[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M764FCP2BRPHDM7X7D06YR5B":3,"skill-same:01M764FCP2BRPHDM7X7D06YR5B":72},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":37,"ownerDescription":38,"updatedAt":39,"install":40,"resources":53},"01M764FCP2BRPHDM7X7D06YR5B","solve-challenge",null,"Solves CTF challenges by performing first-pass triage, identifying the dominant category, and routing execution to the right specialized ctf-* skill. Use when the user gives you a challenge bundle, a remote service, a suspicious file, or only a vague challenge description and you must determine where to start. Do not use it when the category is already clear and a specialized skill can be invoked directly; this is the dispatcher and recon entrypoint, not the deepest reference for category-specific techniques.","jiayaoqijia\u002Fcryptoskill","jiayaoqijia","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1453879?v=4","01M6GMYTX7Q7S504VC6E756ENR","YQ","01M6GMYV1QKJ1CC75MTTGT9PR0",81,"MIT","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdev-tools\u002Fabhay2008-solve-challenge\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdev-tools\u002Fabhay2008-solve-challenge\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: solve-challenge\ndescription: Solves CTF challenges by performing first-pass triage, identifying the dominant category, and routing execution to the right specialized ctf-* skill. Use when the user gives you a challenge bundle, a remote service, a suspicious file, or only a vague challenge description and you must determine where to start. Do not use it when the category is already clear and a specialized skill can be invoked directly; this is the dispatcher and recon entrypoint, not the deepest reference for category-specific techniques.\nlicense: MIT\ncompatibility: Requires filesystem-based agent (Claude Code or similar) with bash, Python 3, and internet access. Orchestrates other ctf-* skills.\nallowed-tools: Bash Read Write Edit Glob Grep Task WebFetch WebSearch Skill\nmetadata:\n  user-invocable: \"true\"\n  argument-hint: \"[category] [challenge-file-or-url]\"\n  author: Lukasz Jagiello\n---\n\n# CTF Challenge Solver\n\nYou're a skilled CTF player. Your goal is to solve the challenge and find the flag.\n\n## Environment Setup\n\nTwo setup strategies depending on your workflow:\n\n### Pre-install (recommended before competitions)\n\nUse the central installer entrypoint:\n\n```bash\nbash scripts\u002Finstall_ctf_tools.sh all\n```\n\nRun a narrower mode when you only want one tool group:\n\n```bash\nbash scripts\u002Finstall_ctf_tools.sh python\nbash scripts\u002Finstall_ctf_tools.sh apt\nbash scripts\u002Finstall_ctf_tools.sh brew\nbash scripts\u002Finstall_ctf_tools.sh gems\nbash scripts\u002Finstall_ctf_tools.sh go\nbash scripts\u002Finstall_ctf_tools.sh manual\n```\n\nThe full package lists now live in [scripts\u002Finstall_ctf_tools.sh](..\u002Fscripts\u002Finstall_ctf_tools.sh).\n\n### On-demand (during challenges)\n\nEach category skill's `SKILL.md` has a **Prerequisites** section listing only the tools needed for that category. Install as you go.\n\n## Workflow\n\nBefore selecting or escalating a model, read\n[difficulty-routing.md](difficulty-routing.md). Use its evidence-based scoring,\nstop-loss rules, and tier gates throughout the workflow.\n\n### Step 0: CTFd Platform Detection\n\nIf the CTF platform URL is known, check if it runs CTFd and switch to API-driven navigation:\n\n```bash\n# Detect CTFd (look for \u002Fapi\u002Fv1\u002F and \u002Fthemes\u002Fcore\u002F)\ncurl -s \"$CTF_URL\u002Fapi\u002Fv1\u002F\" | head -5\ncurl -s \"$CTF_URL\" | grep -oE '\u002Fthemes\u002Fcore\u002F'\n```\n\nIf CTFd is detected, **ask the user for their API token** (generated from CTFd Settings > Access Tokens). The token is not provided by default — the user must create one in the CTFd web UI first. Once provided, set the environment variables and proceed via API:\n\n```bash\nexport CTF_URL=\"https:\u002F\u002Fctf.example.com\"\nexport CTF_TOKEN=\"ctfd_...\"  # Ask user for this\n```\n\nInvoke `\u002Fctf-misc` and load its `ctfd-navigation.md` for the full API reference and Python client class.\n\n#### CTF Platform Interaction via Playwright MCP\n\nWhen the platform is **not** CTFd, has no usable API, or gates challenges behind a\nJS-rendered UI \u002F login, drive the platform in a real browser with **Playwright\nMCP** (`https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fplaywright-mcp`). This lets the agent read\nchallenge text, download attachments, keep a login session, and submit flags\ndirectly through the site.\n\n```text\nbrowser_navigate \"https:\u002F\u002Fctf.example.com\u002Fchallenges\"\nbrowser_snapshot                 # list challenges, points, categories (rendered)\nbrowser_click \u003Cchallenge ref>    # open a challenge card\nbrowser_snapshot                 # read description, hints, attachment links\nbrowser_click \u003Cattachment ref>   # download the challenge file (saved by the browser)\n# ... solve the challenge ...\nbrowser_type \u003Cflag input ref> \"flag{...}\"\nbrowser_click \u003Csubmit ref>\nbrowser_find text=\"Correct\"      # cheaper than a full snapshot to check the verdict\n```\n\n`browser_find` (text or regex over the accessibility tree) is the right tool\nwhenever you only need to confirm one value — reserve full `browser_snapshot`\nfor when you need element refs to click or type into.\n\nLogin sessions (cookies\u002FlocalStorage) persist across tool calls, so authenticate\nonce and every later navigation is authorized. For general browser-automation\ntooling see [..\u002Fctf-web\u002Ftools-mcp.md](..\u002Fctf-web\u002Ftools-mcp.md#playwright-mcp-browser-automation).\n\n**Prefer a native API when one exists** (CTFd token flow above is faster and more\nreliable); use Playwright MCP for platforms without an API or when the challenge\nlist only renders client-side.\n\n### Step 1: Recon\n\n1. **Explore files** -- List the challenge directory, run `file *` on everything\n2. **Triage binaries** -- `strings`, `xxd | head`, `binwalk`, `checksec` on binaries\n3. **Fetch links** -- If the challenge mentions URLs, fetch them FIRST for context\n4. **Connect** -- Try remote services (`nc`) to understand what they expect\n5. **Read hints** -- Challenge descriptions, filenames, and comments often contain clues\n\n### Step 2: Categorize\n\nDetermine the primary category, then invoke the matching skill.\n\n**By file type:**\n- `.pcap`, `.pcapng`, `.evtx`, `.raw`, `.dd`, `.E01` -> forensics\n- `.elf`, `.exe`, `.so`, `.dll`, binary with no extension -> reverse or pwn (check if remote service provided -- if yes, likely pwn)\n- `.py`, `.sage`, `.txt` with numbers -> crypto\n- `.apk`, `.wasm`, `.pyc` -> reverse\n- firmware\u002Fimage (`firmware.bin`, `.img`, vendor update), `.sr`\u002F`.vcd` logic capture, CAN log -> hardware\n- `.safetensors`, `.pt`, `.pth`, `.bin`, `.onnx` -> ai-ml\n- Web URL or source code with HTML\u002FJS\u002FPHP\u002Ftemplates -> web\n- Images, audio, PDFs with no obvious content -> forensics (steganography)\n\n**By challenge description keywords:**\n- \"buffer overflow\", \"ROP\", \"shellcode\", \"libc\", \"heap\" -> pwn\n- \"RSA\", \"AES\", \"cipher\", \"encrypt\", \"prime\", \"modulus\", \"lattice\", \"LWE\", \"GCM\" -> crypto\n- \"XSS\", \"SQL\", \"injection\", \"cookie\", \"JWT\", \"SSRF\" -> web\n- \"disk image\", \"memory dump\", \"packet capture\", \"registry\", \"power trace\", \"side-channel\", \"spectrogram\", \"audio tracks\", \"MKV\" -> forensics\n- \"find\", \"locate\", \"identify\", \"who\", \"where\" -> osint\n- \"obfuscated\", \"packed\", \"C2\", \"malware\", \"beacon\" -> malware\n- \"prompt injection\", \"LoRA\", \"adversarial\", \"model weights\", \"embedding\" -> ai-ml\n- \"jail\", \"sandbox\", \"escape\", \"restricted shell\", \"no quotes\", \"eval\" -> jail\n- \"metadata\", \"IAM\", \"S3\", \"kubectl\", \"container escape\", \"docker.sock\" -> cloud\n- \"firmware\", \"UART\", \"JTAG\", \"SPI flash\", \"logic analyzer\", \"power trace\", \"CAN bus\" -> hardware\n- \"encoding\", \"signal\", \"game\", \"Nim\", \"commitment\", \"Gray code\" -> misc\n\n**By service behavior:**\n- Port with interactive prompt, crash on long input -> pwn\n- HTTP service -> web\n- netcat with math\u002Fcrypto puzzles -> crypto\n- netcat with restricted shell or eval -> misc (jail)\n\n### Step 3: Invoke the Category Skill\n\nOnce you identify the category, **invoke the matching skill** to get specialized techniques:\n\n| Category | Invoke | When to Use |\n|----------|--------|-------------|\n| Web | `\u002Fctf-web` | XSS, SQLi, SSTI, SSRF, JWT, file uploads, prototype pollution |\n| Pwn | `\u002Fctf-pwn` | Buffer overflow, format string, heap, ROP, sandbox escape |\n| Crypto | `\u002Fctf-crypto` | RSA, AES, ECC, PRNG, ZKP, classical ciphers |\n| Reverse | `\u002Fctf-reverse` | Binary analysis, game clients, VMs, obfuscated code |\n| Forensics | `\u002Fctf-forensics` | Disk images, memory dumps, event logs, stego, network captures |\n| OSINT | `\u002Fctf-osint` | Social media, geolocation, DNS, public records |\n| Malware | `\u002Fctf-malware` | Obfuscated scripts, C2 traffic, PE\u002F.NET analysis |\n| AI\u002FML | `\u002Fctf-ai-ml` | Model weights (`.safetensors`, `.pt`, `.pth`, `.bin`, `.onnx`), prompt injection, LoRA adapters, adversarial examples |\n| Jail | `\u002Fctf-jail` | Python\u002Fbash jails, restricted eval, sandbox escapes, `disable_functions` |\n| Cloud | `\u002Fctf-cloud` | Cloud metadata, IAM, S3, Kubernetes, container escape, CI\u002FCD |\n| Hardware | `\u002Fctf-hardware` | Firmware, UART\u002FJTAG\u002FSPI, logic capture, CAN, side channel |\n| Misc | `\u002Fctf-misc` | Encodings, RF\u002FSDR demod, esoteric languages, constraint solving, games |\n\nYou can also invoke `\u002Fctf-\u003Ccategory>` to load the full skill instructions with detailed techniques.\n\n### Step 4: Pivot When Stuck\n\nIf your first approach doesn't work:\n\n1. **Re-examine assumptions** -- Is this really the category you think? A \"web\" challenge might need crypto for JWT forgery. A \"forensics\" PCAP might contain a pwn exploit to replay.\n2. **Try a different category skill** -- Many challenges span multiple categories. Invoke a second skill for the cross-cutting technique.\n3. **Look for what you missed** -- Hidden files, alternate ports, response headers, comments in source, metadata in images.\n4. **Simplify** -- If an exploit is too complex, check if there's a simpler path (default creds, known CVE, logic bug).\n5. **Check edge cases** -- Off-by-one, race conditions, integer overflow, encoding mismatches.\n\n**Common multi-category patterns:**\n- Forensics + Crypto: encrypted data in PCAP\u002Fdisk image, need crypto to decrypt\n- Web + Reverse: WASM or obfuscated JS in web challenge\n- Web + Crypto: JWT forgery, custom MAC\u002Fsignature schemes\n- Reverse + Pwn: reverse the binary first, then exploit the vulnerability\n- Forensics + OSINT: recover data from dump, then trace it via public sources\n- Misc + Crypto: jail escape requires building crypto primitives under constraints\n- OSINT + Stego: social media posts with unicode homoglyph steganography (Cyrillic lookalikes encode bits)\n- Web + Forensics: paywall bypass (curl reveals content hidden by CSS overlays)\n- Misc + Crypto + Game Theory: multi-phase interactive challenges with AES decryption → HMAC commitment → combinatorial game solving (GF(256) Nim)\n- Crypto + Geometry + Lattice: multi-layer challenges progressing from spatial reconstruction → subspace recovery → LWE solving → AES-GCM decryption\n- Forensics + Signal Processing: power traces \u002F side-channel analysis requiring statistical analysis of measurement data\n- Forensics + Network + Encoding: timing-based encoding in PCAP (inter-packet intervals encode binary data)\n\n### Step 5: Generate Write-up\n\nAfter solving the challenge, invoke `\u002Fctf-writeup` to generate a standardized submission-style writeup — concise, reproducible, and ready for competition organizers or teammates to validate.\n\n## Flag Formats\n\nFlags vary by CTF. Common formats:\n- `flag{...}`, `FLAG{...}`, `CTF{...}`, `TEAM{...}`\n- Custom prefixes: check the challenge description or CTF rules for the format (e.g., `ENO{...}`, `HTB{...}`, `picoCTF{...}`)\n- Sometimes just a plaintext string with no wrapper\n\n**Validation rule (important):**\n- If you find multiple flag-like strings, treat them as candidates and validate before finalizing.\n- Prefer the token tied to the intended artifact\u002Fworkflow (not random metadata noise or obvious decoys).\n- Do a corpus-wide uniqueness check and include the source file\u002Fpath when reporting.\n\n```bash\n# Search for common flag patterns in files\ngrep -rniE '(flag|ctf|eno|htb|pico)\\{' .\n# Search in binary\u002Fmemory output\nstrings output.bin | grep -iE '\\{.*\\}'\n```\n\n## Quick Reference\n\n```bash\n# Recon\nfile *                                    # Identify file types\nstrings binary | grep -i flag             # Quick string search\nxxd binary | head -20                     # Hex dump header\nbinwalk -e firmware.bin                   # Extract embedded files\nchecksec --file=binary                    # Check binary protections\n\n# Connect\nnc host port                              # Connect to challenge\necho -e \"answer1\\nanswer2\" | nc host port # Scripted input\ncurl -v http:\u002F\u002Fhost:port\u002F                 # HTTP recon\n\n# Python exploit template\npython3 -c \"\nfrom pwn import *\nr = remote('host', port)\nr.interactive()\n\"\n```\n\n## Challenge\n\n$ARGUMENTS\n","# CTF Challenge Solver\n\nYou're a skilled CTF player. Your goal is to solve the challenge and find the flag.\n\n## Environment Setup\n\nTwo setup strategies depending on your workflow:\n\n### Pre-install (recommended before competitions)\n\nUse the central installer entrypoint:\n\n```bash\nbash scripts\u002Finstall_ctf_tools.sh all\n```\n\nRun a narrower mode when you only want one tool group:\n\n```bash\nbash scripts\u002Finstall_ctf_tools.sh python\nbash scripts\u002Finstall_ctf_tools.sh apt\nbash scripts\u002Finstall_ctf_tools.sh brew\nbash scripts\u002Finstall_ctf_tools.sh gems\nbash scripts\u002Finstall_ctf_tools.sh go\nbash scripts\u002Finstall_ctf_tools.sh manual\n```\n\nThe full package lists now live in [scripts\u002Finstall_ctf_tools.sh](..\u002Fscripts\u002Finstall_ctf_tools.sh).\n\n### On-demand (during challenges)\n\nEach category skill's `SKILL.md` has a **Prerequisites** section listing only the tools needed for that category. Install as you go.\n\n## Workflow\n\nBefore selecting or escalating a model, read\n[difficulty-routing.md](difficulty-routing.md). Use its evidence-based scoring,\nstop-loss rules, and tier gates throughout the workflow.\n\n### Step 0: CTFd Platform Detection\n\nIf the CTF platform URL is known, check if it runs CTFd and switch to API-driven navigation:\n\n```bash\n# Detect CTFd (look for \u002Fapi\u002Fv1\u002F and \u002Fthemes\u002Fcore\u002F)\ncurl -s \"$CTF_URL\u002Fapi\u002Fv1\u002F\" | head -5\ncurl -s \"$CTF_URL\" | grep -oE '\u002Fthemes\u002Fcore\u002F'\n```\n\nIf CTFd is detected, **ask the user for their API token** (generated from CTFd Settings > Access Tokens). The token is not provided by default — the user must create one in the CTFd web UI first. Once provided, set the environment variables and proceed via API:\n\n```bash\nexport CTF_URL=\"https:\u002F\u002Fctf.example.com\"\nexport CTF_TOKEN=\"ctfd_...\"  # Ask user for this\n```\n\nInvoke `\u002Fctf-misc` and load its `ctfd-navigation.md` for the full API reference and Python client class.\n\n#### CTF Platform Interaction via Playwright MCP\n\nWhen the platform is **not** CTFd, has no usable API, or gates challenges behind a\nJS-rendered UI \u002F login, drive the platform in a real browser with **Playwright\nMCP** (`https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fplaywright-mcp`). This lets the agent read\nchallenge text, download attachments, keep a login session, and submit flags\ndirectly through the site.\n\n```text\nbrowser_navigate \"https:\u002F\u002Fctf.example.com\u002Fchallenges\"\nbrowser_snapshot                 # list challenges, points, categories (rendered)\nbrowser_click \u003Cchallenge ref>    # open a challenge card\nbrowser_snapshot                 # read description, hints, attachment links\nbrowser_click \u003Cattachment ref>   # download the challenge file (saved by the browser)\n# ... solve the challenge ...\nbrowser_type \u003Cflag input ref> \"flag{...}\"\nbrowser_click \u003Csubmit ref>\nbrowser_find text=\"Correct\"      # cheaper than a full snapshot to check the verdict\n```\n\n`browser_find` (text or regex over the accessibility tree) is the right tool\nwhenever you only need to confirm one value — reserve full `browser_snapshot`\nfor when you need element refs to click or type into.\n\nLogin sessions (cookies\u002FlocalStorage) persist across tool calls, so authenticate\nonce and every later navigation is authorized. For general browser-automation\ntooling see [..\u002Fctf-web\u002Ftools-mcp.md](..\u002Fctf-web\u002Ftools-mcp.md#playwright-mcp-browser-automation).\n\n**Prefer a native API when one exists** (CTFd token flow above is faster and more\nreliable); use Playwright MCP for platforms without an API or when the challenge\nlist only renders client-side.\n\n### Step 1: Recon\n\n1. **Explore files** -- List the challenge directory, run `file *` on everything\n2. **Triage binaries** -- `strings`, `xxd | head`, `binwalk`, `checksec` on binaries\n3. **Fetch links** -- If the challenge mentions URLs, fetch them FIRST for context\n4. **Connect** -- Try remote services (`nc`) to understand what they expect\n5. **Read hints** -- Challenge descriptions, filenames, and comments often contain clues\n\n### Step 2: Categorize\n\nDetermine the primary category, then invoke the matching skill.\n\n**By file type:**\n- `.pcap`, `.pcapng`, `.evtx`, `.raw`, `.dd`, `.E01` -> forensics\n- `.elf`, `.exe`, `.so`, `.dll`, binary with no extension -> reverse or pwn (check if remote service provided -- if yes, likely pwn)\n- `.py`, `.sage`, `.txt` with numbers -> crypto\n- `.apk`, `.wasm`, `.pyc` -> reverse\n- firmware\u002Fimage (`firmware.bin`, `.img`, vendor update), `.sr`\u002F`.vcd` logic capture, CAN log -> hardware\n- `.safetensors`, `.pt`, `.pth`, `.bin`, `.onnx` -> ai-ml\n- Web URL or source code with HTML\u002FJS\u002FPHP\u002Ftemplates -> web\n- Images, audio, PDFs with no obvious content -> forensics (steganography)\n\n**By challenge description keywords:**\n- \"buffer overflow\", \"ROP\", \"shellcode\", \"libc\", \"heap\" -> pwn\n- \"RSA\", \"AES\", \"cipher\", \"encrypt\", \"prime\", \"modulus\", \"lattice\", \"LWE\", \"GCM\" -> crypto\n- \"XSS\", \"SQL\", \"injection\", \"cookie\", \"JWT\", \"SSRF\" -> web\n- \"disk image\", \"memory dump\", \"packet capture\", \"registry\", \"power trace\", \"side-channel\", \"spectrogram\", \"audio tracks\", \"MKV\" -> forensics\n- \"find\", \"locate\", \"identify\", \"who\", \"where\" -> osint\n- \"obfuscated\", \"packed\", \"C2\", \"malware\", \"beacon\" -> malware\n- \"prompt injection\", \"LoRA\", \"adversarial\", \"model weights\", \"embedding\" -> ai-ml\n- \"jail\", \"sandbox\", \"escape\", \"restricted shell\", \"no quotes\", \"eval\" -> jail\n- \"metadata\", \"IAM\", \"S3\", \"kubectl\", \"container escape\", \"docker.sock\" -> cloud\n- \"firmware\", \"UART\", \"JTAG\", \"SPI flash\", \"logic analyzer\", \"power trace\", \"CAN bus\" -> hardware\n- \"encoding\", \"signal\", \"game\", \"Nim\", \"commitment\", \"Gray code\" -> misc\n\n**By service behavior:**\n- Port with interactive prompt, crash on long input -> pwn\n- HTTP service -> web\n- netcat with math\u002Fcrypto puzzles -> crypto\n- netcat with restricted shell or eval -> misc (jail)\n\n### Step 3: Invoke the Category Skill\n\nOnce you identify the category, **invoke the matching skill** to get specialized techniques:\n\n| Category | Invoke | When to Use |\n|----------|--------|-------------|\n| Web | `\u002Fctf-web` | XSS, SQLi, SSTI, SSRF, JWT, file uploads, prototype pollution |\n| Pwn | `\u002Fctf-pwn` | Buffer overflow, format string, heap, ROP, sandbox escape |\n| Crypto | `\u002Fctf-crypto` | RSA, AES, ECC, PRNG, ZKP, classical ciphers |\n| Reverse | `\u002Fctf-reverse` | Binary analysis, game clients, VMs, obfuscated code |\n| Forensics | `\u002Fctf-forensics` | Disk images, memory dumps, event logs, stego, network captures |\n| OSINT | `\u002Fctf-osint` | Social media, geolocation, DNS, public records |\n| Malware | `\u002Fctf-malware` | Obfuscated scripts, C2 traffic, PE\u002F.NET analysis |\n| AI\u002FML | `\u002Fctf-ai-ml` | Model weights (`.safetensors`, `.pt`, `.pth`, `.bin`, `.onnx`), prompt injection, LoRA adapters, adversarial examples |\n| Jail | `\u002Fctf-jail` | Python\u002Fbash jails, restricted eval, sandbox escapes, `disable_functions` |\n| Cloud | `\u002Fctf-cloud` | Cloud metadata, IAM, S3, Kubernetes, container escape, CI\u002FCD |\n| Hardware | `\u002Fctf-hardware` | Firmware, UART\u002FJTAG\u002FSPI, logic capture, CAN, side channel |\n| Misc | `\u002Fctf-misc` | Encodings, RF\u002FSDR demod, esoteric languages, constraint solving, games |\n\nYou can also invoke `\u002Fctf-\u003Ccategory>` to load the full skill instructions with detailed techniques.\n\n### Step 4: Pivot When Stuck\n\nIf your first approach doesn't work:\n\n1. **Re-examine assumptions** -- Is this really the category you think? A \"web\" challenge might need crypto for JWT forgery. A \"forensics\" PCAP might contain a pwn exploit to replay.\n2. **Try a different category skill** -- Many challenges span multiple categories. Invoke a second skill for the cross-cutting technique.\n3. **Look for what you missed** -- Hidden files, alternate ports, response headers, comments in source, metadata in images.\n4. **Simplify** -- If an exploit is too complex, check if there's a simpler path (default creds, known CVE, logic bug).\n5. **Check edge cases** -- Off-by-one, race conditions, integer overflow, encoding mismatches.\n\n**Common multi-category patterns:**\n- Forensics + Crypto: encrypted data in PCAP\u002Fdisk image, need crypto to decrypt\n- Web + Reverse: WASM or obfuscated JS in web challenge\n- Web + Crypto: JWT forgery, custom MAC\u002Fsignature schemes\n- Reverse + Pwn: reverse the binary first, then exploit the vulnerability\n- Forensics + OSINT: recover data from dump, then trace it via public sources\n- Misc + Crypto: jail escape requires building crypto primitives under constraints\n- OSINT + Stego: social media posts with unicode homoglyph steganography (Cyrillic lookalikes encode bits)\n- Web + Forensics: paywall bypass (curl reveals content hidden by CSS overlays)\n- Misc + Crypto + Game Theory: multi-phase interactive challenges with AES decryption → HMAC commitment → combinatorial game solving (GF(256) Nim)\n- Crypto + Geometry + Lattice: multi-layer challenges progressing from spatial reconstruction → subspace recovery → LWE solving → AES-GCM decryption\n- Forensics + Signal Processing: power traces \u002F side-channel analysis requiring statistical analysis of measurement data\n- Forensics + Network + Encoding: timing-based encoding in PCAP (inter-packet intervals encode binary data)\n\n### Step 5: Generate Write-up\n\nAfter solving the challenge, invoke `\u002Fctf-writeup` to generate a standardized submission-style writeup — concise, reproducible, and ready for competition organizers or teammates to validate.\n\n## Flag Formats\n\nFlags vary by CTF. Common formats:\n- `flag{...}`, `FLAG{...}`, `CTF{...}`, `TEAM{...}`\n- Custom prefixes: check the challenge description or CTF rules for the format (e.g., `ENO{...}`, `HTB{...}`, `picoCTF{...}`)\n- Sometimes just a plaintext string with no wrapper\n\n**Validation rule (important):**\n- If you find multiple flag-like strings, treat them as candidates and validate before finalizing.\n- Prefer the token tied to the intended artifact\u002Fworkflow (not random metadata noise or obvious decoys).\n- Do a corpus-wide uniqueness check and include the source file\u002Fpath when reporting.\n\n```bash\n# Search for common flag patterns in files\ngrep -rniE '(flag|ctf|eno|htb|pico)\\{' .\n# Search in binary\u002Fmemory output\nstrings output.bin | grep -iE '\\{.*\\}'\n```\n\n## Quick Reference\n\n```bash\n# Recon\nfile *                                    # Identify file types\nstrings binary | grep -i flag             # Quick string search\nxxd binary | head -20                     # Hex dump header\nbinwalk -e firmware.bin                   # Extract embedded files\nchecksec --file=binary                    # Check binary protections\n\n# Connect\nnc host port                              # Connect to challenge\necho -e \"answer1\\nanswer2\" | nc host port # Scripted input\ncurl -v http:\u002F\u002Fhost:port\u002F                 # HTTP recon\n\n# Python exploit template\npython3 -c \"\nfrom pwn import *\nr = remote('host', port)\nr.interactive()\n\"\n```\n\n## Challenge\n\n$ARGUMENTS\n",{"name":5,"license":15,"metadata":25,"description":7,"allowed-tools":29,"compatibility":30},{"author":26,"argument-hint":27,"user-invocable":28},"Lukasz Jagiello","[category] [challenge-file-or-url]","true","Bash Read Write Edit Glob Grep Task WebFetch WebSearch Skill","Requires filesystem-based agent (Claude Code or similar) with bash, Python 3, and internet access. Orchestrates other ctf-* skills.","main","fa749116cef035d5ee7c7e7deb1aa875e30afc91","skills\u002Fdev-tools\u002Fabhay2008-solve-challenge",17,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia","https:\u002F\u002Feth2030.com","Hardcore infra. Building @alt-research and applied cryptography.","2026-11-15 02:28:10",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add jiayaoqijia\u002Fcryptoskill --skill solve-challenge",{"tool":46,"command":47},"bunx","bunx skills add jiayaoqijia\u002Fcryptoskill --skill solve-challenge",{"tool":49,"command":50},"pnpm","pnpm dlx skills add jiayaoqijia\u002Fcryptoskill --skill solve-challenge","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdev-tools\u002Fabhay2008-solve-challenge\u002FSKILL.md",true,[54,60,64,68],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"difficulty-routing.md","REFERENCE","参考文档",7834,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdev-tools\u002Fabhay2008-solve-challenge\u002Fdifficulty-routing.md",{"path":61,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":16},"LICENSE","许可证",1072,{"path":65,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":66,"sourceHtmlUrl":67},"SOURCE.md",356,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdev-tools\u002Fabhay2008-solve-challenge\u002FSOURCE.md",{"path":69,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":70,"sourceHtmlUrl":71},"TRUST.auto.yaml",2158,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdev-tools\u002Fabhay2008-solve-challenge\u002FTRUST.auto.yaml",[73,82,90,98,106,114],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":81},"01M7DTKCERMV0RNX3HZJP4CZ26","troves","Deposit and withdraw from Troves DeFi yield vault strategies on Starknet. View available strategies, check positions, and manage vault deposits. Use this skill when the user mentions Troves, vault, yield vault, DeFi vault, strategy, yield farming, vault deposit, vault withdraw, earning yield through vaults, passive yield strategies, or wants to deposit into or withdraw from a yield strategy — even if they don't say \"Troves\" explicitly.","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-troves\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-troves\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":86,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":81},"01M7DTK6CJSMGC8KCQHGNYFZBD","trade","Swap tokens on Starknet via Fibrous DEX aggregator. Supports per-provider selection (avnu, ekubo, or auto to race all). Use this skill when the user wants to swap, exchange, trade, convert, buy, or sell one token for another on Starknet. Also use when the user asks about token prices, exchange rates, DEX routing, best swap route, or wants to check how much they would receive for a given amount — even if they don't explicitly say \"swap\".","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-trade\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-trade\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":81},"01M7DTJZ6A0X4PAW3Y8W4J9K64","staking","Stake, unstake, claim, and compound rewards for STRK, WBTC, tBTC, SolvBTC, and LBTC on Starknet. View validators, pools, and staking positions. Use this skill when the user mentions staking, delegating, validators, staking pools, rewards, compounding, unstaking, earning yield, passive income on crypto, or wants to earn on their STRK or BTC tokens — even if they don't say \"stake\" explicitly.","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-staking\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-staking\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":81},"01M7DTJSDZJKCDMW7GHRF4BRH5","send","Send STRK, ETH, or any ERC-20 token to a Starknet address. Supports simulation (dry-run) before execution. Use this skill when the user wants to send, transfer, pay, tip, or move tokens to another wallet address on Starknet. Also trigger when the user mentions sending funds to someone, making a payment, transferring assets, or moving crypto to a specific address — even if they just say \"pay 10 STRK to 0x...\".","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-send\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-send\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":81},"01M7DTJG1E480D51ZQ7WKDQ26K","portfolio","View a comprehensive DeFi portfolio dashboard and optimize portfolio allocation via automated rebalancing. Use this skill when the user wants an overview, summary, dashboard, total value, net worth, portfolio rebalancing, target allocation, or wants to see all their DeFi positions across Starknet at once. Also trigger when the user asks \"what do I have\", \"show me everything\", \"how much am I worth\", \"my positions\", \"my investments\", \"rebalance my portfolio\", \"I want 50% ETH\", \"optimize my holdings\", or any request for a holistic view of their Starknet holdings — even if they don't explicitly say \"portfolio\".","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-portfolio\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-portfolio\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":118,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":81},"01M7DTJ7M8TE9R2N36HFBZDGVD","multi-swap","Execute multiple token swaps in a single Starknet transaction via Fibrous (default). Supports per-provider selection (avnu, ekubo, or auto to race all). Supports 2-3 swap pairs bundled into one multicall. Use this skill when the user wants to swap multiple token pairs at once, do batch swaps, execute several trades simultaneously, perform parallel swaps, or do bulk trading in one transaction. Also trigger when the user mentions \"two swaps\", \"three swaps\", \"swap X and Y at the same time\", or wants to convert multiple tokens in a single call.","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-multi-swap\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-multi-swap\u002FSKILL.md",[],[]]