[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6WZVP6786Z0RVT8H8QDXN4R":3,"skill-same:01M6WZVP6786Z0RVT8H8QDXN4R":63},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":44,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M6WZVP6786Z0RVT8H8QDXN4R","error-recovery",null,"Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.","microsoft\u002Fwaza","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M6WZT4PAP160SPCF851532KH",1511,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ferror-recovery\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32],"error recovery","recovery","error","squad","report","coordination","just","reliability","patterns","adapt","high","for","standard","when","2026-11-10 10:12:30",false,"---\nname: \"error-recovery\"\ndescription: \"Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.\"\ndomain: \"reliability, agent-coordination\"\nconfidence: \"high\"\nlicense: MIT\n---\n\n# Error Recovery Patterns\n\nStandard recovery patterns for all squad agents. When something fails, **adapt** — don't just report the failure.\n\n---\n\n## 1. Retry with Backoff\n\n**When:** Transient failures — API timeouts, rate limits, network errors, temporary service unavailability.\n\n**Pattern:**\n1. Wait briefly, then retry (start at 2s, double each attempt)\n2. Maximum 3 retries before escalating\n3. Log each attempt with the error received\n\n**Example:** API call returns 429 Too Many Requests → wait 2s → retry → wait 4s → retry → wait 8s → retry → escalate if still failing.\n\n---\n\n## 2. Fallback Alternatives\n\n**When:** Primary tool or approach fails and an alternative exists.\n\n**Pattern:**\n1. Attempt primary approach\n2. On failure, identify alternative tool\u002Fmethod\n3. Try the alternative with the same intent\n4. Document which alternative was used and why\n\n**Example:** Primary CLI tool fails → fall back to direct API call for the same operation.\n\n---\n\n## 3. Diagnose-and-Fix\n\n**When:** Build failures, test failures, linting errors — structured errors with actionable output.\n\n**Pattern:**\n1. Read the full error output carefully\n2. Identify the root cause from error messages\n3. Attempt a targeted fix\n4. Re-run to verify the fix\n5. Maximum 3 fix-retry cycles before escalating\n\n**Example:** Build fails with a type error → check for missing import → add it → rebuild.\n\n---\n\n## 4. Escalate with Context\n\n**When:** Recovery attempts have been exhausted, or the failure requires human judgment.\n\n**Pattern:**\n1. Summarize what was attempted and what failed\n2. Include the exact error messages\n3. State what you believe the root cause is\n4. Suggest next steps or who might be able to help\n5. Hand off to the coordinator or the appropriate specialist\n\n**Example:** After 3 failed build attempts → \"Build fails on line 42 with null reference. Tried X, Y, Z. Likely a design issue in the Foo module. Recommend the code owner review.\"\n\n---\n\n## 5. Graceful Degradation\n\n**When:** A non-critical step fails but the overall task can still deliver value.\n\n**Pattern:**\n1. Determine if the failed step is critical to the task outcome\n2. If non-critical, log the failure and continue\n3. Deliver partial results with a clear note of what was skipped\n4. Offer to retry the skipped step separately\n\n**Example:** Generating a report with 5 sections — section 3 data source is unavailable → produce the report with 4 sections, note that section 3 was skipped and why.\n\n---\n\n## Applying These Patterns\n\nEach agent should reference these patterns in their charter's `## Error Recovery` section, tailored to their domain. The charter should list the agent's most common failure modes and map each to the appropriate pattern above.\n\n**Selection guide:**\n\n| Failure Type | Primary Pattern | Fallback Pattern |\n|---|---|---|\n| Network\u002FAPI transient | Retry with Backoff | Escalate with Context |\n| Tool\u002Fdependency missing | Fallback Alternatives | Escalate with Context |\n| Build\u002Ftest error | Diagnose-and-Fix | Escalate with Context |\n| Auth\u002Fpermissions | Retry with Backoff | Escalate with Context |\n| Non-critical data missing | Graceful Degradation | — |\n| Unknown\u002Fnovel error | Escalate with Context | — |\n","# Error Recovery Patterns\n\nStandard recovery patterns for all squad agents. When something fails, **adapt** — don't just report the failure.\n\n---\n\n## 1. Retry with Backoff\n\n**When:** Transient failures — API timeouts, rate limits, network errors, temporary service unavailability.\n\n**Pattern:**\n1. Wait briefly, then retry (start at 2s, double each attempt)\n2. Maximum 3 retries before escalating\n3. Log each attempt with the error received\n\n**Example:** API call returns 429 Too Many Requests → wait 2s → retry → wait 4s → retry → wait 8s → retry → escalate if still failing.\n\n---\n\n## 2. Fallback Alternatives\n\n**When:** Primary tool or approach fails and an alternative exists.\n\n**Pattern:**\n1. Attempt primary approach\n2. On failure, identify alternative tool\u002Fmethod\n3. Try the alternative with the same intent\n4. Document which alternative was used and why\n\n**Example:** Primary CLI tool fails → fall back to direct API call for the same operation.\n\n---\n\n## 3. Diagnose-and-Fix\n\n**When:** Build failures, test failures, linting errors — structured errors with actionable output.\n\n**Pattern:**\n1. Read the full error output carefully\n2. Identify the root cause from error messages\n3. Attempt a targeted fix\n4. Re-run to verify the fix\n5. Maximum 3 fix-retry cycles before escalating\n\n**Example:** Build fails with a type error → check for missing import → add it → rebuild.\n\n---\n\n## 4. Escalate with Context\n\n**When:** Recovery attempts have been exhausted, or the failure requires human judgment.\n\n**Pattern:**\n1. Summarize what was attempted and what failed\n2. Include the exact error messages\n3. State what you believe the root cause is\n4. Suggest next steps or who might be able to help\n5. Hand off to the coordinator or the appropriate specialist\n\n**Example:** After 3 failed build attempts → \"Build fails on line 42 with null reference. Tried X, Y, Z. Likely a design issue in the Foo module. Recommend the code owner review.\"\n\n---\n\n## 5. Graceful Degradation\n\n**When:** A non-critical step fails but the overall task can still deliver value.\n\n**Pattern:**\n1. Determine if the failed step is critical to the task outcome\n2. If non-critical, log the failure and continue\n3. Deliver partial results with a clear note of what was skipped\n4. Offer to retry the skipped step separately\n\n**Example:** Generating a report with 5 sections — section 3 data source is unavailable → produce the report with 4 sections, note that section 3 was skipped and why.\n\n---\n\n## Applying These Patterns\n\nEach agent should reference these patterns in their charter's `## Error Recovery` section, tailored to their domain. The charter should list the agent's most common failure modes and map each to the appropriate pattern above.\n\n**Selection guide:**\n\n| Failure Type | Primary Pattern | Fallback Pattern |\n|---|---|---|\n| Network\u002FAPI transient | Retry with Backoff | Escalate with Context |\n| Tool\u002Fdependency missing | Fallback Alternatives | Escalate with Context |\n| Build\u002Ftest error | Diagnose-and-Fix | Escalate with Context |\n| Auth\u002Fpermissions | Retry with Backoff | Escalate with Context |\n| Non-critical data missing | Graceful Degradation | — |\n| Unknown\u002Fnovel error | Escalate with Context | — |\n",{"name":5,"domain":38,"license":15,"confidence":29,"description":7},"reliability, agent-coordination","main","116214a33b5e07766539f64c0ea21521467829bf",".github\u002Fskills\u002Ferror-recovery",101,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza","https:\u002F\u002Fmicrosoft.github.io\u002Fwaza\u002F","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-15 04:18:35",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add microsoft\u002Fwaza --skill error-recovery",{"tool":55,"command":56},"bunx","bunx skills add microsoft\u002Fwaza --skill error-recovery",{"tool":58,"command":59},"pnpm","pnpm dlx skills add microsoft\u002Fwaza --skill error-recovery","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ferror-recovery\u002FSKILL.md",true,[],[64,99,125,154,174,186],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":78,"publishedAt":33},"01M6X00A438VG96V20V1VMDHCM","waza-runner","Run evaluations on Agent Skills to measure their effectiveness. \nUSE FOR: \"run skill evals\", \"evaluate my skill\", \"test skill quality\", \n\"check skill triggers\", \"skill compliance check\", \"measure skill performance\",\n\"run evals on [skill-name]\", \"grade skill execution\".\nDO NOT USE FOR: writing skills (use skill-authoring), improving frontmatter \n(use sensei), or general testing unrelated to skills.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Fwaza-runner\u002FSKILL.md",[70,75],{"categoryNo":71,"categoryName":72,"taxonomyType":73,"taxonomyTypeDesc":74},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":76,"categoryName":77,"taxonomyType":73,"taxonomyTypeDesc":74},"01JBSEEDCAT000000000000023","Skill与智能体开发",[79,80,81,82,83,84,85,86,87,30,88,89,90,91,92,93,94,95,96,97,98],"waza runner","runner","waza","frontmatter","run","triggers","do","my","general","evals","unrelated","writing skills","my skill","sensei","Test Skill","run evals","performance","writing","testing","authoring",{"skillNo":100,"name":81,"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":106,"publishedAt":33},"01M6X003ZZKY5WQ5SWPAQ3MJMS","**WORKFLOW SKILL** - Evaluate AI agent skills using structured benchmarks with YAML specs, fixture isolation, and pluggable validators. USE FOR: run waza, waza help, run eval, run benchmark, evaluate skill, test agent, generate eval suite, init eval, compare results, score agent, agent evaluation, skill testing, cross-model comparison. DO NOT USE FOR: improving skill frontmatter (use waza dev), creating new skills from scratch (use skill-creator), token counting or budget checks (use waza tokens). INVOKES: Copilot SDK executor, mock engine, code\u002Fregex validators. FOR SINGLE OPERATIONS: use waza run directly for a single benchmark.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Fskills\u002Fwaza\u002FSKILL.md",[104,105],{"categoryNo":71,"categoryName":72,"taxonomyType":73,"taxonomyTypeDesc":74},{"categoryNo":76,"categoryName":77,"taxonomyType":73,"taxonomyTypeDesc":74},[81,83,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,97,122,123,124],"workflow skill","executor","fixture","eval","compare results","model","Evaluation","evaluate skill","code","eval suite","generate","copilot","init","workflow","ai agent","counting","new","skill-creator",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":140,"publishedAt":33},"01M6WZZZHCTPZ8YF9564J3QJVT","waza-interactive","Interactive workflow partner for creating, testing, and improving AI agent skills with waza. USE FOR: run my evals, check my skill, compare models, create eval suite, debug failing tests, is my skill ready, ship readiness, interpret results, improve score. DO NOT USE FOR: general coding, non-skill work, writing skill content (use skill-authoring), improving frontmatter only (use sensei).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Fskills\u002Fwaza-interactive\u002FSKILL.md",[131,132,137],{"categoryNo":76,"categoryName":77,"taxonomyType":73,"taxonomyTypeDesc":74},{"categoryNo":133,"categoryName":134,"taxonomyType":135,"taxonomyTypeDesc":136},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":138,"categoryName":139,"taxonomyType":135,"taxonomyTypeDesc":136},"01JBSEEDCAT000000000000036","内容创作者",[141,81,142,143,96,97,121,144,145,116,30,98,85,87,88,146,147,148,110,149,150,91,83,151,152,92,153,120],"waza interactive","interactive","tests","use","general coding","ready","only","failing","work","improve","create","debug","create eval",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":161,"publishedAt":33},"01M6WZZTQR955SVJ02J33DGQYK","code-explainer","Explains code snippets in plain English, breaking down what the code does step by step. Perfect for learning, code reviews, or documentation.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Fskills\u002Fcode-explainer\u002FSKILL.md",[160],{"categoryNo":133,"categoryName":134,"taxonomyType":135,"taxonomyTypeDesc":136},[162,163,115,164,165,166,30,167,168,169,170,171,172,173],"code explainer","explainer","learning","plain","down","reviews","step by step","english","snippets","what the","plain english","documentation",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":33},"01M6WZZR27J4RE4J10M38ECM26","compatibility-skill","Read fixture status and report whether it is ready.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Finternal\u002Ftestdata\u002Fcompatibility\u002Fv1\u002FSKILL.md",[],[181,182,183,109,146,184,23,185],"compatibility skill","compatibility","it","read","status",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":192,"publishedAt":33},"01M6WZZMYWAKWE36WD4PHQK8V2","evidence-judge","Read a supplied report and summarize its recorded status and numeric items.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fwaza\u002Fblob\u002Fmain\u002Fexamples\u002Fevidence-judge\u002FSKILL.md",[],[193,194,195,184,23,185,196],"evidence","evidence judge","judge","summarize"]