Linear
asgeirtj/system_prompts_leaks
Read and manage software issues, tickets, projects, and planning data in Linear.
Solve KCTF model backdoors and small linear/ReLU crackmes from raw weights.
No licenceAuto-check passed
Install Kctf ML Backdoor Linear
$ npx skills add manyuegong33/r0crawl_skills --skill kctf-ml-backdoor-linear -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install manyuegong33/r0crawl_skills kctf-ml-backdoor-linear --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/manyuegong33/r0crawl_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/kctf-ml-backdoor-linear .claude/skills/kctf-ml-backdoor-linear && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "kctf-ml-backdoor-linear" agent skill from https://github.com/manyuegong33/r0crawl_skills/tree/main/skills/kctf-ml-backdoor-linear into .claude/skills/kctf-ml-backdoor-linear/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kctf-ml-backdoor-linear", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/manyuegong33/r0crawl_skills/tree/main/skills/kctf-ml-backdoor-linearType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add manyuegong33/r0crawl_skills --skill kctf-ml-backdoor-linear -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install manyuegong33/r0crawl_skills kctf-ml-backdoor-linear --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/manyuegong33/r0crawl_skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/kctf-ml-backdoor-linear .agents/skills/kctf-ml-backdoor-linear && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "kctf-ml-backdoor-linear" agent skill from https://github.com/manyuegong33/r0crawl_skills/tree/main/skills/kctf-ml-backdoor-linear into .agents/skills/kctf-ml-backdoor-linear/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kctf-ml-backdoor-linear", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add manyuegong33/r0crawl_skills --skill kctf-ml-backdoor-linear -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install manyuegong33/r0crawl_skills kctf-ml-backdoor-linear --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/manyuegong33/r0crawl_skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/kctf-ml-backdoor-linear .cursor/skills/kctf-ml-backdoor-linear && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "kctf-ml-backdoor-linear" agent skill from https://github.com/manyuegong33/r0crawl_skills/tree/main/skills/kctf-ml-backdoor-linear into .cursor/skills/kctf-ml-backdoor-linear/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kctf-ml-backdoor-linear", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/manyuegong33/r0crawl_skills.git --path skills/kctf-ml-backdoor-linear--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add manyuegong33/r0crawl_skills --skill kctf-ml-backdoor-linear -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install manyuegong33/r0crawl_skills kctf-ml-backdoor-linear --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/manyuegong33/r0crawl_skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/kctf-ml-backdoor-linear .gemini/skills/kctf-ml-backdoor-linear && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "kctf-ml-backdoor-linear" agent skill from https://github.com/manyuegong33/r0crawl_skills/tree/main/skills/kctf-ml-backdoor-linear into .gemini/skills/kctf-ml-backdoor-linear/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kctf-ml-backdoor-linear", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install manyuegong33/r0crawl_skills kctf-ml-backdoor-linearInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add manyuegong33/r0crawl_skills --skill kctf-ml-backdoor-linear -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/manyuegong33/r0crawl_skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/kctf-ml-backdoor-linear .github/skills/kctf-ml-backdoor-linear && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "kctf-ml-backdoor-linear" agent skill from https://github.com/manyuegong33/r0crawl_skills/tree/main/skills/kctf-ml-backdoor-linear into .github/skills/kctf-ml-backdoor-linear/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kctf-ml-backdoor-linear", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add manyuegong33/r0crawl_skills --skill kctf-ml-backdoor-linear -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install manyuegong33/r0crawl_skills kctf-ml-backdoor-linear --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/manyuegong33/r0crawl_skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/kctf-ml-backdoor-linear .opencode/skills/kctf-ml-backdoor-linear && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "kctf-ml-backdoor-linear" agent skill from https://github.com/manyuegong33/r0crawl_skills/tree/main/skills/kctf-ml-backdoor-linear into .opencode/skills/kctf-ml-backdoor-linear/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kctf-ml-backdoor-linear", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
kctf-ml-backdoor-linear- GitHub stars
- 312
- Token cost
- ~443 tokens
- SKILL.md length
- 194 words
- Files
- 4 (incl. scripts, references)
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- None found
At a glance
Solve KCTF model backdoors and small linear/ReLU crackmes from raw weights.
- Works in 6 steps: Parse the raw model file first; do not… → Identify the feature path → Split the problem into → …
- The artifact is a safetensors/torch model
- SKILL.md covers Workflow, Solver pattern, When to use and Notes
- Runs Python scripts from its folder; calls python
What it does
Kctf ML Backdoor Linear is an agent skill from manyuegong33/r0crawl_skills. Solve KCTF model backdoors and small linear/ReLU crackmes from raw weights. Use when the artifact is a safetensors/torch model, token-id-as-feature network, tiny classifier, or a prompt gated by linear inequalities and argmax backdoors.
Its SKILL.md is about 440 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/pattern.md` and `scripts/solve_backdoor.py`).
The repository describes itself as: r0crawlskills is a massive reverse-engineering skill arsenal for web, Android, iOS, Frida, native binaries, protocols, malware, firmware, and anti-analysis—built for beginners…
When your agent uses it
- The artifact is a safetensors/torch model
- Token-id-as-feature network
- Tiny classifier
- A prompt gated by linear inequalities and argmax backdoors
Example prompts
- “/kctf-ml-backdoor-linear”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Parse the raw model file first; do not trust the front-end wrapper.
- Identify the feature path
- Split the problem into
- Solve the linear system or linear program on the visible constraints.
- Round only after checking the residual is effectively zero.
- Decode the candidate with the challenge charset and verify it against the model.
What it can do on your machine
Read from SKILL.md and the folder at commit b9eb545. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Kctf ML Backdoor Linear loads about 443 tokens when it runs, and up to ~642 if it reads all its reference files. Until then it costs about 65 tokens; SKILL.md has 194 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 194 words (~443 tokens).
“Use the supplied script for small KCTF model crackmes:”
- name
- kctf-ml-backdoor-linear
Files
SKILL.md and 3 other files (scripts, references) in skills/kctf-ml-backdoor-linear of manyuegong33/r0crawl_skills.
- SKILL.md
- agents/openai.yaml
- references/pattern.md
- scripts/solve_backdoor.py
Open the folder on GitHubat commit b9eb545
Compare with similar skills
Kctf ML Backdoor Linear next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Kctf ML Backdoor Linear this skillmanyuegong33/r0crawl_skills | 312 | — | ~443 | Automated safety check: Pass | None | |
| Linearasgeirtj/system_prompts_leaks | 69k | — | ~653 | Automated safety check: Pass | CC0-1.0 | |
| Linearyc-software/qm | 15k | — | ~886 | Automated safety check: Pass | MIT | |
| Linear Issue Workflowlobehub/lobehub | 83k | — | ~1.5k | Automated safety check: Pass | Custom licence | |
| Accint Solvesickn33/agentic-awesome-skills | 47k | 1 repos | ~520 | Automated safety check: Pass | Apache-2.0 | |
| Linearkaranhudia/borg-ui | 1.7k | — | ~1.7k | Automated safety check: Pass | AGPL-3.0 |
Similar skills
Linear
yc-software/qm
Search, read, create, and update the user's Linear issues, projects, and comments through per-user OAuth.
Linear Issue Workflow
lobehub/lobehub
Handles Linear issues for the team: reading details and images, checking sub-issues, marking progress, labeling AI-created issues and writing completion comments.
Accint Solve
sickn33/agentic-awesome-skills
Route a goal through acc's scored-memory loop via accact(runtime="solve"); deliberate any returned brainframe and submit via continue.
Linear
karanhudia/borg-ui
Use Symphony's lineargraphql client tool for raw Linear GraphQL operations such as comment editing and upload flows.
Linear Automation
davila7/claude-code-templates
Automate Linear tasks via Rube MCP (Composio): issues, projects, cycles, teams, labels.
More from manyuegong33/r0crawl_skills
All 9 skills in this repoCtf Key Recovery
manyuegong33/r0crawl_skills
Reconstruct CTF key, serial, and flag verifiers using known plaintext, repeating XOR, encoded constants, bytecode replacement, hash constraints, SMT, and bounded brute force.
Cpython Runtime Introspection
manyuegong33/r0crawl_skills
Inspect embedded or packaged CPython processes at runtime by tracing child processes, acquiring the GIL, injecting Python, replacing builtins.input, walking frame.fback, exporting frame code…
Python Frozen App Reversing
manyuegong33/r0crawl_skills
Recover logic from PyInstaller, cxFreeze, py2exe, Nuitka, and other frozen Python applications, including modified bootloaders, decoy entry scripts, patched frozen standard-library modules, embedded…
R0crawl Skills
manyuegong33/r0crawl_skills
面向新手的全谱系逆向工程路由器，覆盖 Web/JavaScript、Android/iOS、Frida、脱壳、反分析、原生二进制、协议、固件、恶意软件、游戏、云 API、CTF、可复现一致性测试。用于逆向、起步、脱壳、反编译、hook、Frida、绕过检测、APK/SO/DEX/JS/PCAP/WASM/PE/ELF/Mach-O 分析、签名还原，或从样本到验证结果的完整调查。
Kctf Algebraic Crackme Chain
manyuegong33/r0crawl_skills
Solve KCTF Windows crackmes with layered codecs, 32/64-bit shell thunks, .data-resident code, and final algebraic or polynomial checks.
Kctf Windows Smc Chain
manyuegong33/r0crawl_skills
KCTF 2026 第八题“亥子合辰·塔影迷楼”两级 SMC、反调试、Feistel 与 GF(2^127-39) 多项式求根的可复用解题流程。
Questions about Kctf ML Backdoor Linear
What does Kctf ML Backdoor Linear do?
Solve KCTF model backdoors and small linear/ReLU crackmes from raw weights. Kctf ML Backdoor Linear is an agent skill from manyuegong33/r0crawl_skills. Solve KCTF model backdoors and small linear/ReLU crackmes from raw weights.
When should I use Kctf ML Backdoor Linear?
Kctf ML Backdoor Linear fits situations like: the artifact is a safetensors/torch model; token-id-as-feature network; tiny classifier; A prompt gated by linear inequalities and argmax backdoors.
How do I install Kctf ML Backdoor Linear in Claude Code?
Run `npx skills add manyuegong33/r0crawl_skills --skill kctf-ml-backdoor-linear -a claude-code`. Or copy the skill folder (skills/kctf-ml-backdoor-linear in manyuegong33/r0crawl_skills) into .claude/skills/kctf-ml-backdoor-linear in your project. Claude Code loads it when a task matches its description.
How do I install Kctf ML Backdoor Linear in Codex?
Run `npx skills add manyuegong33/r0crawl_skills --skill kctf-ml-backdoor-linear -a codex`. Or copy the skill folder (skills/kctf-ml-backdoor-linear in manyuegong33/r0crawl_skills) into .agents/skills/kctf-ml-backdoor-linear in your project. Codex loads it when a task matches its description.
Can I use Kctf ML Backdoor Linear in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add manyuegong33/r0crawl_skills --skill kctf-ml-backdoor-linear -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kctf-ml-backdoor-linear, .gemini/skills/kctf-ml-backdoor-linear, .github/skills/kctf-ml-backdoor-linear and .opencode/skills/kctf-ml-backdoor-linear in your project.
What does Kctf ML Backdoor Linear need to run?
Going by SKILL.md and its folder, Kctf ML Backdoor Linear needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Kctf ML Backdoor Linear access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Kctf ML Backdoor Linear safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Kctf ML Backdoor Linear use?
No licence was found for Kctf ML Backdoor Linear or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Kctf ML Backdoor Linear use?
About 443 tokens (SKILL.md is roughly 1.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 199 tokens, read only when the agent opens those files.
What are the alternatives to Kctf ML Backdoor Linear?
Skills that share tags, products or a category with Kctf ML Backdoor Linear: Linear (asgeirtj/system_prompts_leaks, 69k stars), Linear (yc-software/qm, 15k stars), Linear Issue Workflow (lobehub/lobehub, 83k stars) and Accint Solve (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Kctf ML Backdoor Linear?
manyuegong33 (a GitHub user) maintains it in manyuegong33/r0crawl_skills, which has 312 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 20, 2026.
Source: manyuegong33/r0crawl_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.