain-of-Thought Reasoning) makes the case that visible-reasoning\ntraces are a feature, not a bug. The goal here is not to hide reasoning\nbut to make the visible part read like a person thinking, not a model\nperforming thought.\n","# unslop-reasoning\n\n## Purpose\n\nThe regular unslop skill targets prose. Chain-of-thought output has a\nseparate failure mode — AI-slop patterns that appear in *reasoning*, not in\nthe final answer. These patterns have no equivalent in the prose catalog\nbecause nobody hand-edits a thinking trace. The research in docs\u002Fresearch\u002F\ncalls this gap out explicitly: \"no AI-slop reasoning pattern catalog\" (Cat\n19). This skill fills it.\n\nApply when the user pastes a reasoning trace — an internal chain of\nthought, an agent's decomposition, or extended-thinking output — and asks\nfor it to read less robotic.\n\n## Signals of reasoning slop\n\nSix canonical patterns, each with an example and a tighter rewrite.\n\n### 1. Restating the question\n\n**AI:**\n\n> The user is asking how to fix the auth middleware bug. They want me to\n> identify the root cause and propose a fix.\n\n**Human:**\n\n> Auth middleware bug. Find cause, propose fix.\n\nThe model often spends a paragraph paraphrasing the input back to itself.\nHumans don't. They read, maybe underline, and move.\n\n### 2. Over-hedging the plan\n\n**AI:**\n\n> There are several factors to consider when approaching this problem.\n> First, we should think about the scope. It's also important to consider\n> the context. There are many potential approaches.\n\n**Human:**\n\n> Three options: A, B, C. A is fastest. B is safest. Picking A unless\n> something looks wrong.\n\nHedging in reasoning inflates the trace without narrowing the problem.\nReal thinking commits to a direction early, then revises.\n\n### 3. Over-decomposing\n\n**AI (for a two-line fix):**\n\n> Step 1: Identify the file.\n> Step 2: Find the function.\n> Step 3: Read the function.\n> Step 4: Identify the bug.\n> Step 5: Plan the change.\n> Step 6: Write the change.\n> Step 7: Verify the change.\n\n**Human:**\n\n> Open auth.py. Token expiry uses `\u003C`, should be `\u003C=`. Fix line 42.\n\nTrivial problems don't need a 7-step decomposition. A flat \"here's the\nanswer\" is more honest than a ceremonial march.\n\n### 4. Infinite-loop rationalization\n\n**AI:**\n\n> Option A could work, but it has drawback X. Option B avoids X but has\n> drawback Y. Option A's drawback X might be acceptable if we consider\n> that Y is also a concern. But B's drawback Y could be addressed by...\n\n**Human:**\n\n> A or B. A has X, B has Y. Picking A because X is reversible and Y is not.\n\nWhen the same two options keep re-appearing with reshuffled pros and cons,\nthe reasoning is circling, not progressing. Commit. Name the tiebreaker.\n\n### 5. Performative exhaustiveness\n\n**AI:**\n\n> Let me consider all possibilities. It could be a network issue. It could\n> be a DNS issue. It could be a routing issue. It could be a firewall\n> issue. It could be a permission issue. It could be...\n\n**Human:**\n\n> Looks like DNS or firewall. Checking DNS first because the logs show\n> resolution errors.\n\nHuman reasoning filters. It doesn't enumerate. Listing every possibility\nwithout prioritizing reads as AI performing rigor rather than doing it.\n\n### 6. Unmotivated confidence-then-retraction\n\n**AI:**\n\n> I am certain the bug is in the cache layer. Wait, let me reconsider.\n> Actually, it might be in the middleware. Although, on reflection, I\n> believe I was right the first time. The cache layer is the most likely\n> cause.\n\n**Human:**\n\n> Probably the cache. Middleware is also possible — check logs before\n> committing to one.\n\nSwinging between \"I am certain\" and \"let me reconsider\" three times in\none paragraph is not thinking. It is simulated humility.\n\n## Application\n\nWhen the user asks you to clean up a reasoning trace:\n\n1. Read the trace once.\n2. Mark which of the six patterns appear.\n3. Rewrite the trace so each marked section becomes a single sentence that\n   commits to a direction. Keep facts, cut ceremony.\n4. Preserve every concrete detail — file names, line numbers, error\n   strings, specific numbers. Only the meta-reasoning gets trimmed.\n5. If the cleaned trace is \u003C 30% of the original, flag it: \"This trace\n   was mostly hedging. The actual content is X.\"\n\n## Boundaries\n\n- Do NOT use this on the FINAL answer. Final answers have their own voice\n  targets handled by the regular `\u002Funslop` skill. This is for the visible\n  thinking that precedes the answer.\n- Do NOT remove a correction. If the trace genuinely reconsidered and\n  changed its mind based on a concrete finding, preserve that beat — it's\n  a real reasoning move, not simulated humility.\n- Do NOT over-compress. A 40-line thinking trace compressed to one line\n  is as suspicious as the original. Human reasoning has surface area.\n  Aim for the shape of human thinking, not for word-count minimalism.\n- Code, commands, error messages, file paths, numbers: preserved exactly.\n\n## Research basis\n\nCat 19 (Agentic Autonomous Thinking) names the missing-catalog gap\ndirectly: \"there are well-documented blacklists for AI-slop prose (stock\nphrases, sycophancy, hedging stacks — Cat 01, 16). There is no equivalent\nlist for AI-slop reasoning patterns: over-explaining, over-hedging, over-\ndecomposing, and the infinite-loop rationalization visible mid-agent-run.\"\nThis skill is the first pass at that catalog. It is a starting point, not\na final answer.\n\nCat 06 (Chain-of-Thought Reasoning) makes the case that visible-reasoning\ntraces are a feature, not a bug. The goal here is not to hide reasoning\nbut to make the visible part read like a person thinking, not a model\nperforming thought.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FMohamedAbdallah-14\u002Funslop\u002Fskills\u002Funslop-reasoning",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill unslop-reasoning",{"tool":62,"command":63},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill unslop-reasoning",{"tool":65,"command":66},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill unslop-reasoning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FMohamedAbdallah-14\u002Funslop\u002Fskills\u002Funslop-reasoning\u002FSKILL.md",true,[],[71,81,89,97,105,113],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":76,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":80},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"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":75,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":80},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":80},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":80},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":109,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":80},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":75,"licenseFileUrl":117,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":80},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]