[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CB3EXSJNWYSENK87N8CF4W":3,"skill-same:01M7CB3EXSJNWYSENK87N8CF4W":52},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M7CB3EXSJNWYSENK87N8CF4W","sf-ai-agentforce-testing",null,"Agentforce agent testing with dual-track workflow and 100-point scoring. TRIGGER when: user tests Agentforce agents, runs sf agent test commands, creates test specs, validates topic routing, or analyzes agent test coverage. DO NOT TRIGGER when: Apex unit tests (use sf-testing), building agents (use sf-ai-agentforce), or Agent Script DSL (use sf-ai-agentscript).","om-scogo\u002Fskillsh-scraper","om-scogo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160466840?v=4","01M79AWB6DFVCQ7RK70CS34B96","Om Achrekar","01M79AWB6ZM9SKR8KDH1WSSM22",0,"MIT","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fjaganpro-sf-skills\u002Fsf-ai-agentforce-testing\u002Fskills\u002Fsf-ai-agentforce-testing\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sf-ai-agentforce-testing\ndescription: >\n  Agentforce agent testing with dual-track workflow and 100-point scoring.\n  TRIGGER when: user tests Agentforce agents, runs sf agent test commands, creates\n  test specs, validates topic routing, or analyzes agent test coverage.\n  DO NOT TRIGGER when: Apex unit tests (use sf-testing), building agents\n  (use sf-ai-agentforce), or Agent Script DSL (use sf-ai-agentscript).\nlicense: MIT\ncompatibility: \"Requires API v66.0+ (Spring '26) and Agentforce enabled org\"\nmetadata:\n  version: \"2.1.0\"\n  author: \"Jag Valaiyapathy\"\n  scoring: \"100 points across 7 categories\"\n---\n\n# sf-ai-agentforce-testing: Agentforce Test Execution & Coverage Analysis\n\nUse this skill when the user needs **formal Agentforce testing**: multi-turn conversation validation, CLI Testing Center specs, topic\u002Faction coverage analysis, preview checks, or a structured test-fix loop after publish.\n\n## When This Skill Owns the Task\n\nUse `sf-ai-agentforce-testing` when the work involves:\n- `sf agent test` workflows\n- multi-turn Agent Runtime API testing\n- topic routing, action invocation, context preservation, guardrail, or escalation validation\n- test-spec generation and coverage analysis\n- post-publish \u002F post-activate test-fix loops\n\nDelegate elsewhere when the user is:\n- building or editing the agent itself → [sf-ai-agentforce](..\u002Fsf-ai-agentforce\u002FSKILL.md) or [sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md)\n- running Apex unit tests → [sf-testing](..\u002Fsf-testing\u002FSKILL.md)\n- creating seed data for actions → [sf-data](..\u002Fsf-data\u002FSKILL.md)\n- analyzing session telemetry \u002F STDM traces → [sf-ai-agentforce-observability](..\u002Fsf-ai-agentforce-observability\u002FSKILL.md)\n\n---\n\n## Core Operating Rules\n\n- Testing comes **after** deploy \u002F publish \u002F activate.\n- Use **multi-turn API testing** as the primary path when conversation continuity matters.\n- Use **CLI Testing Center** as the secondary path for single-utterance and org-supported test-center workflows.\n- Interactive and programmatic CLI preview use standard `sf org login web` authentication; **ECA is only required for Agent Runtime API testing**, not for live preview.\n- Fixes to the agent should be delegated to **[sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md)** when Agent Script changes are needed.\n- Do **not** use raw `curl` for OAuth token validation in the ECA flow; use the provided credential tooling.\n\n### Script path rule\nUse the existing scripts under:\n- `~\u002F.claude\u002Fskills\u002Fsf-ai-agentforce-testing\u002Fhooks\u002Fscripts\u002F`\n\nThese scripts are pre-approved. Do not recreate them.\n\n---\n\n\u003Ca id=\"phase-0-prerequisites--agent-discovery\">\u003C\u002Fa>\n\n## Required Context to Gather First\n\nAsk for or infer:\n- agent API name \u002F developer name\n- target org alias\n- testing goal: smoke test, regression, coverage expansion, or bug reproduction\n- whether the agent is already published and activated\n- whether the org has **Agent Testing Center** available\n- whether **ECA credentials** are available for Agent Runtime API testing\n\nPreflight checks:\n1. discover the agent\n2. confirm publish \u002F activation state\n3. verify dependencies (Flows, Apex, data)\n4. choose testing track\n\n---\n\n## Dual-Track Workflow\n\n### Track A — Multi-turn API testing (primary)\nUse when you need:\n- multi-turn conversation testing\n- topic re-matching validation\n- context preservation checks\n- escalation or action-chain analysis across turns\n\nRequires:\n- ECA \u002F auth setup\n- agent runtime access\n\n### Track B — CLI Testing Center (secondary)\nUse when you need:\n- org-native `sf agent test` workflows\n- test spec YAML execution\n- quick single-utterance validation\n- CLI-centered CI\u002FCD usage where Testing Center is available\n\n### Quick manual path\nFor manual validation without full formal testing, use preview workflows first, then escalate to Track A or B as needed.\n\n---\n\n## Recommended Workflow\n\n### 1. Discover and verify\n- locate the agent in the target org\n- confirm it is published and activated\n- confirm required actions \u002F Flows \u002F Apex exist\n- decide whether Track A or Track B fits the request\n\n### 2. Plan tests\nCover at least:\n- main topics\n- expected actions\n- guardrails \u002F off-topic handling\n- escalation behavior\n- phrasing variation\n\n### 3. Execute the right track\n#### Track A\n- validate ECA credentials with the provided tooling\n- retrieve metadata needed for scenario generation\n- run multi-turn scenarios with the provided Python scripts\n- analyze per-turn failures and coverage\n\n#### Track B\n- generate or refine a flat YAML test spec\n- run `sf agent test` commands\n- inspect structured results and verbose action output\n\n### 4. Classify failures\nTypical failure buckets:\n- topic not matched\n- wrong topic matched\n- action not invoked\n- wrong action selected\n- action invocation failed\n- context preservation failure\n- guardrail failure\n- escalation failure\n\n### 5. Run fix loop\nWhen failures imply agent-authoring issues:\n- delegate fixes to [sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md)\n- re-publish \u002F re-activate if needed\n- re-run focused tests before full regression\n\n---\n\n## Testing Guardrails\n\nNever skip these:\n- test only after publish\u002Factivate\n- include harmful \u002F off-topic \u002F refusal scenarios\n- use multiple phrasings per important topic\n- clean up sessions after API tests\n- keep swarm execution small and controlled\n\nAvoid these anti-patterns:\n- testing unpublished agents\n- treating one happy-path utterance as coverage\n- storing ECA secrets in repo files\n- debugging auth with brittle shell-expanded `curl` commands\n- changing both tests and agent simultaneously without isolating the cause\n\n---\n\n## Output Format\n\nWhen finishing a run, report in this order:\n1. **Test track used**\n2. **What was executed**\n3. **Pass\u002Ffail summary**\n4. **Coverage gaps**\n5. **Root-cause themes**\n6. **Recommended fix loop \u002F next test step**\n\nSuggested shape:\n\n```text\nAgent: \u003Cname>\nTrack: Multi-turn API | CLI Testing Center | Preview\nExecuted: \u003Cspecs \u002F scenarios \u002F turns>\nResult: \u003Cpassed \u002F partial \u002F failed>\nCoverage: \u003Ctopics, actions, guardrails, context>\nIssues: \u003Chighest-signal failures>\nNext step: \u003Cfix, republish, rerun, or expand coverage>\n```\n\n---\n\n## Cross-Skill Integration\n\n| Need | Delegate to | Reason |\n|---|---|---|\n| fix Agent Script logic | [sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md) | authoring and deterministic fix loops |\n| create test data | [sf-data](..\u002Fsf-data\u002FSKILL.md) | action-ready data setup |\n| fix Flow-backed actions | [sf-flow](..\u002Fsf-flow\u002FSKILL.md) | Flow repair |\n| fix Apex-backed actions | [sf-apex](..\u002Fsf-apex\u002FSKILL.md) | Apex repair |\n| set up ECA \u002F OAuth for Agent Runtime API | [sf-connected-apps](..\u002Fsf-connected-apps\u002FSKILL.md) | auth and app configuration |\n| analyze session telemetry | [sf-ai-agentforce-observability](..\u002Fsf-ai-agentforce-observability\u002FSKILL.md) | STDM \u002F trace analysis |\n\n---\n\n## Reference Map\n\n### Start here\n- [references\u002Finterview-wizard.md](references\u002Finterview-wizard.md)\n- [references\u002Fmulti-turn-testing.md](references\u002Fmulti-turn-testing.md)\n- [references\u002Fcli-commands.md](references\u002Fcli-commands.md)\n- [references\u002Ftest-spec-reference.md](references\u002Ftest-spec-reference.md)\n\n### Execution \u002F auth\n- [references\u002Fexecution-protocol.md](references\u002Fexecution-protocol.md)\n- [references\u002Fmulti-turn-execution.md](references\u002Fmulti-turn-execution.md)\n- [references\u002Feca-setup-guide.md](references\u002Feca-setup-guide.md)\n- [references\u002Fcredential-convention.md](references\u002Fcredential-convention.md)\n- [references\u002Fconnected-app-setup.md](references\u002Fconnected-app-setup.md)\n\n### Coverage \u002F fix loops\n- [references\u002Fcoverage-analysis.md](references\u002Fcoverage-analysis.md)\n- [references\u002Fagentic-fix-loops.md](references\u002Fagentic-fix-loops.md)\n- [references\u002Fresults-scoring.md](references\u002Fresults-scoring.md)\n- [references\u002Fknown-issues.md](references\u002Fknown-issues.md)\n\n### Advanced \u002F specialized\n- [references\u002Fagentscript-agents.md](references\u002Fagentscript-agents.md)\n- [references\u002Fagentscript-testing-patterns.md](references\u002Fagentscript-testing-patterns.md)\n- [references\u002Fcli-testing-details.md](references\u002Fcli-testing-details.md)\n- [references\u002Fdeep-conversation-history-patterns.md](references\u002Fdeep-conversation-history-patterns.md)\n- [references\u002Fswarm-execution.md](references\u002Fswarm-execution.md)\n- [references\u002Ftrace-analysis.md](references\u002Ftrace-analysis.md)\n- [references\u002Fagent-api-reference.md](references\u002Fagent-api-reference.md)\n\n### Templates \u002F assets\n- [references\u002Ftest-templates.md](references\u002Ftest-templates.md)\n- [references\u002Ftest-plan-format.md](references\u002Ftest-plan-format.md)\n- [assets\u002F](assets\u002F)\n\n---\n\n## Score Guide\n\n| Score | Meaning |\n|---|---|\n| 90+ | production-ready test confidence |\n| 80–89 | strong coverage with minor gaps |\n| 70–79 | acceptable but coverage expansion recommended |\n| 60–69 | partial validation only |\n| \u003C 60 | insufficient confidence; block release |\n","# sf-ai-agentforce-testing: Agentforce Test Execution & Coverage Analysis\n\nUse this skill when the user needs **formal Agentforce testing**: multi-turn conversation validation, CLI Testing Center specs, topic\u002Faction coverage analysis, preview checks, or a structured test-fix loop after publish.\n\n## When This Skill Owns the Task\n\nUse `sf-ai-agentforce-testing` when the work involves:\n- `sf agent test` workflows\n- multi-turn Agent Runtime API testing\n- topic routing, action invocation, context preservation, guardrail, or escalation validation\n- test-spec generation and coverage analysis\n- post-publish \u002F post-activate test-fix loops\n\nDelegate elsewhere when the user is:\n- building or editing the agent itself → [sf-ai-agentforce](..\u002Fsf-ai-agentforce\u002FSKILL.md) or [sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md)\n- running Apex unit tests → [sf-testing](..\u002Fsf-testing\u002FSKILL.md)\n- creating seed data for actions → [sf-data](..\u002Fsf-data\u002FSKILL.md)\n- analyzing session telemetry \u002F STDM traces → [sf-ai-agentforce-observability](..\u002Fsf-ai-agentforce-observability\u002FSKILL.md)\n\n---\n\n## Core Operating Rules\n\n- Testing comes **after** deploy \u002F publish \u002F activate.\n- Use **multi-turn API testing** as the primary path when conversation continuity matters.\n- Use **CLI Testing Center** as the secondary path for single-utterance and org-supported test-center workflows.\n- Interactive and programmatic CLI preview use standard `sf org login web` authentication; **ECA is only required for Agent Runtime API testing**, not for live preview.\n- Fixes to the agent should be delegated to **[sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md)** when Agent Script changes are needed.\n- Do **not** use raw `curl` for OAuth token validation in the ECA flow; use the provided credential tooling.\n\n### Script path rule\nUse the existing scripts under:\n- `~\u002F.claude\u002Fskills\u002Fsf-ai-agentforce-testing\u002Fhooks\u002Fscripts\u002F`\n\nThese scripts are pre-approved. Do not recreate them.\n\n---\n\n\u003Ca id=\"phase-0-prerequisites--agent-discovery\">\u003C\u002Fa>\n\n## Required Context to Gather First\n\nAsk for or infer:\n- agent API name \u002F developer name\n- target org alias\n- testing goal: smoke test, regression, coverage expansion, or bug reproduction\n- whether the agent is already published and activated\n- whether the org has **Agent Testing Center** available\n- whether **ECA credentials** are available for Agent Runtime API testing\n\nPreflight checks:\n1. discover the agent\n2. confirm publish \u002F activation state\n3. verify dependencies (Flows, Apex, data)\n4. choose testing track\n\n---\n\n## Dual-Track Workflow\n\n### Track A — Multi-turn API testing (primary)\nUse when you need:\n- multi-turn conversation testing\n- topic re-matching validation\n- context preservation checks\n- escalation or action-chain analysis across turns\n\nRequires:\n- ECA \u002F auth setup\n- agent runtime access\n\n### Track B — CLI Testing Center (secondary)\nUse when you need:\n- org-native `sf agent test` workflows\n- test spec YAML execution\n- quick single-utterance validation\n- CLI-centered CI\u002FCD usage where Testing Center is available\n\n### Quick manual path\nFor manual validation without full formal testing, use preview workflows first, then escalate to Track A or B as needed.\n\n---\n\n## Recommended Workflow\n\n### 1. Discover and verify\n- locate the agent in the target org\n- confirm it is published and activated\n- confirm required actions \u002F Flows \u002F Apex exist\n- decide whether Track A or Track B fits the request\n\n### 2. Plan tests\nCover at least:\n- main topics\n- expected actions\n- guardrails \u002F off-topic handling\n- escalation behavior\n- phrasing variation\n\n### 3. Execute the right track\n#### Track A\n- validate ECA credentials with the provided tooling\n- retrieve metadata needed for scenario generation\n- run multi-turn scenarios with the provided Python scripts\n- analyze per-turn failures and coverage\n\n#### Track B\n- generate or refine a flat YAML test spec\n- run `sf agent test` commands\n- inspect structured results and verbose action output\n\n### 4. Classify failures\nTypical failure buckets:\n- topic not matched\n- wrong topic matched\n- action not invoked\n- wrong action selected\n- action invocation failed\n- context preservation failure\n- guardrail failure\n- escalation failure\n\n### 5. Run fix loop\nWhen failures imply agent-authoring issues:\n- delegate fixes to [sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md)\n- re-publish \u002F re-activate if needed\n- re-run focused tests before full regression\n\n---\n\n## Testing Guardrails\n\nNever skip these:\n- test only after publish\u002Factivate\n- include harmful \u002F off-topic \u002F refusal scenarios\n- use multiple phrasings per important topic\n- clean up sessions after API tests\n- keep swarm execution small and controlled\n\nAvoid these anti-patterns:\n- testing unpublished agents\n- treating one happy-path utterance as coverage\n- storing ECA secrets in repo files\n- debugging auth with brittle shell-expanded `curl` commands\n- changing both tests and agent simultaneously without isolating the cause\n\n---\n\n## Output Format\n\nWhen finishing a run, report in this order:\n1. **Test track used**\n2. **What was executed**\n3. **Pass\u002Ffail summary**\n4. **Coverage gaps**\n5. **Root-cause themes**\n6. **Recommended fix loop \u002F next test step**\n\nSuggested shape:\n\n```text\nAgent: \u003Cname>\nTrack: Multi-turn API | CLI Testing Center | Preview\nExecuted: \u003Cspecs \u002F scenarios \u002F turns>\nResult: \u003Cpassed \u002F partial \u002F failed>\nCoverage: \u003Ctopics, actions, guardrails, context>\nIssues: \u003Chighest-signal failures>\nNext step: \u003Cfix, republish, rerun, or expand coverage>\n```\n\n---\n\n## Cross-Skill Integration\n\n| Need | Delegate to | Reason |\n|---|---|---|\n| fix Agent Script logic | [sf-ai-agentscript](..\u002Fsf-ai-agentscript\u002FSKILL.md) | authoring and deterministic fix loops |\n| create test data | [sf-data](..\u002Fsf-data\u002FSKILL.md) | action-ready data setup |\n| fix Flow-backed actions | [sf-flow](..\u002Fsf-flow\u002FSKILL.md) | Flow repair |\n| fix Apex-backed actions | [sf-apex](..\u002Fsf-apex\u002FSKILL.md) | Apex repair |\n| set up ECA \u002F OAuth for Agent Runtime API | [sf-connected-apps](..\u002Fsf-connected-apps\u002FSKILL.md) | auth and app configuration |\n| analyze session telemetry | [sf-ai-agentforce-observability](..\u002Fsf-ai-agentforce-observability\u002FSKILL.md) | STDM \u002F trace analysis |\n\n---\n\n## Reference Map\n\n### Start here\n- [references\u002Finterview-wizard.md](references\u002Finterview-wizard.md)\n- [references\u002Fmulti-turn-testing.md](references\u002Fmulti-turn-testing.md)\n- [references\u002Fcli-commands.md](references\u002Fcli-commands.md)\n- [references\u002Ftest-spec-reference.md](references\u002Ftest-spec-reference.md)\n\n### Execution \u002F auth\n- [references\u002Fexecution-protocol.md](references\u002Fexecution-protocol.md)\n- [references\u002Fmulti-turn-execution.md](references\u002Fmulti-turn-execution.md)\n- [references\u002Feca-setup-guide.md](references\u002Feca-setup-guide.md)\n- [references\u002Fcredential-convention.md](references\u002Fcredential-convention.md)\n- [references\u002Fconnected-app-setup.md](references\u002Fconnected-app-setup.md)\n\n### Coverage \u002F fix loops\n- [references\u002Fcoverage-analysis.md](references\u002Fcoverage-analysis.md)\n- [references\u002Fagentic-fix-loops.md](references\u002Fagentic-fix-loops.md)\n- [references\u002Fresults-scoring.md](references\u002Fresults-scoring.md)\n- [references\u002Fknown-issues.md](references\u002Fknown-issues.md)\n\n### Advanced \u002F specialized\n- [references\u002Fagentscript-agents.md](references\u002Fagentscript-agents.md)\n- [references\u002Fagentscript-testing-patterns.md](references\u002Fagentscript-testing-patterns.md)\n- [references\u002Fcli-testing-details.md](references\u002Fcli-testing-details.md)\n- [references\u002Fdeep-conversation-history-patterns.md](references\u002Fdeep-conversation-history-patterns.md)\n- [references\u002Fswarm-execution.md](references\u002Fswarm-execution.md)\n- [references\u002Ftrace-analysis.md](references\u002Ftrace-analysis.md)\n- [references\u002Fagent-api-reference.md](references\u002Fagent-api-reference.md)\n\n### Templates \u002F assets\n- [references\u002Ftest-templates.md](references\u002Ftest-templates.md)\n- [references\u002Ftest-plan-format.md](references\u002Ftest-plan-format.md)\n- [assets\u002F](assets\u002F)\n\n---\n\n## Score Guide\n\n| Score | Meaning |\n|---|---|\n| 90+ | production-ready test confidence |\n| 80–89 | strong coverage with minor gaps |\n| 70–79 | acceptable but coverage expansion recommended |\n| 60–69 | partial validation only |\n| \u003C 60 | insufficient confidence; block release |\n",{"name":5,"license":15,"metadata":24,"description":28,"compatibility":29},{"author":25,"scoring":26,"version":27},"Jag Valaiyapathy","100 points across 7 categories","2.1.0","Agentforce agent testing with dual-track workflow and 100-point scoring. TRIGGER when: user tests Agentforce agents, runs sf agent test commands, creates test specs, validates topic routing, or analyzes agent test coverage. DO NOT TRIGGER when: Apex unit tests (use sf-testing), building agents (use sf-ai-agentforce), or Agent Script DSL (use sf-ai-agentscript).\n","Requires API v66.0+ (Spring '26) and Agentforce enabled org","main","8859218955d9504cd18b59e7892100718039d3b4","data\u002Fskills\u002Fjaganpro-sf-skills\u002Fsf-ai-agentforce-testing\u002Fskills\u002Fsf-ai-agentforce-testing",1,"https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper","https:\u002F\u002Fgithub.com\u002Fom-scogo","SDE-1 @ Scogo ","2026-07-18 12:22:46",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add om-scogo\u002Fskillsh-scraper --skill sf-ai-agentforce-testing",{"tool":44,"command":45},"bunx","bunx skills add om-scogo\u002Fskillsh-scraper --skill sf-ai-agentforce-testing",{"tool":47,"command":48},"pnpm","pnpm dlx skills add om-scogo\u002Fskillsh-scraper --skill sf-ai-agentforce-testing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fjaganpro-sf-skills\u002Fsf-ai-agentforce-testing\u002Fskills\u002Fsf-ai-agentforce-testing\u002FSKILL.md",true,[],[53,60,65,72,77,84],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7D6MC9FAAEV4CMNYX8W7JTG","arxiv-search","Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002Fskills\u002Farxiv-search\u002FSKILL.md",[],[],{"skillNo":61,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7D6M85CKKN87TA98VCQV4H7","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002FSkill.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7D4ZTCS4DR3CE4JY06X84T2","working-with-legacy-code","Safely change and test untested codebases using Feathers' \"Working Effectively with Legacy Code\". Use when the user mentions \"legacy code\", \"no tests\", \"untested codebase\", \"how do I test this\", \"seams\", \"characterization tests\", \"golden master\", \"sprout method\", \"afraid to change this code\", \"monster method\", \"dependency breaking\", or \"inherited a messy codebase\". Also trigger when changing code without tests safely, getting a class under test when constructors, statics, or singletons block it, adding features to tangled modules, or planning incremental test coverage for an old codebase. Covers the legacy-code change algorithm, seams, characterization tests, sprout\u002Fwrap, and dependency-breaking techniques. For refactoring code that already has tests, see refactoring-patterns. For day-to-day code quality, see clean-code.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002Fworking-with-legacy-code\u002FSKILL.md",[],[],{"skillNo":73,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7D4ZHZKJD2RSNGAF63V14P4","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002FSkill.md",[],[],{"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},"01M7D4ZB4CJBFW5JE67CPH2QRV","web-typography","Select, pair, and implement typefaces for web projects. Use when the user mentions \"font pairing\", \"which typeface\", \"line height\", \"responsive typography\", \"web font loading\", \"type hierarchy\", \"variable fonts\", \"FOUT\u002FFOIT\", \"typographic scale\", or \"the text is hard to read\". Also trigger when choosing between system fonts and web fonts, optimizing font-loading performance, or designing readable long-form content. Covers readability evaluation, CSS implementation, and performance optimization. For overall UI design systems, see refactoring-ui. For dramatic typographic experiences, see top-design.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002Fweb-typography\u002FSKILL.md",[],[],{"skillNo":85,"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":86,"categories":87,"keywords":88,"publishedAt":19},"01M7D4Z4MVYVY3NMJ18BNV6WNA","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002FSkill.md",[],[]]