GitHub
moonshot-classify-task
Classifies a user request into task types (feature, modification, bugfix, refactor) and extracts intent keywords. Use at the start of PM analysis.
☆ 0View skill
Testing & security AI Skills
Discover Testing & security skills, compare source repositories and read the instructions for each workflow.
Categories: Testing & security
Testing & security Clear filters
Browse skills
GitHub
claude-codex-guardrail-loop
Use after planning or implementing non-trivial tasks - runs Codex MCP background verification/review for quality gates (plan validation + implementation review)
☆ 0View skill
GitHub
make-lib-skill
Generate a library-specific documentation/source reference skill
☆ 0View skill
GitHub
session-logger
Logs development sessions in real-time to track decisions and issues.
☆ 0View skill
GitHub
moonshot-decide-sequence
Determines phase and execution chain based on analysisContext (task type, complexity, signals). Use after uncertainty detection.
☆ 0View skill
GitHub
reference-mmcif
Reference documentation for PDBx/mmCIF dictionary queries and category lookup
☆ 0View skill
GitHub
game-mobile-ui
用于游戏项目的移动端界面样式与适配。涉及统一移动布局触发条件、移动端 UI 样式调整、触摸交互优化、以及小游戏虚拟摇杆接入与复用时使用；也用于快速定位移动端相关文件与入口。
☆ 0View skill
GitHub
generate-texture
Generate seamless block textures. You must use this skill when creating game assets / textures / art.
☆ 0View skill
GitHub
optimize-readability-system
Interactive guide for tuning the unmangleJS Readability Scoring System(readability.ts) and Semantic Scoring System (semantic.ts). Use when Golden Set validation fails, when scoring heuristics need adjustment, o...
☆ 0View skill
GitHub
pass-workflow
Universal guide for all unmangleJS pass development tasks. Covers creating, modifying, debugging, refactoring, reviewing, and documenting passes. Integrates with existing project documentation - see CLAUDE.md f...
☆ 0View skill
GitHub
developer-assessment
GitLab 開發者評估與分析技能。分析單一開發者、多位開發者或所有開發者的程式碼品質、commit 記錄、專案參與度、技術能力。支援時間區間篩選（過去一個月、三個月等）、專案範圍篩選（特定專案或全專案）。使用 gl-cli.py 工...
☆ 0View skill
GitHub
x07-format
Canonically format X07 x07AST JSON files using `x07 fmt` (check/write) with a machine-readable JSON report.
☆ 0View skill
GitHub
x07-io-streams
Canonical streaming I/O patterns in X07 using std.io / std.io.bufread and world adapters.
☆ 0View skill
GitHub
x07-os-run
Expert backend for run-os / run-os-sandboxed execution via x07-os-runner. Prefer `x07 run --profile os` / `x07 run --profile sandbox`.
☆ 0View skill
GitHub
x07-package
Manage X07 project dependencies and lockfiles for reproducible builds (lock, publish). Designed for autonomous agents.
☆ 0View skill
GitHub
x07-language-guide
Canonical X07 language + stdlib reference (mirrors `x07 guide` output) for end-user skill packs.
☆ 0View skill
GitHub
x07-build-run
Expert backend for deterministic solve-world execution via x07-host-runner. Prefer `x07 run` as the canonical agent entry point.
☆ 0View skill
GitHub
x07-lint-repair
Lint X07 x07AST JSON and converge via deterministic quickfixes (`x07 fix`) or explicit JSON Patch (`x07 ast apply-patch`).
☆ 0View skill
GitHub
x07-agent-playbook
Agent-first workflow and design rails for building X07 programs with the released toolchain (no repo-only dependencies). Canonical execution is via `x07 run`.
☆ 0View skill
GitHub
x07-concurrency
Canonical deterministic concurrency patterns in X07 (defasync + task.* + chan.bytes.*), including the determinism constraints.
☆ 0View skill
GitHub
x07-ffi-c
Emit C output and a C header for embedding X07 in C/C++ via `x07 build --emit-c-header`.
☆ 0View skill
GitHub
x07-test
Run project tests using the X07 test harness (x07 test), producing a machine-readable JSON report.
☆ 0View skill
GitHub
x07-run
Canonical execution front door for X07 programs (solve-* and run-os*), producing pass-through runner reports.
☆ 0View skill
GitHub
project-structure
Vista rápida del repo y orientación sobre qué archivo tocar según la tarea.
☆ 0View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.