[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EB3VRM4XFT698G9XYX34YY":3,"skill-same:01M7EB3VRM4XFT698G9XYX34YY":78},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EB3VRM4XFT698G9XYX34YY","call-summarizer",null,"Turn a finished CALL-E phone-call transcript into a structured post-call brief with a one-line outcome, a masked summary, extracted action items with owners and due dates, caller sentiment, and a redacted caller fingerprint. Use after any CALL-E call when an agent or operator needs an actionable, reviewable record of what was said without re-reading the whole transcript or re-playing the recording.","fozagtx\u002FBuildOS-workflow","fozagtx","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160292135?v=4","01M7EAS4W39D2X3WNCCVVZ7CVZ","fawuzan","01M7EAS4WP1G4JD4KG87P6PTK6",0,"MIT","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fcall-summarizer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: call-summarizer\ndescription: Turn a finished CALL-E phone-call transcript into a structured post-call brief with a one-line outcome, a masked summary, extracted action items with owners and due dates, caller sentiment, and a redacted caller fingerprint. Use after any CALL-E call when an agent or operator needs an actionable, reviewable record of what was said without re-reading the whole transcript or re-playing the recording.\nlicense: MIT\n---\n\n# Call Summarizer\n\nUse this skill after a CALL-E call has completed and the agent needs to turn the\nreturned transcript into a compact, actionable post-call record.\n\n`call-summarizer` is a post-call analysis skill. It takes a CALL-E call result\nthat already contains a transcript, runs locally with no additional phone calls\nand no network access, and emits a single structured brief: a one-line outcome,\na masked summary of the conversation, the action items with owners and due\ndates, the caller sentiment, and a redacted caller fingerprint for dedup.\n\nIt is a good fit for CALL-E's design: the hard part (the call) is already done,\nand the remaining work (turning a long transcript into something an agent can\nact on) is pure text analysis that should not require a second provider or a\npaid summarization API.\n\n## When To Use\n\nUse this skill for:\n\n- turning a completed CALL-E call transcript into a one-page post-call brief\n- extracting action items with owners and due dates from a call\n- surfacing caller sentiment so a follow-up can be triaged correctly\n- producing a masked summary that is safe to log, store, or hand to a human\n- building a redacted caller fingerprint for de-duplicating repeat callers\n- any workflow where the call is done and the record is the deliverable\n\n## When Not To Use\n\nDo not use this skill to:\n\n- place, schedule, or cancel a phone call; it only reads transcripts\n- summarize a call that has no transcript; it will abstain instead of inventing one\n- act on the action items; it reports them, the operator decides whether to execute\n- store PII; every output is masked and the fingerprint is one-way hashed\n- replace a human review for medical, legal, financial, or emergency content\n- run during the call; it is strictly post-call and never affects call behavior\n\n## Workflow\n\n### 1. Collect the call result\n\nRequired: a CALL-E call result containing a `transcript` field (the full\ndialogue turns between the agent and the callee). The transcript may be plain\ntext or a list of turns; both are handled.\n\nConfirm with the operator that this transcript belongs to a call they\nauthorized and that they want a post-call brief generated. Never run this skill\non a transcript whose origin is unknown.\n\n### 2. Generate the brief locally\n\nRun `scripts\u002Fsummarize_call.py` on the transcript. By default it reads from a\nfile path and prints the brief to stdout; it makes no network calls and places\nno calls.\n\n```bash\npython3 scripts\u002Fsummarize_call.py --transcript path\u002Fto\u002Ftranscript.json --out brief.json\n```\n\nThe script performs:\n\n1. **Outcome line**: a single sentence stating the call result (confirmed,\n   declined, rescheduled, no-answer, voicemail, unknown) using only words that\n   appear in the transcript. The outcome is bound to the callee's latest\n   effective response (agent text never counts as a confirmation), and any\n   contradictory intent — across utterances or within a single utterance\n   (e.g. \"Yes, I can't make it\") — fails closed to `unknown`.\n2. **Masked summary**: a short prose summary with phone numbers, emails,\n   account identifiers, and title-prefixed or cue-introduced personal names\n   replaced by masked tokens. The brief sets `masked: \"partial\"` with a\n   `masking_scope` field documenting exactly which PII classes are tokenized;\n   ordinary personal names without an introduction cue are NOT redacted (the\n   skill uses no NER model and the contract is honest about this boundary).\n3. **Action items**: each commitment, follow-up, or next step extracted with an\n   owner (the party who said they would do it), a verb, and an optional due\n   date parsed from natural-language time references. Ambiguous items keep\n   `owner: unknown` rather than guessing.\n4. **Sentiment**: a coarse label (`positive`, `neutral`, `negative`, `mixed`)\n   with a short justification span from the transcript. It never reports a\n   sentiment the transcript does not support.\n5. **Caller fingerprint**: a one-way hash of a stable caller identity input\n   (the masked caller phone number, or an explicit `caller_id` field if\n   provided). The `call_id` is deliberately excluded so the same caller\n   produces the same fingerprint across calls, enabling de-duplication without\n   storing PII.\n\n### 3. Validate the brief\n\nRun `scripts\u002Fvalidate_brief.py` to confirm the brief is well-formed before any\ndownstream system consumes it. It checks that every action item has an owner,\nthat masking has no residual raw phone numbers, emails, account identifiers,\nor personal names, and that the outcome line is non-empty and grounded in the\ntranscript.\n\n### 4. Review or route\n\nReturn the brief to the operator or the calling agent. The skill does not\nexecute any action item; it only reports them. Routing decisions (escalate,\nfollow up, close the ticket) stay with the operator or the host agent.\n\n## Output Schema\n\nThe brief is a single JSON object:\n\n```json\n{\n  \"outcome\": \"Appointment confirmed for Tuesday 10:00.\",\n  \"summary\": \"The callee confirmed the appointment and asked for a reminder the day before.\",\n  \"actions\": [\n    {\n      \"owner\": \"agent\",\n      \"verb\": \"send reminder\",\n      \"due\": \"2026-09-15\",\n      \"source_span\": \"I will send a reminder the day before.\"\n    }\n  ],\n  \"sentiment\": {\n    \"label\": \"positive\",\n    \"justification\": \"Callee confirmed without hesitation.\"\n  },\n  \"caller_fingerprint\": \"sha256:9f2c...\",\n  \"masked\": \"partial\",\n  \"masking_scope\": \"phone_numbers emails account_ids title_prefixed_names cue_introduced_names\",\n  \"masking_note\": \"Structured PII and cued personal names are tokenized. Ordinary uncued names are NOT redacted.\"\n}\n```\n\n## Safety Rules\n\nRead `references\u002Fsafety.md` for the full safety contract.\n\n- This skill never places a call and never modifies call state.\n- Every output is partially masked: phone numbers, emails, account IDs, and\n  cued personal names are tokenized. The `masked` field is `\"partial\"` with a\n  `masking_scope` documenting the boundary; ordinary uncued names are NOT\n  redacted (no NER model).\n- The caller fingerprint is a one-way hash; the raw identity is never stored.\n- Action items are reported, not executed. Medical, legal, financial, and\n  emergency commitments are flagged as `category: sensitive` and routed to a\n  human rather than auto-dispatched.\n- If the transcript is empty, garbled, or does not support an outcome, the skill\n  abstains with `outcome: unknown` and an empty `actions` list. It never invents\n  a plausible outcome.\n- No PII leaves the local process. There is no network call and no third-party\n  summarization API.\n\n## Requirements\n\n- Python 3.9 or newer. The skill uses only the Python standard library, so no\n  `pip install` is required for the default (no-call) path.\n- A CALL-E call result with a transcript. Live calls are out of scope; see the\n  `call-reminder` or `verify-by-phone` skills for placing calls.\n\n## Quick Start\n\n```bash\n# Dry run on the bundled example transcript (no calls, no network).\npython3 scripts\u002Fsummarize_call.py \\\n  --transcript references\u002Fexample-transcript.json \\\n  --out \u002Ftmp\u002Fbrief.json\n\n# Validate the brief.\npython3 scripts\u002Fvalidate_brief.py --brief \u002Ftmp\u002Fbrief.json\n```\n\n## Examples\n\nSee `references\u002Fexamples.md` for worked examples on different call types\n(confirmation, reschedule, no-answer, voicemail) and the expected brief for\neach.\n","# Call Summarizer\n\nUse this skill after a CALL-E call has completed and the agent needs to turn the\nreturned transcript into a compact, actionable post-call record.\n\n`call-summarizer` is a post-call analysis skill. It takes a CALL-E call result\nthat already contains a transcript, runs locally with no additional phone calls\nand no network access, and emits a single structured brief: a one-line outcome,\na masked summary of the conversation, the action items with owners and due\ndates, the caller sentiment, and a redacted caller fingerprint for dedup.\n\nIt is a good fit for CALL-E's design: the hard part (the call) is already done,\nand the remaining work (turning a long transcript into something an agent can\nact on) is pure text analysis that should not require a second provider or a\npaid summarization API.\n\n## When To Use\n\nUse this skill for:\n\n- turning a completed CALL-E call transcript into a one-page post-call brief\n- extracting action items with owners and due dates from a call\n- surfacing caller sentiment so a follow-up can be triaged correctly\n- producing a masked summary that is safe to log, store, or hand to a human\n- building a redacted caller fingerprint for de-duplicating repeat callers\n- any workflow where the call is done and the record is the deliverable\n\n## When Not To Use\n\nDo not use this skill to:\n\n- place, schedule, or cancel a phone call; it only reads transcripts\n- summarize a call that has no transcript; it will abstain instead of inventing one\n- act on the action items; it reports them, the operator decides whether to execute\n- store PII; every output is masked and the fingerprint is one-way hashed\n- replace a human review for medical, legal, financial, or emergency content\n- run during the call; it is strictly post-call and never affects call behavior\n\n## Workflow\n\n### 1. Collect the call result\n\nRequired: a CALL-E call result containing a `transcript` field (the full\ndialogue turns between the agent and the callee). The transcript may be plain\ntext or a list of turns; both are handled.\n\nConfirm with the operator that this transcript belongs to a call they\nauthorized and that they want a post-call brief generated. Never run this skill\non a transcript whose origin is unknown.\n\n### 2. Generate the brief locally\n\nRun `scripts\u002Fsummarize_call.py` on the transcript. By default it reads from a\nfile path and prints the brief to stdout; it makes no network calls and places\nno calls.\n\n```bash\npython3 scripts\u002Fsummarize_call.py --transcript path\u002Fto\u002Ftranscript.json --out brief.json\n```\n\nThe script performs:\n\n1. **Outcome line**: a single sentence stating the call result (confirmed,\n   declined, rescheduled, no-answer, voicemail, unknown) using only words that\n   appear in the transcript. The outcome is bound to the callee's latest\n   effective response (agent text never counts as a confirmation), and any\n   contradictory intent — across utterances or within a single utterance\n   (e.g. \"Yes, I can't make it\") — fails closed to `unknown`.\n2. **Masked summary**: a short prose summary with phone numbers, emails,\n   account identifiers, and title-prefixed or cue-introduced personal names\n   replaced by masked tokens. The brief sets `masked: \"partial\"` with a\n   `masking_scope` field documenting exactly which PII classes are tokenized;\n   ordinary personal names without an introduction cue are NOT redacted (the\n   skill uses no NER model and the contract is honest about this boundary).\n3. **Action items**: each commitment, follow-up, or next step extracted with an\n   owner (the party who said they would do it), a verb, and an optional due\n   date parsed from natural-language time references. Ambiguous items keep\n   `owner: unknown` rather than guessing.\n4. **Sentiment**: a coarse label (`positive`, `neutral`, `negative`, `mixed`)\n   with a short justification span from the transcript. It never reports a\n   sentiment the transcript does not support.\n5. **Caller fingerprint**: a one-way hash of a stable caller identity input\n   (the masked caller phone number, or an explicit `caller_id` field if\n   provided). The `call_id` is deliberately excluded so the same caller\n   produces the same fingerprint across calls, enabling de-duplication without\n   storing PII.\n\n### 3. Validate the brief\n\nRun `scripts\u002Fvalidate_brief.py` to confirm the brief is well-formed before any\ndownstream system consumes it. It checks that every action item has an owner,\nthat masking has no residual raw phone numbers, emails, account identifiers,\nor personal names, and that the outcome line is non-empty and grounded in the\ntranscript.\n\n### 4. Review or route\n\nReturn the brief to the operator or the calling agent. The skill does not\nexecute any action item; it only reports them. Routing decisions (escalate,\nfollow up, close the ticket) stay with the operator or the host agent.\n\n## Output Schema\n\nThe brief is a single JSON object:\n\n```json\n{\n  \"outcome\": \"Appointment confirmed for Tuesday 10:00.\",\n  \"summary\": \"The callee confirmed the appointment and asked for a reminder the day before.\",\n  \"actions\": [\n    {\n      \"owner\": \"agent\",\n      \"verb\": \"send reminder\",\n      \"due\": \"2026-09-15\",\n      \"source_span\": \"I will send a reminder the day before.\"\n    }\n  ],\n  \"sentiment\": {\n    \"label\": \"positive\",\n    \"justification\": \"Callee confirmed without hesitation.\"\n  },\n  \"caller_fingerprint\": \"sha256:9f2c...\",\n  \"masked\": \"partial\",\n  \"masking_scope\": \"phone_numbers emails account_ids title_prefixed_names cue_introduced_names\",\n  \"masking_note\": \"Structured PII and cued personal names are tokenized. Ordinary uncued names are NOT redacted.\"\n}\n```\n\n## Safety Rules\n\nRead `references\u002Fsafety.md` for the full safety contract.\n\n- This skill never places a call and never modifies call state.\n- Every output is partially masked: phone numbers, emails, account IDs, and\n  cued personal names are tokenized. The `masked` field is `\"partial\"` with a\n  `masking_scope` documenting the boundary; ordinary uncued names are NOT\n  redacted (no NER model).\n- The caller fingerprint is a one-way hash; the raw identity is never stored.\n- Action items are reported, not executed. Medical, legal, financial, and\n  emergency commitments are flagged as `category: sensitive` and routed to a\n  human rather than auto-dispatched.\n- If the transcript is empty, garbled, or does not support an outcome, the skill\n  abstains with `outcome: unknown` and an empty `actions` list. It never invents\n  a plausible outcome.\n- No PII leaves the local process. There is no network call and no third-party\n  summarization API.\n\n## Requirements\n\n- Python 3.9 or newer. The skill uses only the Python standard library, so no\n  `pip install` is required for the default (no-call) path.\n- A CALL-E call result with a transcript. Live calls are out of scope; see the\n  `call-reminder` or `verify-by-phone` skills for placing calls.\n\n## Quick Start\n\n```bash\n# Dry run on the bundled example transcript (no calls, no network).\npython3 scripts\u002Fsummarize_call.py \\\n  --transcript references\u002Fexample-transcript.json \\\n  --out \u002Ftmp\u002Fbrief.json\n\n# Validate the brief.\npython3 scripts\u002Fvalidate_brief.py --brief \u002Ftmp\u002Fbrief.json\n```\n\n## Examples\n\nSee `references\u002Fexamples.md` for worked examples on different call types\n(confirmation, reschedule, no-answer, voicemail) and the expected brief for\neach.\n",{"name":5,"license":15,"description":7},"master","8c91ae30409640de28e218b3e9c7fe01c01d257b","skills\u002Fcall-summarizer","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow","https:\u002F\u002Fgithub.com\u002Ffozagtx","hi.fawuzanpima@gmail.com","Forward deployed","2026-10-08 00:13:28",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add fozagtx\u002FBuildOS-workflow --skill call-summarizer",{"tool":38,"command":39},"bunx","bunx skills add fozagtx\u002FBuildOS-workflow --skill call-summarizer",{"tool":41,"command":42},"pnpm","pnpm dlx skills add fozagtx\u002FBuildOS-workflow --skill call-summarizer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fcall-summarizer\u002FSKILL.md",true,[46,52,56,60,64,70,74],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcall-e-feedback.md","REFERENCE","参考文档",5129,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fcall-summarizer\u002Freferences\u002Fcall-e-feedback.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fexample-transcript.json",482,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fcall-summarizer\u002Freferences\u002Fexample-transcript.json",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fexamples.md",4585,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fcall-summarizer\u002Freferences\u002Fexamples.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fsafety.md",3727,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fcall-summarizer\u002Freferences\u002Fsafety.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fsummarize_call.py","SCRIPT","脚本",21119,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fcall-summarizer\u002Fscripts\u002Fsummarize_call.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Ftest_summarizer.py",22067,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fcall-summarizer\u002Fscripts\u002Ftest_summarizer.py",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"scripts\u002Fvalidate_brief.py",5650,"https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fcall-summarizer\u002Fscripts\u002Fvalidate_brief.py",[79,86,93,100,107,116],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7EE49XAN8GE213J691P3RZ9","xitter","Interact with X\u002FTwitter via the x-cli terminal client using official X API credentials. Use for posting, reading timelines, searching tweets, liking, retweeting, bookmarks, mentions, and user lookups.","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fxitter\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7EE3TMR3CR7HR7HTCAKPTTR","writing-plans","Use when you have a spec or requirements for a multi-step task. Creates comprehensive implementation plans with bite-sized tasks, exact file paths, and complete code examples.","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7EE3AJ6V2VBVAX1WTV7M447","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fwhisper\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7EE36AAP5THSCQAHH6JCWVV","weights-and-biases","Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fweights-and-biases\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":111,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M7EE30R3S4EAK1FWJEBG7MW9","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":19},"01M7EE2X3PJ0ZJR0JJNF2M4NS5","web-pentest","Authorized web pentest: recon, proof-based exploits, report.","https:\u002F\u002Fgithub.com\u002Ffozagtx\u002FBuildOS-workflow\u002Fblob\u002Fmaster\u002Fskills\u002Fweb-pentest\u002FSKILL.md",[],[]]