[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EK9CSZ2WBX15ENZ0FMXK6F":3,"skill-same:01M7EK9CSZ2WBX15ENZ0FMXK6F":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},"01M7EK9CSZ2WBX15ENZ0FMXK6F","hunt-auth",null,"Auth bypass and ATO hunting - legacy protocol matrix (XMLRPC, SharePoint \u002F_vti_bin\u002F, EWS, Citrix, etc.), JWT manipulation, password reset poisoning, SAML auth bypass, session fixation. Wiki-first, FIND schema output.","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\u002Fhunt-auth\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: hunt-auth\ndescription: Auth bypass and ATO hunting - legacy protocol matrix (XMLRPC, SharePoint \u002F_vti_bin\u002F, EWS, Citrix, etc.), JWT manipulation, password reset poisoning, SAML auth bypass, session fixation. Wiki-first, FIND schema output.\n---\n\n# Hunt: Auth Bypass & Account Takeover\n\n**Assumes `hunt-core`** for the scope gate, two-account rule, confirmation gate, enumeration limits, stop conditions, wiki protocol, FIND output, and Deadends. Do not re-derive any of that here.\n\n## Wiki\n\n```\nqmd_query \"authentication bypass account takeover password reset poisoning session fixation legacy protocol\" via wiki-search MCP\n```\n\nHub: [[web-moc]] (live index). Primary page: [[authentication-attacks]]. Payload arsenal: `wiki\u002Fpayloads\u002F{auth-bypass,jwt,oauth-saml,session,mfa-bypass,crypto}.md`.\nAnchors: [[session-management-attacks]], [[mfa-bypass]].\n\n## Attack surface (ranked)\n\nProbe in this order; a higher entry is more often unguarded than a cleverer payload on the main form is likely to land.\n\n1. **Legacy protocol endpoints** (matrix below) - a second door to the same credential store, frequently with no rate limit, MFA, or CAPTCHA. Probe first on any custom\u002Fbranded login.\n2. **Password reset flows** - host-header poisoning, token in Referer, token reuse\u002Fexpiry, reset that does not invalidate live sessions.\n3. **Session and MFA** - fixation, missing rotation on privilege change, MFA-optional endpoints, JWT manipulation.\n4. **Read the login form's fields, not just the endpoint.** A login that takes **username only, no password field** is instant ATO - just submit the privileged\u002Ftarget username (custom auth on a CTF\u002Flab app does this constantly). Same for a \"just email\"\u002F\"just token\" form with no secret.\n5. **Predictable\u002Fleaked signing key -> forge as any user.** When auth or a \"signed message\" rests on a per-user key, hunt for a `\u002Fdebug`, docs, or `\u002Fabout` endpoint (or source) that discloses the **key-derivation** (deterministic seed like `f(username, CONST)`, `nextprime(int(SHA256(seed)))`). If the derivation is known, reconstruct the private key offline and forge signatures\u002Fsessions\u002FJWTs for admin - no factoring, modulus size irrelevant. Build + oracle-brute steps in [[cryptography-attacks]] (\"RSA private key from a known\u002Fdeterministic seed\").\n\n## Legacy Protocol Matrix (Probe First on Any Custom-Branded Login)\n\nWhen a target has a custom\u002Fbranded login UI, ALWAYS probe the platform's legacy protocol endpoints. These often accept native credentials with NO rate limit, NO MFA, NO CAPTCHA.\n\n| Target tech | Legacy endpoint | Bypass surface |\n|---|---|---|\n| WordPress | `\u002Fxmlrpc.php` | Native WP creds; bypasses SSO, MFA, IP-allow on \u002Fwp-login.php |\n| SharePoint | `\u002F_vti_bin\u002FAuthentication.asmx` | SOAP Login op; FedAuth cookie returned; no rate limit observed |\n| SharePoint REST | `\u002F_api\u002Fcontextinfo` (POST) | Anonymous FormDigest issuance |\n| Atlassian Jira\u002FConfluence | `\u002Frest\u002Fauth\u002F1\u002Fsession` | Native creds accepted even when Atlassian Access SSO enforced on UI |\n| Exchange \u002F OWA | `\u002FEWS\u002FExchange.asmx`, `\u002FMicrosoft-Server-ActiveSync` | NTLM\u002FBasic; bypasses OWA MFA restrictions |\n| Citrix NetScaler | `\u002Fvpn\u002Findex.html`, `\u002Fcgi\u002Flogin` | Native AD credentials independent of MFA wrappers |\n| F5 BIG-IP | `\u002Fmgmt\u002Ftm\u002Futil\u002Fbash`, `\u002Ftmui\u002Flogin.jsp` | Native admin creds |\n| Spring Boot | `\u002Factuator\u002F*` | Sometimes anonymously enumerable |\n| Jenkins | `\u002FjnlpJars\u002Fjenkins-cli.jar`, `\u002Fscript` | API tokens + native auth |\n| Apache Tomcat | `\u002Fmanager\u002Fhtml` | Native Tomcat realm creds |\n| Drupal | `\u002Fuser\u002Flogin?_format=json` | JSON POST accepts native passwords independent of SSO middleware |\n| Generic ASP.NET | `*.asmx?WSDL`, `trace.axd`, `elmah.axd` | Each ASMX may take creds independently |\n\n**How to use:**\n1. Identify tech stack from headers\u002Fpaths\n2. Probe legacy endpoint anonymously (confirm reachable, not 403\u002F404)\n3. Test with synthetic credentials - confirm differential (success vs failure)\n4. Verify NO rate limit against a synthetic or your OWN test account (never a real user - every failed attempt counts toward account lockout): send a bounded burst - 5 by default per hunt-core, 20 ceiling with operator approval, 0 under `no_bruteforce` - and confirm uniform timing, no `429`, no lockout counter. The ABSENCE of the limit is the finding; do not actually brute-force to prove it.\n5. Confirmed when the endpoint takes native creds with no rate limit \u002F MFA \u002F CAPTCHA (severity below).\n\n## JWT Attacks\n```bash\n# 1. Decode JWT\necho \"HEADER.PAYLOAD.SIGNATURE\" | cut -d. -f2 | base64 -d 2>\u002Fdev\u002Fnull | python3 -m json.tool\n\n# 2. Test none algorithm\n# Change \"alg\":\"RS256\" -> \"alg\":\"none\", remove signature\neyJhbGciOiJub25lIn0.PAYLOAD.\n\n# 3. HS256\u002FRS256 key confusion\n# If RS256, try signing with public key as HS256 secret\n```\n\n## ATO Attack Paths (Priority Order)\n1. **Password reset poisoning**: `POST \u002Fforgot-password` with `X-Forwarded-Host: attacker.com` -> reset link sent to attacker\n2. **Reset token in Referer leak**: reset page loads external analytics -> full Referer with token leaked\n3. **Email change without re-auth**: `PUT \u002Fapi\u002Fuser\u002Femail {\"new_email\": \"attacker@evil.com\"}` without current_password\n4. **Session fixation**: set session cookie before auth -> persists after login\n5. **IDOR -> ATO chain**: `PATCH \u002Fapi\u002Fusers\u002F{victim_uid}` with attacker session -> change victim email -> reset password\n\n## Methodology\n1. Map all authentication entry points (main, admin, API, partner, mobile)\n2. Identify auth mechanism per entry (forms, SAML, OAuth, API key, session)\n3. Test legacy endpoints per tech stack (use matrix above)\n4. Probe XMLRPC if WordPress: `system.listMethods`, `wp.getUsersBlogs`\n5. Test JWT if present: none algorithm, key confusion, weak secret\n6. Test password reset: host header injection, token in Referer, token reuse after expiry\n7. Test email change: no re-auth, no confirmation\n7a. On a legacy PHP\u002FMySQL stack (old Apache\u002FPHP banner) with self-registration, try **SQL truncation** to forge a duplicate of a privileged username (register `admin`+spaces+junk, log in as `admin`\u002Fyourpass) - see [[authentication-attacks]] \"SQL Truncation Duplicate-Account Auth Bypass\".\n8. Verify impact: demonstrate full ATO on test account B from attacker session A, then clear the confirmation gate below\n9. **Distill when confirmed** (per hunt-core): a reusable legacy-endpoint bypass or JWT variant, GENERIC (no client host): `python3 scripts\u002Fwiki-stage.py --kind technique --slug \u003Cslug> --target-page techniques\u002Fweb\u002Fauthentication-attacks.md`\n\n## Drive it through Burp\n\nPush the load-bearing requests through Burp for operator visibility (`Skill(hunt-burp)`):\n- The password-reset request with the injected `X-Forwarded-Host` \u002F `Host`, and each JWT-tampered request (`alg:none`, key-confusion), go to **Repeater** so the operator can replay and inspect them.\n- The bounded rate-limit \u002F lockout probe (matrix step 4) goes to **Intruder** with the hunt-core bound, never a hand-rolled loop.\n- `scripts\u002Fcapture.sh burp` grabs the request+response PoC the moment it lands.\n\n## Confirmation gate\n\n**NOT confirmation:** a `200` on the login page or reset form; a different or friendlier error message; a password-reset email merely received; a JWT that decodes cleanly or whose `alg`\u002Fclaims you edited and the server did not reject; a legacy endpoint that returns `200` to an anonymous probe; the server \"accepting\" a modified token without acting on it.\n\n**IS confirmation:** an authenticated session obtained as a *different* user - exercise a capability only that account has - OR a reset token that actually resets another account's password and lets you log in as them. Reproduced from scratch in a clean session (fresh profile, no cached cookies) per hunt-core, with your own account ruled out as the thing you logged into.\n\n## Chaining\n\n- **Reset poisoning \u002F token leak -> ATO.** A host-header or Referer-leaked reset token completes a full victim takeover - report the chain, not the leak alone.\n- **Trusted JWT claim -> ATO.** A `sub`\u002F`user_id` the server trusts plus a weak or strippable signature is arbitrary account takeover.\n- **Hand off `hunt-federation`** for SSO\u002FOAuth\u002FSAML redirect_uri, state CSRF, and XSW signature attacks; this skill covers the SAML *auth-bypass* surface only.\n- **Hand off `hunt-idor`** for the trusted-identifier overlap - a `PATCH \u002Fusers\u002F{victim}` that rewrites a victim email is an IDOR that chains straight back here to reset-based ATO (ATO path 5).\n\n## Evasion\n\nWhen the primary login rate-limits or enforces MFA, the bypass is usually a *different entry point to the same credential store*, not a cleverer payload: the legacy endpoints above, an alternate host (mobile\u002Fpartner\u002FAPI), an older API version, or a SOAP\u002FJSON variant of the same auth call. For a hardened reset flow, vary the host-header injection vector (`X-Forwarded-Host`, dual `Host` headers, absolute-URI request line) rather than repeating one form.\n\n## Severity\n\nRated on demonstrated impact (per hunt-core), not the mechanism.\n\n| Condition | Typical |\n|---|---|\n| Auth bypass reaching an authenticated context with no credentials | critical |\n| Full ATO of a victim account (reset poisoning, trusted-JWT claim, session fixation) | critical \u002F high |\n| Full ATO requiring one victim click | high |\n| Unlimited credential brute-force endpoint confirmed (legacy protocol, no rate limit) | critical \u002F high |\n| Legacy endpoint reachable, accepts native creds, no rate limit, no creds tested yet | medium |\n\nUnauthenticated outranks authenticated. A precondition you cannot satisfy (a victim click, a cred list you do not hold) lowers it.\n","# Hunt: Auth Bypass & Account Takeover\n\n**Assumes `hunt-core`** for the scope gate, two-account rule, confirmation gate, enumeration limits, stop conditions, wiki protocol, FIND output, and Deadends. Do not re-derive any of that here.\n\n## Wiki\n\n```\nqmd_query \"authentication bypass account takeover password reset poisoning session fixation legacy protocol\" via wiki-search MCP\n```\n\nHub: [[web-moc]] (live index). Primary page: [[authentication-attacks]]. Payload arsenal: `wiki\u002Fpayloads\u002F{auth-bypass,jwt,oauth-saml,session,mfa-bypass,crypto}.md`.\nAnchors: [[session-management-attacks]], [[mfa-bypass]].\n\n## Attack surface (ranked)\n\nProbe in this order; a higher entry is more often unguarded than a cleverer payload on the main form is likely to land.\n\n1. **Legacy protocol endpoints** (matrix below) - a second door to the same credential store, frequently with no rate limit, MFA, or CAPTCHA. Probe first on any custom\u002Fbranded login.\n2. **Password reset flows** - host-header poisoning, token in Referer, token reuse\u002Fexpiry, reset that does not invalidate live sessions.\n3. **Session and MFA** - fixation, missing rotation on privilege change, MFA-optional endpoints, JWT manipulation.\n4. **Read the login form's fields, not just the endpoint.** A login that takes **username only, no password field** is instant ATO - just submit the privileged\u002Ftarget username (custom auth on a CTF\u002Flab app does this constantly). Same for a \"just email\"\u002F\"just token\" form with no secret.\n5. **Predictable\u002Fleaked signing key -> forge as any user.** When auth or a \"signed message\" rests on a per-user key, hunt for a `\u002Fdebug`, docs, or `\u002Fabout` endpoint (or source) that discloses the **key-derivation** (deterministic seed like `f(username, CONST)`, `nextprime(int(SHA256(seed)))`). If the derivation is known, reconstruct the private key offline and forge signatures\u002Fsessions\u002FJWTs for admin - no factoring, modulus size irrelevant. Build + oracle-brute steps in [[cryptography-attacks]] (\"RSA private key from a known\u002Fdeterministic seed\").\n\n## Legacy Protocol Matrix (Probe First on Any Custom-Branded Login)\n\nWhen a target has a custom\u002Fbranded login UI, ALWAYS probe the platform's legacy protocol endpoints. These often accept native credentials with NO rate limit, NO MFA, NO CAPTCHA.\n\n| Target tech | Legacy endpoint | Bypass surface |\n|---|---|---|\n| WordPress | `\u002Fxmlrpc.php` | Native WP creds; bypasses SSO, MFA, IP-allow on \u002Fwp-login.php |\n| SharePoint | `\u002F_vti_bin\u002FAuthentication.asmx` | SOAP Login op; FedAuth cookie returned; no rate limit observed |\n| SharePoint REST | `\u002F_api\u002Fcontextinfo` (POST) | Anonymous FormDigest issuance |\n| Atlassian Jira\u002FConfluence | `\u002Frest\u002Fauth\u002F1\u002Fsession` | Native creds accepted even when Atlassian Access SSO enforced on UI |\n| Exchange \u002F OWA | `\u002FEWS\u002FExchange.asmx`, `\u002FMicrosoft-Server-ActiveSync` | NTLM\u002FBasic; bypasses OWA MFA restrictions |\n| Citrix NetScaler | `\u002Fvpn\u002Findex.html`, `\u002Fcgi\u002Flogin` | Native AD credentials independent of MFA wrappers |\n| F5 BIG-IP | `\u002Fmgmt\u002Ftm\u002Futil\u002Fbash`, `\u002Ftmui\u002Flogin.jsp` | Native admin creds |\n| Spring Boot | `\u002Factuator\u002F*` | Sometimes anonymously enumerable |\n| Jenkins | `\u002FjnlpJars\u002Fjenkins-cli.jar`, `\u002Fscript` | API tokens + native auth |\n| Apache Tomcat | `\u002Fmanager\u002Fhtml` | Native Tomcat realm creds |\n| Drupal | `\u002Fuser\u002Flogin?_format=json` | JSON POST accepts native passwords independent of SSO middleware |\n| Generic ASP.NET | `*.asmx?WSDL`, `trace.axd`, `elmah.axd` | Each ASMX may take creds independently |\n\n**How to use:**\n1. Identify tech stack from headers\u002Fpaths\n2. Probe legacy endpoint anonymously (confirm reachable, not 403\u002F404)\n3. Test with synthetic credentials - confirm differential (success vs failure)\n4. Verify NO rate limit against a synthetic or your OWN test account (never a real user - every failed attempt counts toward account lockout): send a bounded burst - 5 by default per hunt-core, 20 ceiling with operator approval, 0 under `no_bruteforce` - and confirm uniform timing, no `429`, no lockout counter. The ABSENCE of the limit is the finding; do not actually brute-force to prove it.\n5. Confirmed when the endpoint takes native creds with no rate limit \u002F MFA \u002F CAPTCHA (severity below).\n\n## JWT Attacks\n```bash\n# 1. Decode JWT\necho \"HEADER.PAYLOAD.SIGNATURE\" | cut -d. -f2 | base64 -d 2>\u002Fdev\u002Fnull | python3 -m json.tool\n\n# 2. Test none algorithm\n# Change \"alg\":\"RS256\" -> \"alg\":\"none\", remove signature\neyJhbGciOiJub25lIn0.PAYLOAD.\n\n# 3. HS256\u002FRS256 key confusion\n# If RS256, try signing with public key as HS256 secret\n```\n\n## ATO Attack Paths (Priority Order)\n1. **Password reset poisoning**: `POST \u002Fforgot-password` with `X-Forwarded-Host: attacker.com` -> reset link sent to attacker\n2. **Reset token in Referer leak**: reset page loads external analytics -> full Referer with token leaked\n3. **Email change without re-auth**: `PUT \u002Fapi\u002Fuser\u002Femail {\"new_email\": \"attacker@evil.com\"}` without current_password\n4. **Session fixation**: set session cookie before auth -> persists after login\n5. **IDOR -> ATO chain**: `PATCH \u002Fapi\u002Fusers\u002F{victim_uid}` with attacker session -> change victim email -> reset password\n\n## Methodology\n1. Map all authentication entry points (main, admin, API, partner, mobile)\n2. Identify auth mechanism per entry (forms, SAML, OAuth, API key, session)\n3. Test legacy endpoints per tech stack (use matrix above)\n4. Probe XMLRPC if WordPress: `system.listMethods`, `wp.getUsersBlogs`\n5. Test JWT if present: none algorithm, key confusion, weak secret\n6. Test password reset: host header injection, token in Referer, token reuse after expiry\n7. Test email change: no re-auth, no confirmation\n7a. On a legacy PHP\u002FMySQL stack (old Apache\u002FPHP banner) with self-registration, try **SQL truncation** to forge a duplicate of a privileged username (register `admin`+spaces+junk, log in as `admin`\u002Fyourpass) - see [[authentication-attacks]] \"SQL Truncation Duplicate-Account Auth Bypass\".\n8. Verify impact: demonstrate full ATO on test account B from attacker session A, then clear the confirmation gate below\n9. **Distill when confirmed** (per hunt-core): a reusable legacy-endpoint bypass or JWT variant, GENERIC (no client host): `python3 scripts\u002Fwiki-stage.py --kind technique --slug \u003Cslug> --target-page techniques\u002Fweb\u002Fauthentication-attacks.md`\n\n## Drive it through Burp\n\nPush the load-bearing requests through Burp for operator visibility (`Skill(hunt-burp)`):\n- The password-reset request with the injected `X-Forwarded-Host` \u002F `Host`, and each JWT-tampered request (`alg:none`, key-confusion), go to **Repeater** so the operator can replay and inspect them.\n- The bounded rate-limit \u002F lockout probe (matrix step 4) goes to **Intruder** with the hunt-core bound, never a hand-rolled loop.\n- `scripts\u002Fcapture.sh burp` grabs the request+response PoC the moment it lands.\n\n## Confirmation gate\n\n**NOT confirmation:** a `200` on the login page or reset form; a different or friendlier error message; a password-reset email merely received; a JWT that decodes cleanly or whose `alg`\u002Fclaims you edited and the server did not reject; a legacy endpoint that returns `200` to an anonymous probe; the server \"accepting\" a modified token without acting on it.\n\n**IS confirmation:** an authenticated session obtained as a *different* user - exercise a capability only that account has - OR a reset token that actually resets another account's password and lets you log in as them. Reproduced from scratch in a clean session (fresh profile, no cached cookies) per hunt-core, with your own account ruled out as the thing you logged into.\n\n## Chaining\n\n- **Reset poisoning \u002F token leak -> ATO.** A host-header or Referer-leaked reset token completes a full victim takeover - report the chain, not the leak alone.\n- **Trusted JWT claim -> ATO.** A `sub`\u002F`user_id` the server trusts plus a weak or strippable signature is arbitrary account takeover.\n- **Hand off `hunt-federation`** for SSO\u002FOAuth\u002FSAML redirect_uri, state CSRF, and XSW signature attacks; this skill covers the SAML *auth-bypass* surface only.\n- **Hand off `hunt-idor`** for the trusted-identifier overlap - a `PATCH \u002Fusers\u002F{victim}` that rewrites a victim email is an IDOR that chains straight back here to reset-based ATO (ATO path 5).\n\n## Evasion\n\nWhen the primary login rate-limits or enforces MFA, the bypass is usually a *different entry point to the same credential store*, not a cleverer payload: the legacy endpoints above, an alternate host (mobile\u002Fpartner\u002FAPI), an older API version, or a SOAP\u002FJSON variant of the same auth call. For a hardened reset flow, vary the host-header injection vector (`X-Forwarded-Host`, dual `Host` headers, absolute-URI request line) rather than repeating one form.\n\n## Severity\n\nRated on demonstrated impact (per hunt-core), not the mechanism.\n\n| Condition | Typical |\n|---|---|\n| Auth bypass reaching an authenticated context with no credentials | critical |\n| Full ATO of a victim account (reset poisoning, trusted-JWT claim, session fixation) | critical \u002F high |\n| Full ATO requiring one victim click | high |\n| Unlimited credential brute-force endpoint confirmed (legacy protocol, no rate limit) | critical \u002F high |\n| Legacy endpoint reachable, accepts native creds, no rate limit, no creds tested yet | medium |\n\nUnauthenticated outranks authenticated. A precondition you cannot satisfy (a victim click, a cred list you do not hold) lowers it.\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fhunt-auth",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 hunt-auth",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill hunt-auth",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill hunt-auth","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fhunt-auth\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",[],[]]