{"id":6120,"date":"2026-10-19T16:49:03","date_gmt":"2026-10-19T16:49:03","guid":{"rendered":"https:\/\/i10xnews.kinsta.cloud\/?p=6120"},"modified":"2026-10-19T17:17:37","modified_gmt":"2026-10-19T17:17:37","slug":"demystifying-agent-skills-procedural-anchors","status":"publish","type":"post","link":"https:\/\/i10x.ai\/news\/demystifying-agent-skills-procedural-anchors","title":{"rendered":"Agent &#8220;Skills&#8221; Mostly Anchor Procedures, Not Inject Knowledge \u2014 and Retrieval Breaks Them"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">\u26a1 Quick Take<\/h2>\n\n<ul class=\"wp-block-list\"><li><strong>The finding:<\/strong> Skill-augmented agents beat workflow memory by 6.06 points (95% CI +0.76 to +11.36).<\/li><li><strong>Why they work:<\/strong> Procedural anchoring explains 65.7% of skill cases; explicit knowledge injection only 4.5%.<\/li><li><strong>Why they fail:<\/strong> As skill pools grow from 5 to 100, actual-use precision falls from 29.6% to 3.3% \u2014 retrieval becomes the bottleneck.<\/li><\/ul>\n\n\n<p class=\"wp-block-paragraph\">Agent systems increasingly store reusable &#8220;skills&#8221;: compact descriptions of what to do, check and avoid. Princeton, UCSD, Stanford, USC and Johns Hopkins researchers ask not whether skills raise success, but why they work \u2014 and when they stop.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1344\" height=\"768\" src=\"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/demystifying-agent-skills-procedural-anchors-retrieval.webp\" alt=\"Dumbbell: skill actual-use precision falls from 29.6 percent at pool size 5 to 3.3 percent at pool size 100.\" class=\"wp-image-6119\" srcset=\"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/demystifying-agent-skills-procedural-anchors-retrieval.webp 1344w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/demystifying-agent-skills-procedural-anchors-retrieval-300x171.webp 300w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/demystifying-agent-skills-procedural-anchors-retrieval-1024x585.webp 1024w, https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/demystifying-agent-skills-procedural-anchors-retrieval-768x439.webp 768w\" sizes=\"auto, (max-width: 1344px) 100vw, 1344px\" \/><figcaption class=\"wp-element-caption\">i10X chart based on data from Jiang et al. (2026), arXiv:2608.14036, retrieval-scale analysis (arXiv non-exclusive license).<\/figcaption><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udd2c What the study shows<\/h2>\n\n\n<p class=\"wp-block-paragraph\">Matched comparisons against raw baselines and workflow memory, with a human-validated mechanism taxonomy (95.8% agreement, Cohen&#8217;s \u03ba = 0.952).<\/p>\n\n\n<ul class=\"wp-block-list\"><li><strong>Skills stabilize action:<\/strong> They encode procedures more than missing facts.<\/li><li><strong>Success composition:<\/strong> Skill-guided success accounts for 61.6% of skill-arm cases vs 54.5% workflow-guided success in the workflow arm.<\/li><li><strong>Taxonomy mode:<\/strong> Skills fall into successful-procedure class in 61.7% of cases vs 59.1% raw and 55.7% workflow memory.<\/li><\/ul>\n\n\n<h2 class=\"wp-block-heading\">\u2705 Why it matters: skills are not a knowledge base<\/h2>\n\n\n<p class=\"wp-block-paragraph\">If skills mainly anchor procedures, bloating a skill library with facts will not help \u2014 and poor retrieval will erase the gains.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83e\uddea Method in brief<\/h2>\n\n\n<p class=\"wp-block-paragraph\">Trajectory grounding with 714 checks; taxonomy aggregation validated by humans.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\u2753 What remains open<\/h2>\n\n<ul class=\"wp-block-list\"><li><strong>Setting-specific:<\/strong> Results depend on the skill format and domains tested.<\/li><li><strong>Retrieval methods:<\/strong> Better retrievers might slow the precision drop.<\/li><\/ul>\n\n\n<h2 class=\"wp-block-heading\">\ud83e\udded Context<\/h2>\n\n\n<p class=\"wp-block-paragraph\">Related to Anthropic-style skills and agent memory. See <a href=\"\/news\/category\/studies\/agent-research\">Agents<\/a>.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udee0\ufe0f What it means for skill libraries<\/h2>\n\n<ul class=\"wp-block-list\"><li><strong>Keep pools small or curated:<\/strong> Precision collapses at scale.<\/li><li><strong>Write procedural skills:<\/strong> Checklists and pitfalls beat trivia.<\/li><li><strong>Measure actual use:<\/strong> Retrieval hit rate alone is insufficient.<\/li><\/ul>\n\n\n<h2 class=\"wp-block-heading\">\u270d\ufe0f About the analysis<\/h2>\n\n\n<p class=\"wp-block-paragraph\">This article is based on the full text of the preprint &#8220;Demystifying Agent Skills: Why They Work-Until They Don&#x27;t&#8221; (arXiv:2608.14036v1, submitted August 14, 2026). All numbers are taken from the paper&#8217;s text, tables and figures; i10X did not rerun the experiments. The paper is distributed under arXiv&#8217;s non-exclusive license, so i10X does not reproduce its figures; the chart was drawn by i10X from numbers reported in retrieval-scale analysis.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\ud83d\udd2d i10x Perspective<\/h2>\n\n\n<p class=\"wp-block-paragraph\">Skills looked like a way to give agents lasting know-how. This paper says most of the win is reminding the agent how to act, and that win dies when the library gets noisy. The product lesson is ruthless curation.<\/p>\n\n","protected":false},"excerpt":{"rendered":"<p>Skills beat workflow memory by 6.06 points, but 65.7% of their benefit is procedural anchoring. As skill pools grow from 5 to 100, actual-use precision falls from 29.6% to 3.3%.<\/p>\n","protected":false},"author":2,"featured_media":6270,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"paper_title":"Demystifying Agent Skills: Why They Work-Until They Don't","paper_url":"https:\/\/arxiv.org\/abs\/2608.14036","pdf_url":"https:\/\/arxiv.org\/pdf\/2608.14036v1","doi":"","arxiv_id":"2608.14036","authors":"Zhiyuan Jiang, Fangrui Huang, Hanwen Xing, Xander Wu, Yipeng Gao, Rui Cao, Mengdi Wang, Shilong Liu, Yijiang Li","institutions":"Princeton; UC San Diego; Stanford; USC; Johns Hopkins","paper_date":"2026-08-14","venue":"arXiv (cs.AI), version 1","peer_reviewed":false,"code_url":"","data_url":"","funding_coi":"Internship at Princeton noted.","figure_license":"Chart drawn by i10X from retrieval-scale analysis (arXiv non-exclusive license)","paper_license":"arXiv non-exclusive license","replication":"no","study_models":"Skill-augmented LLM agents vs workflow memory baselines","study_sample":"Matched skill vs workflow comparisons with taxonomy labels","footnotes":"","_yoast_wpseo_primary_category":""},"categories":[55,52],"tags":[],"companies":[39],"products":[],"class_list":["post-6120","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-agent-research","category-studies","company-anthropic"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.7 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Why Agent Skills Work \u2014 Until Retrieval Collapses - i10X News<\/title>\n<meta name=\"description\" content=\"Study: agent skills help via procedural anchoring (+6.06 vs workflow memory). Retrieval precision falls from 29.6% to 3.3% as pools grow.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Why Agent Skills Work \u2014 Until Retrieval Collapses - i10X News\" \/>\n<meta property=\"og:description\" content=\"Study: agent skills help via procedural anchoring (+6.06 vs workflow memory). Retrieval precision falls from 29.6% to 3.3% as pools grow.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors\" \/>\n<meta property=\"og:site_name\" content=\"i10X News\" \/>\n<meta property=\"article:published_time\" content=\"2026-10-19T16:49:03+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-10-19T17:17:37+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/demystifying-agent-skills-procedural-anchors-title.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1344\" \/>\n\t<meta property=\"og:image:height\" content=\"768\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Christopher Ort\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@i10x_ai\" \/>\n<meta name=\"twitter:site\" content=\"@i10x_ai\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Christopher Ort\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/demystifying-agent-skills-procedural-anchors#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/demystifying-agent-skills-procedural-anchors\"},\"author\":{\"name\":\"Christopher Ort\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#\\\/schema\\\/person\\\/d410bb7ee72febefca2c9c369939219a\"},\"headline\":\"Agent &#8220;Skills&#8221; Mostly Anchor Procedures, Not Inject Knowledge \u2014 and Retrieval Breaks Them\",\"datePublished\":\"2026-10-19T16:49:03+00:00\",\"dateModified\":\"2026-10-19T17:17:37+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/demystifying-agent-skills-procedural-anchors\"},\"wordCount\":395,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/demystifying-agent-skills-procedural-anchors#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/demystifying-agent-skills-procedural-anchors-title.webp\",\"articleSection\":[\"Agent Research\",\"Studies\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/demystifying-agent-skills-procedural-anchors#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/demystifying-agent-skills-procedural-anchors\",\"url\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/demystifying-agent-skills-procedural-anchors\",\"name\":\"Why Agent Skills Work \u2014 Until Retrieval Collapses - i10X News\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/demystifying-agent-skills-procedural-anchors#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/demystifying-agent-skills-procedural-anchors#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/demystifying-agent-skills-procedural-anchors-title.webp\",\"datePublished\":\"2026-10-19T16:49:03+00:00\",\"dateModified\":\"2026-10-19T17:17:37+00:00\",\"description\":\"Study: agent skills help via procedural anchoring (+6.06 vs workflow memory). Retrieval precision falls from 29.6% to 3.3% as pools grow.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/demystifying-agent-skills-procedural-anchors#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/demystifying-agent-skills-procedural-anchors\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/demystifying-agent-skills-procedural-anchors#primaryimage\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/demystifying-agent-skills-procedural-anchors-title.webp\",\"contentUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/demystifying-agent-skills-procedural-anchors-title.webp\",\"width\":1344,\"height\":768,\"caption\":\"Illustration: i10X\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/demystifying-agent-skills-procedural-anchors#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/news.i10x.ai\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Agent &#8220;Skills&#8221; Mostly Anchor Procedures, Not Inject Knowledge \u2014 and Retrieval Breaks Them\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#website\",\"url\":\"https:\\\/\\\/news.i10x.ai\\\/\",\"name\":\"i10X News\",\"description\":\"Stay updated with the latest news and announcements from i10X.\",\"publisher\":{\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/news.i10x.ai\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#organization\",\"name\":\"i10X\",\"url\":\"https:\\\/\\\/news.i10x.ai\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/i10x-logo-180.png\",\"contentUrl\":\"https:\\\/\\\/i10xnews.kinsta.cloud\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/i10x-logo-180.png\",\"width\":180,\"height\":180,\"caption\":\"i10X\"},\"image\":{\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/i10x_ai\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/i10x-ai\",\"https:\\\/\\\/instagram.com\\\/i10x.ai\",\"https:\\\/\\\/www.youtube.com\\\/@i10X_ai_official\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/news.i10x.ai\\\/#\\\/schema\\\/person\\\/d410bb7ee72febefca2c9c369939219a\",\"name\":\"Christopher Ort\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"contentUrl\":\"https:\\\/\\\/i10x.ai\\\/news\\\/wp-content\\\/uploads\\\/2026\\\/10\\\/christopher-ort-192.webp\",\"caption\":\"Christopher Ort\"},\"description\":\"Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU). He is the author of \u201cThe Style Penalty\u201d, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.\",\"url\":\"https:\\\/\\\/i10x.ai\\\/news\\\/author\\\/christopher-ort\",\"sameAs\":[\"https:\\\/\\\/i10x.ai\\\/blog\\\/author\\\/christopher-ort\"],\"worksFor\":{\"@id\":\"https:\\\/\\\/i10x.ai\\\/news\\\/#organization\"},\"alumniOf\":{\"@type\":\"EducationalOrganization\",\"name\":\"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU)\",\"url\":\"https:\\\/\\\/www.fau.eu\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Why Agent Skills Work \u2014 Until Retrieval Collapses - i10X News","description":"Study: agent skills help via procedural anchoring (+6.06 vs workflow memory). Retrieval precision falls from 29.6% to 3.3% as pools grow.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors","og_locale":"en_US","og_type":"article","og_title":"Why Agent Skills Work \u2014 Until Retrieval Collapses - i10X News","og_description":"Study: agent skills help via procedural anchoring (+6.06 vs workflow memory). Retrieval precision falls from 29.6% to 3.3% as pools grow.","og_url":"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors","og_site_name":"i10X News","article_published_time":"2026-10-19T16:49:03+00:00","article_modified_time":"2026-10-19T17:17:37+00:00","og_image":[{"width":1344,"height":768,"url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/demystifying-agent-skills-procedural-anchors-title.webp","type":"image\/webp"}],"author":"Christopher Ort","twitter_card":"summary_large_image","twitter_creator":"@i10x_ai","twitter_site":"@i10x_ai","twitter_misc":{"Written by":"Christopher Ort","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors#article","isPartOf":{"@id":"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors"},"author":{"name":"Christopher Ort","@id":"https:\/\/news.i10x.ai\/#\/schema\/person\/d410bb7ee72febefca2c9c369939219a"},"headline":"Agent &#8220;Skills&#8221; Mostly Anchor Procedures, Not Inject Knowledge \u2014 and Retrieval Breaks Them","datePublished":"2026-10-19T16:49:03+00:00","dateModified":"2026-10-19T17:17:37+00:00","mainEntityOfPage":{"@id":"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors"},"wordCount":395,"commentCount":0,"publisher":{"@id":"https:\/\/news.i10x.ai\/#organization"},"image":{"@id":"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors#primaryimage"},"thumbnailUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/demystifying-agent-skills-procedural-anchors-title.webp","articleSection":["Agent Research","Studies"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors#respond"]}]},{"@type":"WebPage","@id":"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors","url":"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors","name":"Why Agent Skills Work \u2014 Until Retrieval Collapses - i10X News","isPartOf":{"@id":"https:\/\/news.i10x.ai\/#website"},"primaryImageOfPage":{"@id":"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors#primaryimage"},"image":{"@id":"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors#primaryimage"},"thumbnailUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/demystifying-agent-skills-procedural-anchors-title.webp","datePublished":"2026-10-19T16:49:03+00:00","dateModified":"2026-10-19T17:17:37+00:00","description":"Study: agent skills help via procedural anchoring (+6.06 vs workflow memory). Retrieval precision falls from 29.6% to 3.3% as pools grow.","breadcrumb":{"@id":"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors#primaryimage","url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/demystifying-agent-skills-procedural-anchors-title.webp","contentUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/demystifying-agent-skills-procedural-anchors-title.webp","width":1344,"height":768,"caption":"Illustration: i10X"},{"@type":"BreadcrumbList","@id":"https:\/\/i10xnews.kinsta.cloud\/demystifying-agent-skills-procedural-anchors#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/news.i10x.ai\/"},{"@type":"ListItem","position":2,"name":"Agent &#8220;Skills&#8221; Mostly Anchor Procedures, Not Inject Knowledge \u2014 and Retrieval Breaks Them"}]},{"@type":"WebSite","@id":"https:\/\/news.i10x.ai\/#website","url":"https:\/\/news.i10x.ai\/","name":"i10X News","description":"Stay updated with the latest news and announcements from i10X.","publisher":{"@id":"https:\/\/news.i10x.ai\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/news.i10x.ai\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/news.i10x.ai\/#organization","name":"i10X","url":"https:\/\/news.i10x.ai\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/news.i10x.ai\/#\/schema\/logo\/image\/","url":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/i10x-logo-180.png","contentUrl":"https:\/\/i10xnews.kinsta.cloud\/wp-content\/uploads\/2026\/10\/i10x-logo-180.png","width":180,"height":180,"caption":"i10X"},"image":{"@id":"https:\/\/news.i10x.ai\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/i10x_ai","https:\/\/www.linkedin.com\/company\/i10x-ai","https:\/\/instagram.com\/i10x.ai","https:\/\/www.youtube.com\/@i10X_ai_official"]},{"@type":"Person","@id":"https:\/\/news.i10x.ai\/#\/schema\/person\/d410bb7ee72febefca2c9c369939219a","name":"Christopher Ort","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","url":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","contentUrl":"https:\/\/i10x.ai\/news\/wp-content\/uploads\/2026\/10\/christopher-ort-192.webp","caption":"Christopher Ort"},"description":"Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU). He is the author of \u201cThe Style Penalty\u201d, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.","url":"https:\/\/i10x.ai\/news\/author\/christopher-ort","sameAs":["https:\/\/i10x.ai\/blog\/author\/christopher-ort"],"worksFor":{"@id":"https:\/\/i10x.ai\/news\/#organization"},"alumniOf":{"@type":"EducationalOrganization","name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU)","url":"https:\/\/www.fau.eu"}}]}},"_links":{"self":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/6120","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/comments?post=6120"}],"version-history":[{"count":2,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/6120\/revisions"}],"predecessor-version":[{"id":6271,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/posts\/6120\/revisions\/6271"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/media\/6270"}],"wp:attachment":[{"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/media?parent=6120"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/categories?post=6120"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/tags?post=6120"},{"taxonomy":"company","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/companies?post=6120"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/i10x.ai\/news\/wp-json\/wp\/v2\/products?post=6120"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}