[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EF6VRZHHFYZJS3AXVYZHKB":3,"skill-same:01M7EF6VRZHHFYZJS3AXVYZHKB":46},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EF6VRZHHFYZJS3AXVYZHKB","bb-workflow",null,"Autonomous bug-bounty campaign driver. Runs a full programme end to end with no operator approvals - the deterministic driver (scripts\u002Fcampaign.py) owns pass state, generates the killchain board from recon, and prints the exact next action (including which Skill and tool to run) every turn. Use when starting or resuming a bug-bounty engagement, \"run the bb workflow\", \"hunt this program\", \"9-pass campaign\", or when handed a *.scope wildcard to test for TIER1 findings. Single agent, refuter-verified, wiki-first, tool-first.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fbb-workflow\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bb-workflow\ndescription: Autonomous bug-bounty campaign driver. Runs a full programme end to end with no operator approvals - the deterministic driver (scripts\u002Fcampaign.py) owns pass state, generates the killchain board from recon, and prints the exact next action (including which Skill and tool to run) every turn. Use when starting or resuming a bug-bounty engagement, \"run the bb workflow\", \"hunt this program\", \"9-pass campaign\", or when handed a *.scope wildcard to test for TIER1 findings. Single agent, refuter-verified, wiki-first, tool-first.\n---\n\n# bb-workflow\n\nThe driver is the plan. You run one command, do exactly what it prints, record the result, repeat.\nNothing here is advisory: the gates are enforced by `scripts\u002Fcampaign.py`, so follow its output\nliterally rather than improvising. This exists because prose routing failed - 22 Skill calls against\n341 hand-rolled curls in the reference campaign; the board fixes that by making the mandate tool\noutput, fresh every turn.\n\n## The loop\n\n```\npython3 scripts\u002Fcampaign.py next        # prints ONE required-action block\n# do EXACTLY what it lists, in order\npython3 scripts\u002Fcampaign.py note \u003Crow> --arsenal \u003Cslug>     # after Skill(wiki-arsenal)\npython3 scripts\u002Fcampaign.py done \u003Crow> --poc \u003Cimg> --kind req   # | --dead R | --park Q | --find F\n# repeat\n```\n\n## Start \u002F resume\n\n1. `python3 scripts\u002Fcampaign.py init --type bb` - validates `scope.md` + the autonomy envelope,\n   repairs `engagement_type`\u002Fschema, prints the Deadends size. If it exits 2, fix what it names\n   (an empty `scope.md` is the one thing it cannot invent - fill it from the programme brief first).\n2. Passes 0-3 (OSINT\u002FWayback, crawl, fingerprint, CVE) feed `state.md`. Read every JS bundle and\n   handler end to end (`Skill`-less; volume-reduce first: source-map, drop vendor, beautify, read).\n   Grep never substitutes for the read.\n3. `python3 scripts\u002Fcampaign.py board` - writes the killchain 4a rows. Refuses on an empty state.\n4. Enter the loop. `next` serves one row, depth-first, one open row at a time.\n\n## Browser observation (chrome-devtools MCP)\n\nThe programme's targets are internet-reachable, so **drive them through a real browser**, not just\n`curl` - a modern site's real attack surface is only visible rendered. Use the `chrome-devtools` MCP:\n\n- **Pass 1 crawl:** `navigate_page` to each app, then `list_network_requests` - the XHR\u002Ffetch calls a\n  page makes reveal the **API endpoints\u002Froutes** a static crawl never sees (this is exactly the lead a\n  curl-only recon misses). `take_snapshot` for the rendered DOM; `evaluate_script` to read client\n  config \u002F `__NEXT_DATA__` \u002F JS globals.\n- **Confirmation + evidence:** DOM-XSS fires in the real DOM (`evaluate_script` \u002F console); a rendered\n  `take_screenshot` of the exploited state is a valid `web` PoC (G3).\n\nCaveat: chrome-devtools drives a **local** browser, so it only reaches internet targets. For a\nVPN-boxed host it cannot connect - use the VM-side browser (`scripts\u002Fbrowser.sh` \u002F `capture.sh web`)\nas the equivalent. `pt-workflow` \u002F `ctf-workflow` default to the VM browser for that reason.\n\n**Manual login \u002F MFA the agent cannot do headlessly** (Smart-ID, Mobile-ID, a CAPTCHA) -> `Skill(chrome-devtools-browser)`: a VISIBLE chromium on the VM desktop (`scripts\u002Fbrowser-visible.sh`) the operator logs into, driven + observed live via the chrome-devtools MCP - capture the authenticated session and the real `\u002F…` API calls, then feed the hunt skills.\n\n## Gates (the driver enforces; do not fight them)\n\n- **G1** no exploit action until the row's arsenal card exists (`Skill(wiki-arsenal)` fills it).\n- **G2** a row cannot close unless its mapped `Skill(hunt-*)` actually fired.\n- **G3** a row cannot close without typed evidence: `req` (default), `burp`, or `web` (visual classes\n  only). A page render is not evidence of a bug.\n- **G8** run the mapped tool before hand-rolling; the driver warns if you skipped it.\n\n## Autonomy\n\nNo approvals. Out-of-envelope work **parks** to `decisions.md` and the loop moves on - it never blocks\nand never asks a question. A confirmed TIER1 is written up and chained but does not stop the run; the\ncampaign ends when the board is exhausted (two dry reframe rounds) or the request budget is spent.\n\n## Model routing\n\nExplicit per-role model assignment (the driver enforces the verifier gate; the rest is operating policy):\n\n- **Main brain - Opus 5 1M:** the `campaign.py` loop, board\u002Fstate, strategy, Burp\u002Fchrome-devtools, finding write-ups. This session.\n- **Verifier - Opus (fresh context), MANDATORY:** before any CONFIRMED, `campaign.py verify \u003CF>` prints an Opus refuter prompt; dispatch ONE fresh Opus agent that reads the raw PoC, tries to REFUTE, and writes `verdicts\u002F\u003CF>.json`. `done --find` refuses unless that verdict exists, is `refuted:false`, and cites the finding's PoC (anti-rubber-stamp). Fails CLOSED.\n- **RTL - Opus (fresh context):** `Skill(redteamlead)` for direction at a fork or when a vector stalls.\n- **Short tasks - Haiku:** `Skill(wiki-arsenal)` deep, `Skill(delegate)` (mechanical exploit-run), `Skill(ingest)` recon-parse. Bounded, fully-specified, single-shot ONLY.\n\nThe line that keeps quota safety: Haiku is allowed for a **bounded single job**, never for open-ended parallel hunting.\n\n## Discipline (carried, not restated - hunt-core owns the gates)\n\n- **Do NOT** invoke `superpowers:brainstorming` or `superpowers:writing-plans` mid-campaign, and keep\n  no parallel `TaskCreate` list. The board is the plan.\n- Model routing (see `## Model routing`): Opus-1M drives the loop; bounded short tasks go to Haiku;\n  the mandatory Opus **verifier** gates every finding (`done --find` refuses without a passing\n  `verdicts\u002F\u003CF>.json`). Still **no open-ended hunter fan-out** (it exhausted the weekly quota last\n  time) - Haiku is only for single, fully-specified jobs.\n- Load-bearing exploit requests go through Burp Repeater when it is reachable; degrade to\n  `capture.sh req` when it is not. Never block on Burp.\n- Scope and the enumeration ceiling come from `scope.md`, never from this skill.\n- **RCE-first:** with >1 vector open, take the code-exec one first - it is the attack vector with\n  impact; chase lower-impact classes only after code-exec is ruled out or the target needs them.\n- **Read whole, not grep:** on a post-foothold host where a sudoer has no findable password and the\n  usual vectors dead-end, READ `\u002Fetc\u002Fpam.d\u002F{sudo,su}` + `\u002Fetc\u002Fsudoers.d\u002F*` and linpeas output WHOLE -\n  a `pam_ssh_agent_auth`\u002F`pam_exec`\u002F`NOPASSWD` line is the tell a grep skips. See [[linux-privesc]].\n- **Long tools:** run pspy\u002Flinpeas via `bash scripts\u002Fvm-bg.sh \u003Ceng> \u003Cwin> '\u003Ctool>'` (stages to\n  `\u002Fdev\u002Fshm`, runs in the stabilized shell, `--read`\u002F`--wait 120` the logfile); never retry a broken\n  tool pattern >2x - switch method or call `Skill(redteamlead)`.\n\n## Close-out\n\nWhen `next` prints the close-out chain, run it: `Skill(triage)` -> `Skill(evidence)` ->\n`Skill(report)` -> `Skill(learn)`.\n\n## If the driver is unavailable\n\nManual fallback, same gates by hand: read `Approach.md`, take the top open row for the current\nasset, run its wiki lookup then its hunt skill, capture `req` evidence, mark it `[x]`; on exhaustion\none `Deadends.md` line and `[!]`.\n","# bb-workflow\n\nThe driver is the plan. You run one command, do exactly what it prints, record the result, repeat.\nNothing here is advisory: the gates are enforced by `scripts\u002Fcampaign.py`, so follow its output\nliterally rather than improvising. This exists because prose routing failed - 22 Skill calls against\n341 hand-rolled curls in the reference campaign; the board fixes that by making the mandate tool\noutput, fresh every turn.\n\n## The loop\n\n```\npython3 scripts\u002Fcampaign.py next        # prints ONE required-action block\n# do EXACTLY what it lists, in order\npython3 scripts\u002Fcampaign.py note \u003Crow> --arsenal \u003Cslug>     # after Skill(wiki-arsenal)\npython3 scripts\u002Fcampaign.py done \u003Crow> --poc \u003Cimg> --kind req   # | --dead R | --park Q | --find F\n# repeat\n```\n\n## Start \u002F resume\n\n1. `python3 scripts\u002Fcampaign.py init --type bb` - validates `scope.md` + the autonomy envelope,\n   repairs `engagement_type`\u002Fschema, prints the Deadends size. If it exits 2, fix what it names\n   (an empty `scope.md` is the one thing it cannot invent - fill it from the programme brief first).\n2. Passes 0-3 (OSINT\u002FWayback, crawl, fingerprint, CVE) feed `state.md`. Read every JS bundle and\n   handler end to end (`Skill`-less; volume-reduce first: source-map, drop vendor, beautify, read).\n   Grep never substitutes for the read.\n3. `python3 scripts\u002Fcampaign.py board` - writes the killchain 4a rows. Refuses on an empty state.\n4. Enter the loop. `next` serves one row, depth-first, one open row at a time.\n\n## Browser observation (chrome-devtools MCP)\n\nThe programme's targets are internet-reachable, so **drive them through a real browser**, not just\n`curl` - a modern site's real attack surface is only visible rendered. Use the `chrome-devtools` MCP:\n\n- **Pass 1 crawl:** `navigate_page` to each app, then `list_network_requests` - the XHR\u002Ffetch calls a\n  page makes reveal the **API endpoints\u002Froutes** a static crawl never sees (this is exactly the lead a\n  curl-only recon misses). `take_snapshot` for the rendered DOM; `evaluate_script` to read client\n  config \u002F `__NEXT_DATA__` \u002F JS globals.\n- **Confirmation + evidence:** DOM-XSS fires in the real DOM (`evaluate_script` \u002F console); a rendered\n  `take_screenshot` of the exploited state is a valid `web` PoC (G3).\n\nCaveat: chrome-devtools drives a **local** browser, so it only reaches internet targets. For a\nVPN-boxed host it cannot connect - use the VM-side browser (`scripts\u002Fbrowser.sh` \u002F `capture.sh web`)\nas the equivalent. `pt-workflow` \u002F `ctf-workflow` default to the VM browser for that reason.\n\n**Manual login \u002F MFA the agent cannot do headlessly** (Smart-ID, Mobile-ID, a CAPTCHA) -> `Skill(chrome-devtools-browser)`: a VISIBLE chromium on the VM desktop (`scripts\u002Fbrowser-visible.sh`) the operator logs into, driven + observed live via the chrome-devtools MCP - capture the authenticated session and the real `\u002F…` API calls, then feed the hunt skills.\n\n## Gates (the driver enforces; do not fight them)\n\n- **G1** no exploit action until the row's arsenal card exists (`Skill(wiki-arsenal)` fills it).\n- **G2** a row cannot close unless its mapped `Skill(hunt-*)` actually fired.\n- **G3** a row cannot close without typed evidence: `req` (default), `burp`, or `web` (visual classes\n  only). A page render is not evidence of a bug.\n- **G8** run the mapped tool before hand-rolling; the driver warns if you skipped it.\n\n## Autonomy\n\nNo approvals. Out-of-envelope work **parks** to `decisions.md` and the loop moves on - it never blocks\nand never asks a question. A confirmed TIER1 is written up and chained but does not stop the run; the\ncampaign ends when the board is exhausted (two dry reframe rounds) or the request budget is spent.\n\n## Model routing\n\nExplicit per-role model assignment (the driver enforces the verifier gate; the rest is operating policy):\n\n- **Main brain - Opus 5 1M:** the `campaign.py` loop, board\u002Fstate, strategy, Burp\u002Fchrome-devtools, finding write-ups. This session.\n- **Verifier - Opus (fresh context), MANDATORY:** before any CONFIRMED, `campaign.py verify \u003CF>` prints an Opus refuter prompt; dispatch ONE fresh Opus agent that reads the raw PoC, tries to REFUTE, and writes `verdicts\u002F\u003CF>.json`. `done --find` refuses unless that verdict exists, is `refuted:false`, and cites the finding's PoC (anti-rubber-stamp). Fails CLOSED.\n- **RTL - Opus (fresh context):** `Skill(redteamlead)` for direction at a fork or when a vector stalls.\n- **Short tasks - Haiku:** `Skill(wiki-arsenal)` deep, `Skill(delegate)` (mechanical exploit-run), `Skill(ingest)` recon-parse. Bounded, fully-specified, single-shot ONLY.\n\nThe line that keeps quota safety: Haiku is allowed for a **bounded single job**, never for open-ended parallel hunting.\n\n## Discipline (carried, not restated - hunt-core owns the gates)\n\n- **Do NOT** invoke `superpowers:brainstorming` or `superpowers:writing-plans` mid-campaign, and keep\n  no parallel `TaskCreate` list. The board is the plan.\n- Model routing (see `## Model routing`): Opus-1M drives the loop; bounded short tasks go to Haiku;\n  the mandatory Opus **verifier** gates every finding (`done --find` refuses without a passing\n  `verdicts\u002F\u003CF>.json`). Still **no open-ended hunter fan-out** (it exhausted the weekly quota last\n  time) - Haiku is only for single, fully-specified jobs.\n- Load-bearing exploit requests go through Burp Repeater when it is reachable; degrade to\n  `capture.sh req` when it is not. Never block on Burp.\n- Scope and the enumeration ceiling come from `scope.md`, never from this skill.\n- **RCE-first:** with >1 vector open, take the code-exec one first - it is the attack vector with\n  impact; chase lower-impact classes only after code-exec is ruled out or the target needs them.\n- **Read whole, not grep:** on a post-foothold host where a sudoer has no findable password and the\n  usual vectors dead-end, READ `\u002Fetc\u002Fpam.d\u002F{sudo,su}` + `\u002Fetc\u002Fsudoers.d\u002F*` and linpeas output WHOLE -\n  a `pam_ssh_agent_auth`\u002F`pam_exec`\u002F`NOPASSWD` line is the tell a grep skips. See [[linux-privesc]].\n- **Long tools:** run pspy\u002Flinpeas via `bash scripts\u002Fvm-bg.sh \u003Ceng> \u003Cwin> '\u003Ctool>'` (stages to\n  `\u002Fdev\u002Fshm`, runs in the stabilized shell, `--read`\u002F`--wait 120` the logfile); never retry a broken\n  tool pattern >2x - switch method or call `Skill(redteamlead)`.\n\n## Close-out\n\nWhen `next` prints the close-out chain, run it: `Skill(triage)` -> `Skill(evidence)` ->\n`Skill(report)` -> `Skill(learn)`.\n\n## If the driver is unavailable\n\nManual fallback, same gates by hand: read `Approach.md`, take the top open row for the current\nasset, run its wiki lookup then its hunt skill, capture `req` evidence, mark it `[x]`; on exhaustion\none `Deadends.md` line and `[!]`.\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fbb-workflow",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill bb-workflow",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill bb-workflow",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill bb-workflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fbb-workflow\u002FSKILL.md",true,[],[47,55,60,67,74,81],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":54},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":56,"name":49,"nameZh":6,"description":50,"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":54},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":54},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":54},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":54},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":54},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]