{"id":106543,"date":"2026-04-10T17:28:41","date_gmt":"2026-04-10T11:58:41","guid":{"rendered":"https:\/\/www.guvi.in\/blog\/?p=106543"},"modified":"2026-04-10T17:28:43","modified_gmt":"2026-04-10T11:58:43","slug":"building-skills-for-claude-code","status":"publish","type":"post","link":"https:\/\/www.guvi.in\/blog\/building-skills-for-claude-code\/","title":{"rendered":"Building Skills for Claude Code: Automating your procedural knowledge"},"content":{"rendered":"\n<p>Every software team runs on two kinds of knowledge. The first kind is easy to find, it lives in docs, textbooks, and Stack Overflow. The second kind is harder. It lives in people&#8217;s heads, built up over years of working together on the same codebase.<\/p>\n\n\n\n<p>That second kind is called procedural knowledge. It is the step-by-step, &#8220;here is how we do it on this team&#8221; knowledge behind every pull request, every deployment, and every code review. And right now, your team is manually re-explaining it to Claude Code every single time.<\/p>\n\n\n\n<p>In this article, you will learn how Skills for Claude Code lets you encode that knowledge once and have it run automatically from that point forward, every time, without re-explaining.<\/p>\n\n\n\n<p><strong>Quick TL;DR Summary<\/strong><\/p>\n\n\n\n<ol>\n<li>This blog explains what procedural knowledge is and why it is the missing piece in most teams&#8217; Claude Code setups.<br><\/li>\n\n\n\n<li>It covers what Skills actually do, how they automate your team&#8217;s processes, and why that automation is more valuable than just saving time on individual tasks.<br><\/li>\n\n\n\n<li>You will learn how to identify which procedural knowledge is worth turning into a Skill and how to write Skill instructions that actually work in practice.<br><\/li>\n\n\n\n<li>The article includes a step-by-step guide to building your first Skill, a concrete real-world example, and honest pros and cons of the approach.<br><\/li>\n\n\n\n<li>It also covers common mistakes to avoid and practical tips to get started without overcomplicating things.<\/li>\n<\/ol>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>What Is Procedural Knowledge and Why Does It Matter for Claude Code?<\/strong><\/h2>\n\n\n\n<p>Procedural knowledge is the &#8220;how&#8221; behind your work. Not &#8220;what is a code review&#8221; but &#8220;how do we do code reviews on this team.&#8221; Not &#8220;what is a deployment&#8221; but &#8220;what are the exact steps we follow before we push to production.&#8221;<\/p>\n\n\n\n<p>It is the kind of knowledge that takes a new developer months to absorb, not because the concepts are hard, but because no one ever wrote it all down in one usable place. It gets passed on through review comments, Slack threads, and the occasional incident that teaches everyone something the hard way.<\/p>\n\n\n\n<p>When you try to use <a href=\"https:\/\/www.guvi.in\/blog\/what-is-claude-code\/\" target=\"_blank\" rel=\"noreferrer noopener\">Claude Code<\/a> for specialized work without giving it this knowledge, the gap shows up immediately. The tool is capable, but it does not know your process. It does not know your standards. It does not know what your team considers done. So it guesses, someone corrects it, and then it guesses the same way again next time because it still does not know.<\/p>\n\n\n\n<p>Skills are how you close that gap permanently by automating the application of your procedural knowledge across every task.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Why Teams Are Building Skills for Claude Code<\/strong><\/h2>\n\n\n\n<ul>\n<li>Processes run automatically every time instead of only when someone remembers to ask for them.<br><\/li>\n\n\n\n<li>Standards travel with the task so Claude Code does not need to be reminded what your team cares about each session.<br><\/li>\n\n\n\n<li>Senior engineers&#8217; approaches become available on every task, not just the ones those engineers happen to touch personally.<br><\/li>\n\n\n\n<li>New team members get access to the team&#8217;s accumulated process knowledge from day one instead of spending weeks absorbing it informally.<br><\/li>\n\n\n\n<li>Institutional knowledge stops walking out the door when people leave because it is encoded in Skills that belong to the team, not to individuals.<br><\/li>\n\n\n\n<li>Edge cases get handled consistently because the Skill includes the guidance your team has already figured out from real experience.<\/li>\n<\/ul>\n\n\n\n<div style=\"background-color: #099f4e; border: 3px solid #110053; border-radius: 12px; padding: 18px 22px; color: #FFFFFF; font-size: 18px; font-family: Montserrat, Helvetica, sans-serif; line-height: 1.7; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.15); max-width: 750px;\">\n  <strong style=\"font-size: 22px; color: #FFFFFF;\">\ud83d\udca1 Did You Know?<\/strong> \n  <br \/><br \/>\n  Research from <strong style=\"color: #110053;\">Stanford\u2019s AI Lab<\/strong> shows that agents given <strong style=\"color: #110053;\">structured, task-specific instructions<\/strong> complete complex workflows with up to <strong style=\"color: #110053;\">60% fewer errors<\/strong> compared to open-ended reasoning. Providing <strong style=\"color: #110053;\">Claude Code<\/strong> with the right <strong style=\"color: #110053;\">skills and structure<\/strong> is not just convenient \u2014 it makes the system <strong style=\"color: #110053;\">measurably more reliable<\/strong>.\n  <br \/><br \/>\n<\/div>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>4 Types of Procedural Knowledge Worth Automating as Skills<\/strong><\/h2>\n\n\n\n<ol>\n<li><strong>Code review standards.&nbsp;<\/strong><\/li>\n<\/ol>\n\n\n\n<p>Your team has specific things it cares about. Security patterns, performance red flags, naming conventions, test coverage expectations. A Skill encodes all of that so <a href=\"https:\/\/www.guvi.in\/blog\/bringing-code-review-to-claude-code\/\" target=\"_blank\" rel=\"noreferrer noopener\">Claude Code reviews<\/a> code the way your senior engineers would, consistently, on every single review.<\/p>\n\n\n\n<ol start=\"2\">\n<li><strong>Project and service setup.&nbsp;<\/strong><\/li>\n<\/ol>\n\n\n\n<p>Starting a new service involves dozens of small decisions your team has already figured out. Folder structure, configuration conventions, CI\/CD setup, default dependencies. A Skill automates all of those decisions so every new project starts the right way without anyone having to remember the full checklist.<\/p>\n\n\n\n<ol start=\"3\">\n<li><strong>Debugging approaches.&nbsp;<\/strong><\/li>\n<\/ol>\n\n\n\n<p>Senior engineers do not randomly poke at a bug. They follow a process. Check the logs, isolate the component, reproduce in isolation, and narrow down the cause. A Skill gives Claude Code that same structured approach so every debugging session starts from the right place.<\/p>\n\n\n\n<ol start=\"4\">\n<li><strong>Pre-deployment procedures.&nbsp;<\/strong><\/li>\n<\/ol>\n\n\n\n<p>These are the highest-stakes processes most teams have. A skill encoding your exact pre-deployment checks, rollback procedure, and post-deployment verification steps is worth a lot when things are moving fast and no one wants to forget a step.<\/p>\n\n\n\n<p><strong>Read More: <\/strong><a href=\"https:\/\/www.guvi.in\/blog\/how-to-use-claude-code\/\" target=\"_blank\" rel=\"noreferrer noopener\">How to Use Claude Code: A Beginner\u2019s Guide<\/a><\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Step-by-Step: How to Build a Skill That Automates Your Procedural Knowledge<\/strong><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 1: Observe the process, not just your memory of it<\/strong><\/h3>\n\n\n\n<p>Before writing anything, watch the process actually happen. Run through a real code review while noting every decision. Do a real debugging session and track every step. The gap between the process you describe from memory and the process that actually happens is usually significant. Start from reality, not from what you think you do.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 2: Write every step as if you are explaining it to someone on their first day<\/strong><\/h3>\n\n\n\n<p>The best Skill instructions are specific enough that a smart new team member with no prior context could follow them and get a good result. If you find yourself writing something vague like &#8220;review the code carefully,&#8221; stop and ask what carefully actually means on your team. The answer to that question is the instruction you need to write.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 3: Include your non-negotiables as explicit rules<\/strong><\/h3>\n\n\n\n<p>Every team has things that are absolute. We always write tests for new functions. We never push directly to the main. We always include error handling. These need to be in the Skill as rules, not suggestions. <a href=\"https:\/\/claude.com\/product\/claude-code\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">Claude Code<\/a> follows explicit rules consistently. It treats vague preferences inconsistently.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 4: Add examples of good and bad outputs<\/strong><\/h3>\n\n\n\n<p>Examples do more work than instructions alone. Show Claude Code what a good pull request comment looks like next to a vague one. Show what a properly structured commit message looks like compared to a useless one. The contrast teaches the standard faster than any abstract description.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 5: Build in the edge cases your team has already learned the hard way<\/strong><\/h3>\n\n\n\n<p>Every team has situations where the standard process does not quite fit and someone figured out the right way to handle it. Write those into the Skill. That is where the automation earns its value most clearly, because it means Claude Code handles the hard case the smart way automatically instead of guessing.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 6: Load the Skill and test it with real work, not toy examples<\/strong><\/h3>\n\n\n\n<p>Take three actual pull requests your team has already reviewed and run Claude Code through them using the Skill. Compare the output to what your engineers actually commented. The gaps you find are exactly the places where the Skill needs more detail.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 7: Refine based on what breaks<\/strong><\/h3>\n\n\n\n<p>The first version of any Skill handles the common case well and misses edge cases you did not anticipate. That is normal. Update the Skill when real work exposes a gap and the update is immediately live across every future task. Treat Skill building as an ongoing practice, not a one-time setup.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 8: Keep humans in the loop for high-stakes outputs<\/strong><\/h3>\n\n\n\n<p>Skills make Claude Code more reliable. They do not make it perfect. For anything where a mistake has real consequences, keep a human review step in the process. Use the time the automation saves to give humans more capacity to review carefully, not to remove review entirely.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>A Real Example: Automating a Code Review Process<\/strong><\/h2>\n\n\n\n<p>Imagine your backend team always checks five things during API code reviews: input validation, correct error codes, no database queries inside loops, proper authentication, and no sensitive data in logs.<\/p>\n\n\n\n<p>Without a Skill, Claude Code might catch some of these on a good day and miss others the next. It has no way of knowing these five things are what your team actually cares about.<\/p>\n\n\n\n<p>With a Skill, you write those five checks as explicit steps, add examples of good and bad reviews, and Claude Code follows that process automatically on every single review, not just when the prompt happens to be detailed enough.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Features That Make Skill-Based Automation Powerful<\/strong><\/h2>\n\n\n\n<ol>\n<li><strong>Zero re-explanation overhead.&nbsp;<\/strong><\/li>\n<\/ol>\n\n\n\n<p>Once a Skill is built, Claude Code knows your process before you describe the task. The context is already there.<\/p>\n\n\n\n<ol start=\"2\">\n<li><strong>Consistent output every time.&nbsp;<\/strong><\/li>\n<\/ol>\n\n\n\n<p>The Skill defines the standard. Claude Code follows it on every task, with no variation based on how the prompt was phrased that day.<\/p>\n\n\n\n<ol start=\"3\">\n<li><strong>Expertise at scale.&nbsp;<\/strong><\/li>\n<\/ol>\n\n\n\n<p>One Skill built on your best engineer&#8217;s approach applies that approach to every task, not just the ones that engineer personally handles.<\/p>\n\n\n\n<ol start=\"4\">\n<li><strong>Living institutional memory.&nbsp;<\/strong><\/li>\n<\/ol>\n\n\n\n<p>Unlike a wiki page that goes stale, a Skill gets tested constantly against real work and updated when something does not fit. It stays accurate because it is actively used.<\/p>\n\n\n\n<ol start=\"5\">\n<li><strong>Modular and updatable.&nbsp;<\/strong><\/li>\n<\/ol>\n\n\n\n<p>When your standards evolve, you update the Skill and the new standard applies immediately to every task from that point forward. Nothing else needs to change.<\/p>\n\n\n\n<ol start=\"6\">\n<li><strong>Reusable across the team.&nbsp;<\/strong><\/li>\n<\/ol>\n\n\n\n<p>A well-built Skill belongs to the team, not to the person who built it. Every team member gets the same consistent behavior from Claude Code automatically.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Pros and Cons of Building Skills for Claude Code<\/strong><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Pros:<\/strong><\/h3>\n\n\n\n<ul>\n<li>Claude Code becomes genuinely useful for specialized work instead of defaulting to generic best practices that may not fit your team.<br><\/li>\n\n\n\n<li>Processes run automatically every time instead of relying on someone remembering to ask for them.<br><\/li>\n\n\n\n<li>Senior engineers&#8217; accumulated knowledge gets applied consistently across every task, not just the ones they happen to review.<br><\/li>\n\n\n\n<li>Skills are reusable and shareable across the whole team without being rebuilt.<br><\/li>\n\n\n\n<li>Institutional knowledge stays with the team even when people leave.<br><\/li>\n\n\n\n<li>Skills get better over time as they are tested against real work and refined.<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Cons:<\/strong><\/h3>\n\n\n\n<ul>\n<li>Writing good skills takes real time and iteration upfront, especially if the process has never been written down before.<br><\/li>\n\n\n\n<li>Skills need maintenance as your team&#8217;s standards, tools, and processes evolve.<br><\/li>\n\n\n\n<li>Poorly written Skill instructions can make Claude Code less reliable than no Skill at all if the instructions are contradictory or too vague.<br><\/li>\n\n\n\n<li>Automating a broken process makes the broken process run faster. If your current approach has problems, fix those before encoding it into a Skill.<br><\/li>\n\n\n\n<li>High-stakes work still needs human review. Skills improve consistency, they do not replace judgment.<\/li>\n<\/ul>\n\n\n\n<div style=\"background-color: #099f4e; border: 3px solid #110053; border-radius: 12px; padding: 18px 22px; color: #FFFFFF; font-size: 18px; font-family: Montserrat, Helvetica, sans-serif; line-height: 1.7; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.15); max-width: 750px;\">\n  <strong style=\"font-size: 22px; color: #FFFFFF;\">\ud83d\udca1 Did You Know?<\/strong> \n  <br \/><br \/>\n  A <strong style=\"color: #110053;\">2024 McKinsey report<\/strong> found that organizations using <strong style=\"color: #110053;\">AI tools with specialized, task-specific instruction sets<\/strong> achieved <strong style=\"color: #110053;\">30\u201350% productivity gains<\/strong> in targeted workflows. In contrast, teams relying on <strong style=\"color: #110053;\">general-purpose AI<\/strong> without structured capabilities saw only <strong style=\"color: #110053;\">single-digit improvements<\/strong>. This highlights that <strong style=\"color: #110053;\">specialization<\/strong> is what transforms AI from a novelty into <strong style=\"color: #110053;\">real business impact<\/strong>.\n  <br \/><br \/>\n<\/div>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Top Tips to Get Started<\/strong><\/h2>\n\n\n\n<ol>\n<li><strong>Start with one Skill, not ten.&nbsp;<\/strong><\/li>\n<\/ol>\n\n\n\n<p>Pick the single most repetitive specialized task your team handles and build one Skill for it. Get that working reliably before adding more. Teams that try to automate everything at once usually end up with nothing that works properly.<\/p>\n\n\n\n<ol start=\"2\">\n<li><strong>Write instructions the way you would explain the process to a new hire.&nbsp;<\/strong><\/li>\n<\/ol>\n\n\n\n<p>If the instruction would confuse a smart person on their first day, it would confuse Claude Code too. Clarity is the whole job.<\/p>\n\n\n\n<ol start=\"3\">\n<li><strong>Include examples in every Skill you build.&nbsp;<\/strong><\/li>\n<\/ol>\n\n\n\n<p>Examples are one of the most effective tools in Skill writing. Show Claude Code what a good output looks like and what a bad one looks like. The contrast teaches the standard better than any amount of abstract description.<\/p>\n\n\n\n<ol start=\"4\">\n<li><strong>Build feedback loops into your workflow.&nbsp;<\/strong><\/li>\n<\/ol>\n\n\n\n<p>Create a simple way for your team to flag when a Skill&#8217;s output is off. Use that feedback to update the Skill regularly. The teams with the best Skills treat them as living documents, not finished configurations.<\/p>\n\n\n\n<ol start=\"5\">\n<li><strong>Automate the process you actually have, not the one you wish you had.<\/strong>&nbsp;<\/li>\n<\/ol>\n\n\n\n<p>If your current process is inconsistent or unclear, building a Skill will make that inconsistency run automatically. Fix the process first, then encode it.<\/p>\n\n\n\n<p>If you want to learn more about building skills for Claude Code and automating your procedural knowledg<strong>e<\/strong>, do not miss the chance to enroll in HCL GUVI&#8217;s <strong>Intel &amp; IITM Pravartak Certified <\/strong><a href=\"https:\/\/www.guvi.in\/mlp\/artificial-intelligence-and-machine-learning?utm_source=blog&amp;utm_medium=hyperlink&amp;utm_campaign=building-skills-for-claude-code-and-automating-your-procedural-knowledge\" target=\"_blank\" rel=\"noreferrer noopener\"><strong>Artificial Intelligence &amp; Machine Learning course<\/strong><\/a><strong>. <\/strong>Endorsed with <strong>Intel certification<\/strong>, this course adds a globally recognized credential to your resume, a powerful edge that sets you apart in the competitive AI job market.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Conclusion<\/strong><\/h2>\n\n\n\n<p>Procedural knowledge is the most valuable and most fragile asset most engineering teams have. It is expensive to build, hard to preserve, and easy to lose. Every time someone re-explains a process to Claude Code, every time a standard gets applied inconsistently, every time a new team member spends weeks learning &#8220;how we do things here,&#8221; the cost of not automating that knowledge shows up somewhere.<\/p>\n\n\n\n<p>Skills for Claude Code give you a practical path to change that. Capture the knowledge once. Write it clearly. Test it against real work. Let it run automatically from then on.<\/p>\n\n\n\n<p>The overhead of explaining your process every session goes away. The inconsistency that comes from relying on whoever happens to be handling a task goes away. The institutional knowledge that would have walked out the door with your last senior engineer stays inside your team&#8217;s workflow, running automatically every time it is needed. Start with one process. Build it properly. Then do the next one.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>FAQs<\/strong><\/h2>\n\n\n<div id=\"rank-math-faq\" class=\"rank-math-block\">\n<div class=\"rank-math-list \">\n<div id=\"faq-question-1775799875558\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \">1. <strong>What is the difference between giving Claude Code instructions in a prompt and building a Skill?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>A prompt instruction disappears after the session ends. Claude Code has no memory of it the next time. A Skill is a permanent, reusable instruction set that runs automatically every time Claude Code handles that kind of task, without anyone having to re-explain it.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1775799884376\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \">2. <strong>How many Skills should one team build?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Start with one and get it working really well before adding more. A focused team with two or three well-built Skills will outperform a team with ten half-finished ones. More Skills means more complexity and more maintenance. Add a new Skill only when there is a clear, recurring need for it.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1775799896326\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \">3. <strong>How do I know if a Skill is actually working?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Test it against real tasks your team has already completed and compare the output to what your team actually produced. A working Skill produces outputs your team would be comfortable using without significant editing. If the output regularly needs heavy revision, the Skill instructions need more work.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1775799907428\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \">4. <strong>What happens when our process changes?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>You update the Skill. That is one of the main advantages of encoding your process this way. When your standards evolve, you update the Skill once and the new standard applies immediately to every future task. You do not have to retrain anyone or update multiple documents. The Skill is the single source of truth.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1775799934307\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \">5. <strong>Can the same Skill be used by multiple team members?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Yes, and this is one of the most valuable things about building Skills properly. A well-built code review Skill, for example, gives every team member access to the same consistent process and standards. The approach your best engineers use becomes the approach every team member gets from Claude Code automatically.<\/p>\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>Every software team runs on two kinds of knowledge. The first kind is easy to find, it lives in docs, textbooks, and Stack Overflow. The second kind is harder. It lives in people&#8217;s heads, built up over years of working together on the same codebase. That second kind is called procedural knowledge. It is the [&hellip;]<\/p>\n","protected":false},"author":63,"featured_media":106582,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[933],"tags":[],"views":"23","authorinfo":{"name":"Vishalini Devarajan","url":"https:\/\/www.guvi.in\/blog\/author\/vishalini\/"},"thumbnailURL":"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/04\/Claude-Code-1-1-300x112.webp","jetpack_featured_media_url":"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/04\/Claude-Code-1-1.webp","_links":{"self":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/106543"}],"collection":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/users\/63"}],"replies":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/comments?post=106543"}],"version-history":[{"count":4,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/106543\/revisions"}],"predecessor-version":[{"id":106585,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/106543\/revisions\/106585"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/media\/106582"}],"wp:attachment":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/media?parent=106543"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/categories?post=106543"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/tags?post=106543"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}