[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F90KMMJHV77FDEBHRXSWJ1":3,"skill-same:01M7F90KMMJHV77FDEBHRXSWJ1":76},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7F90KMMJHV77FDEBHRXSWJ1","agent-self-evaluation",null,"Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.","siddu1004\u002FSFP","siddu1004","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F260113491?v=4","01M7F8W1SAJAR49097VRTE1TW5","Siddhardh Vanguri","01M7F8W1SYGY7JE15AHAECCT9R",5,"MIT","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fagent-dev\u002Fskills\u002Fagent-self-evaluation\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: agent-self-evaluation\ndescription: Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.\norigin: ECC\n---\n\n# Agent Self-Evaluation\n\nAfter completing a complex task, the agent pauses to rate its own output against a structured 5-axis rubric. This is NOT a pass\u002Ffail gate — it's a deliberate reflection step that catches omissions, flags overconfidence, and surface areas for improvement before the user has to.\n\n## When to Activate\n\n- After writing code that spans 3+ files or 50+ lines\n- After completing a multi-step workflow (implement → test → review)\n- After a debugging session that involved 3+ attempts\n- After producing a design document, architecture decision, or written analysis\n- When the user asks \"how good was that?\" or \"rate yourself\"\n- At the end of any session Stop hook (if configured — see `references\u002Fhook-integration.md`)\n\n## Core Concepts\n\n### The 5 Evaluation Axes\n\n| Axis | Question | What it catches |\n|---|---|---|\n| **Accuracy** | Are the facts, claims, and outputs correct? | Hallucinations, wrong API names, incorrect syntax, false statements |\n| **Completeness** | Did it cover everything the user asked for? | Missed edge cases, unhandled error paths, forgotten requirements, skipped subtasks |\n| **Clarity** | Is the explanation understandable and well-structured? | Confusing explanations, jargon without definition, missing context, rambling |\n| **Actionability** | Can the user act on the output immediately? | Vague suggestions, missing steps, \"you should X\" without showing how, no verification path |\n| **Conciseness** | Did it use the minimum words\u002Ftokens needed? | Redundancy, over-explanation, repeating the user's question verbatim, filler content |\n\n### Scoring Scale\n\n```\n5 — Exceptional: no reasonable improvement possible\n4 — Good: minor nits only, no substantive gaps\n3 — Adequate: meets the request but has a notable weakness on at least one axis\n2 — Weak: has a clear gap that affects usability or correctness\n1 — Poor: fundamentally misses the request or contains significant errors\n```\n\n### The Evidence Rule\n\nEvery score below 5 MUST cite specific evidence. A score of 3 cannot just say \"could be better\" — it must say exactly what is missing or wrong. The mantra: **\"Show the gap, don't just name it.\"**\n\n## Workflow\n\n### Step 1: Collect the Raw Material\n\nGather what you'll evaluate:\n\n```\n- The original user request (read back from conversation)\n- Your final response\u002Foutput (the deliverable)\n- Any tool outputs that verify correctness (test results, exit codes, lint output)\n- Any user feedback received during the task (corrections, \"try again\", \"that's not right\")\n```\n\n### Step 2: Score Each Axis Independently\n\nWork through the 5 axes one at a time. For each:\n\n1. Read the axis question\n2. Find evidence (or lack of evidence) in the output\n3. Assign a score 1-5\n4. If score \u003C 5, write a one-sentence improvement note citing the gap\n\nDo NOT average the scores in your head first and then work backwards. Score each axis fresh.\n\n### Step 3: Produce the Evaluation Report\n\nUse the template from `templates\u002Fevaluation-report.md`. The report must include:\n\n```\n- One-line summary\n- 5-axis scorecard (score + evidence per axis)\n- Overall score (simple average, rounded to 1 decimal)\n- 1-3 specific improvements ranked by impact\n- Self-check: \"Would the user agree with this assessment?\"\n```\n\n### Step 4: Apply the Improvement\n\nIf any axis scored 3 or below:\n\n1. State what you would do differently\n2. If the gap is fixable in \u003C 30 seconds (missing link, unclear phrasing), fix it now\n3. If the gap requires rework, flag it explicitly: \"This axis scored [reason] because [evidence]. Re-running with [specific fix] would likely raise it to [score].\"\n\n## Code Examples\n\n### Example: Good Evaluation (Score 4+)\n\n```\nTask: Add retry logic to HTTP client\n\nScorecard:\n  Accuracy:    5 — All API calls correct. Verified: retries use\n                  exponential backoff. No hallucinated methods.\n  Completeness: 4 — Covered happy path + 3 error cases. Missing:\n                  timeout handling for hung connections.\n  Clarity:      5 — Code comments explain backoff formula.\n                  PR description links to incident that motivated this.\n  Actionability:5 — Single merge. No follow-up tasks. Tests pass.\n  Conciseness:  4 — 47 lines total. The retry loop could be extracted\n                  into a helper to drop ~8 lines.\n\nOverall: 4.6 — One gap (timeout handling). Fix before merging.\n```\n\n### Example: Weak Evaluation (Score 2-3)\n\n```\nTask: Add retry logic to HTTP client\n\nScorecard:\n  Accuracy:    2 — Used urllib3 which doesn't match our\n                  httpx-based codebase. Wrong library.\n  Completeness: 3 — Works for GET. POST\u002FPUT not handled (user\n                  said \"all HTTP requests\").\n  Clarity:      4 — Code is readable. Good variable names.\n  Actionability:2 — \"Add tests\" mentioned but no test file created.\n                  User has to write tests before merging.\n  Conciseness:  3 — 120 lines. The retry config is duplicated in\n                  3 places instead of one shared RetryConfig object.\n\nOverall: 2.8 — Wrong library used. Needs httpx rewrite.\n  Fix accuracy first (switch to httpx), then extend to all\n  HTTP methods, then consolidate config.\n```\n\n## Anti-Patterns\n\n### \"Everything is a 5\"\n\n```\nFAIL: Accuracy:    5 — All good.\n   Completeness: 5 — Everything covered.\n   Clarity:      5 — Clear.\n```\n\nNo evidence cited. This is self-congratulation, not evaluation. A real 5 requires proving there's nothing to improve.\n\n### Over-penalizing for scope creep\n\n```\nFAIL: Completeness: 2 — Didn't handle WebSocket connections or\n   gRPC streaming (user didn't ask for these)\n```\n\nOnly evaluate against what the user actually requested, not what you could have additionally built.\n\n### Using the evaluation to re-litigate\n\n```\nFAIL: \"As I said earlier, this approach is wrong. Score: 1\"\n```\n\nThe evaluation is about the delivered output, not about re-arguing design decisions that were already made. If the approach was wrong, that should have been caught before delivery.\n\n### Mixing personal preference with objective gaps\n\n```\nFAIL: \"Score: 3. I don't like Python decorators.\"\n```\n\n\"Don't like\" is not evidence. Cite a concrete readability, testability, or correctness concern, or leave the score at 4+.\n\n## Best Practices\n\n- **Evaluate the output, not the process.** The user cares about what you delivered, not how many iterations you took.\n- **One improvement per weak axis.** Don't list 5 things for one axis — pick the highest-impact gap.\n- **Tie improvements to user impact.** \"Missing error handling means the user's API call will crash silently\" beats \"add error handling.\"\n- **Be specific about what 'fixed' looks like.** \"Re-run with httpx transport configured for retries\" beats \"fix the library issue.\"\n- **Use tool outputs as evidence.** If tests passed, cite them. If lint is clean, cite it. Don't guess — grep for the proof.\n- **If you can't find any gaps, try harder.** A perfect score across all 5 axes is rare. Ask: \"If I were the user, what would annoy me about this output?\"\n\n## Related Skills\n\n- `agent-eval` — Head-to-head comparison of different coding agents on benchmark tasks\n- `verification-loop` — Systematic verification of outputs against expected results\n- `security-review` — Security-focused code review checklist\n","# Agent Self-Evaluation\n\nAfter completing a complex task, the agent pauses to rate its own output against a structured 5-axis rubric. This is NOT a pass\u002Ffail gate — it's a deliberate reflection step that catches omissions, flags overconfidence, and surface areas for improvement before the user has to.\n\n## When to Activate\n\n- After writing code that spans 3+ files or 50+ lines\n- After completing a multi-step workflow (implement → test → review)\n- After a debugging session that involved 3+ attempts\n- After producing a design document, architecture decision, or written analysis\n- When the user asks \"how good was that?\" or \"rate yourself\"\n- At the end of any session Stop hook (if configured — see `references\u002Fhook-integration.md`)\n\n## Core Concepts\n\n### The 5 Evaluation Axes\n\n| Axis | Question | What it catches |\n|---|---|---|\n| **Accuracy** | Are the facts, claims, and outputs correct? | Hallucinations, wrong API names, incorrect syntax, false statements |\n| **Completeness** | Did it cover everything the user asked for? | Missed edge cases, unhandled error paths, forgotten requirements, skipped subtasks |\n| **Clarity** | Is the explanation understandable and well-structured? | Confusing explanations, jargon without definition, missing context, rambling |\n| **Actionability** | Can the user act on the output immediately? | Vague suggestions, missing steps, \"you should X\" without showing how, no verification path |\n| **Conciseness** | Did it use the minimum words\u002Ftokens needed? | Redundancy, over-explanation, repeating the user's question verbatim, filler content |\n\n### Scoring Scale\n\n```\n5 — Exceptional: no reasonable improvement possible\n4 — Good: minor nits only, no substantive gaps\n3 — Adequate: meets the request but has a notable weakness on at least one axis\n2 — Weak: has a clear gap that affects usability or correctness\n1 — Poor: fundamentally misses the request or contains significant errors\n```\n\n### The Evidence Rule\n\nEvery score below 5 MUST cite specific evidence. A score of 3 cannot just say \"could be better\" — it must say exactly what is missing or wrong. The mantra: **\"Show the gap, don't just name it.\"**\n\n## Workflow\n\n### Step 1: Collect the Raw Material\n\nGather what you'll evaluate:\n\n```\n- The original user request (read back from conversation)\n- Your final response\u002Foutput (the deliverable)\n- Any tool outputs that verify correctness (test results, exit codes, lint output)\n- Any user feedback received during the task (corrections, \"try again\", \"that's not right\")\n```\n\n### Step 2: Score Each Axis Independently\n\nWork through the 5 axes one at a time. For each:\n\n1. Read the axis question\n2. Find evidence (or lack of evidence) in the output\n3. Assign a score 1-5\n4. If score \u003C 5, write a one-sentence improvement note citing the gap\n\nDo NOT average the scores in your head first and then work backwards. Score each axis fresh.\n\n### Step 3: Produce the Evaluation Report\n\nUse the template from `templates\u002Fevaluation-report.md`. The report must include:\n\n```\n- One-line summary\n- 5-axis scorecard (score + evidence per axis)\n- Overall score (simple average, rounded to 1 decimal)\n- 1-3 specific improvements ranked by impact\n- Self-check: \"Would the user agree with this assessment?\"\n```\n\n### Step 4: Apply the Improvement\n\nIf any axis scored 3 or below:\n\n1. State what you would do differently\n2. If the gap is fixable in \u003C 30 seconds (missing link, unclear phrasing), fix it now\n3. If the gap requires rework, flag it explicitly: \"This axis scored [reason] because [evidence]. Re-running with [specific fix] would likely raise it to [score].\"\n\n## Code Examples\n\n### Example: Good Evaluation (Score 4+)\n\n```\nTask: Add retry logic to HTTP client\n\nScorecard:\n  Accuracy:    5 — All API calls correct. Verified: retries use\n                  exponential backoff. No hallucinated methods.\n  Completeness: 4 — Covered happy path + 3 error cases. Missing:\n                  timeout handling for hung connections.\n  Clarity:      5 — Code comments explain backoff formula.\n                  PR description links to incident that motivated this.\n  Actionability:5 — Single merge. No follow-up tasks. Tests pass.\n  Conciseness:  4 — 47 lines total. The retry loop could be extracted\n                  into a helper to drop ~8 lines.\n\nOverall: 4.6 — One gap (timeout handling). Fix before merging.\n```\n\n### Example: Weak Evaluation (Score 2-3)\n\n```\nTask: Add retry logic to HTTP client\n\nScorecard:\n  Accuracy:    2 — Used urllib3 which doesn't match our\n                  httpx-based codebase. Wrong library.\n  Completeness: 3 — Works for GET. POST\u002FPUT not handled (user\n                  said \"all HTTP requests\").\n  Clarity:      4 — Code is readable. Good variable names.\n  Actionability:2 — \"Add tests\" mentioned but no test file created.\n                  User has to write tests before merging.\n  Conciseness:  3 — 120 lines. The retry config is duplicated in\n                  3 places instead of one shared RetryConfig object.\n\nOverall: 2.8 — Wrong library used. Needs httpx rewrite.\n  Fix accuracy first (switch to httpx), then extend to all\n  HTTP methods, then consolidate config.\n```\n\n## Anti-Patterns\n\n### \"Everything is a 5\"\n\n```\nFAIL: Accuracy:    5 — All good.\n   Completeness: 5 — Everything covered.\n   Clarity:      5 — Clear.\n```\n\nNo evidence cited. This is self-congratulation, not evaluation. A real 5 requires proving there's nothing to improve.\n\n### Over-penalizing for scope creep\n\n```\nFAIL: Completeness: 2 — Didn't handle WebSocket connections or\n   gRPC streaming (user didn't ask for these)\n```\n\nOnly evaluate against what the user actually requested, not what you could have additionally built.\n\n### Using the evaluation to re-litigate\n\n```\nFAIL: \"As I said earlier, this approach is wrong. Score: 1\"\n```\n\nThe evaluation is about the delivered output, not about re-arguing design decisions that were already made. If the approach was wrong, that should have been caught before delivery.\n\n### Mixing personal preference with objective gaps\n\n```\nFAIL: \"Score: 3. I don't like Python decorators.\"\n```\n\n\"Don't like\" is not evidence. Cite a concrete readability, testability, or correctness concern, or leave the score at 4+.\n\n## Best Practices\n\n- **Evaluate the output, not the process.** The user cares about what you delivered, not how many iterations you took.\n- **One improvement per weak axis.** Don't list 5 things for one axis — pick the highest-impact gap.\n- **Tie improvements to user impact.** \"Missing error handling means the user's API call will crash silently\" beats \"add error handling.\"\n- **Be specific about what 'fixed' looks like.** \"Re-run with httpx transport configured for retries\" beats \"fix the library issue.\"\n- **Use tool outputs as evidence.** If tests passed, cite them. If lint is clean, cite it. Don't guess — grep for the proof.\n- **If you can't find any gaps, try harder.** A perfect score across all 5 axes is rare. Ask: \"If I were the user, what would annoy me about this output?\"\n\n## Related Skills\n\n- `agent-eval` — Head-to-head comparison of different coding agents on benchmark tasks\n- `verification-loop` — Systematic verification of outputs against expected results\n- `security-review` — Security-focused code review checklist\n",{"name":5,"origin":24,"description":7},"ECC","main","15fa5201935d2b1d172b4e61c2360c908d876d20","plugins\u002Fagent-dev\u002Fskills\u002Fagent-self-evaluation",0,"https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP","https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fsfp-hive","https:\u002F\u002Fgithub.com\u002Fsiddu1004","I am a student at Amrita Vishwa Vidyapeetham pursuing my BTECH degree in Electronics and Electrical Engineering (2024-2028).","2026-11-09 16:04:40",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add siddu1004\u002FSFP --skill agent-self-evaluation",{"tool":40,"command":41},"bunx","bunx skills add siddu1004\u002FSFP --skill agent-self-evaluation",{"tool":43,"command":44},"pnpm","pnpm dlx skills add siddu1004\u002FSFP --skill agent-self-evaluation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fagent-dev\u002Fskills\u002Fagent-self-evaluation\u002FSKILL.md",true,[48,54,58,62,66,72],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"examples\u002Fhigh-score-example.md","REFERENCE","参考文档",3545,"https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fagent-dev\u002Fskills\u002Fagent-self-evaluation\u002Fexamples\u002Fhigh-score-example.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"examples\u002Flow-score-example.md",3702,"https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fagent-dev\u002Fskills\u002Fagent-self-evaluation\u002Fexamples\u002Flow-score-example.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fevaluation-criteria.md",5820,"https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fagent-dev\u002Fskills\u002Fagent-self-evaluation\u002Freferences\u002Fevaluation-criteria.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fhook-integration.md",2500,"https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fagent-dev\u002Fskills\u002Fagent-self-evaluation\u002Freferences\u002Fhook-integration.md",{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"scripts\u002Fevaluate.py","SCRIPT","脚本",15334,"https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fagent-dev\u002Fskills\u002Fagent-self-evaluation\u002Fscripts\u002Fevaluate.py",{"path":73,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":74,"sourceHtmlUrl":75},"templates\u002Fevaluation-report.md",3485,"https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fagent-dev\u002Fskills\u002Fagent-self-evaluation\u002Ftemplates\u002Fevaluation-report.md",[77,84,91,98,105,112],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7FEEDADZBNBVY19H3XZKCBQ","scientific-schematics","Generates scientific diagram drafts using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.7 Flash for quality review. Refines when the review requests improvement, with at most two generations. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fscientific-schematics\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7FEE0JS04FE58MST48D0MMC","polyhaven-texture-apply","Apply realistic PBR textures from PolyHaven to any Blender object. Supports metals, wood, concrete, fabric, and more. Trigger when asked to texture an object, apply a material from PolyHaven, make something look like metal\u002Fwood\u002Fmarble, or change object surface.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-texture-apply\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7FEDJRWV194TY411WVRS84W","polyhaven-studio-setup","Set up a professional product photography studio in Blender using PolyHaven HDRIs and PBR ground materials. Trigger when asked to create a studio setup, add HDRI lighting, set up product photography, or create a showroom scene.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-studio-setup\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7FED5H2FGS50XGETMGSM0RV","polyhaven-scene-builder","Build complete product scenes using PolyHaven assets — HDRI environment, textured ground\u002Fpedestal, and optional props from the 3D model library. Trigger when asked to build a product scene, create a showcase setup, add a pedestal, or compose a product shot.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-scene-builder\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":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M7FECSNZ2CJA7Z8TPE5R844R","polyhaven-material-swap","Cycle through multiple PolyHaven materials on a product and render each variant. Great for showing color\u002Ffinish options. Trigger when asked to show material variants, swap textures, create color options, show finish comparisons, or render product in different materials.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-material-swap\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":19},"01M7FECBPQ6YWH48PYAMS0C5CE","polyhaven-hdri-showcase","Render the same product across multiple HDRI environments and output a comparison grid. Trigger when asked to compare lighting setups, test different environments, show product in multiple settings, or create an HDRI comparison.","https:\u002F\u002Fgithub.com\u002Fsiddu1004\u002FSFP\u002Fblob\u002Fmain\u002Fplugins\u002Fscience-hardware\u002Fskills\u002Fpolyhaven-hdri-showcase\u002FSKILL.md",[],[]]