Practical async patterns using TaskEither - clean pipelines instead of try/catch hell, with real API examples
cat ~/最新
浏览最新添加到市场的技能
Product types, sum types, semigroups, monoids, Eq, Ord, and building custom type class instances for domain modeling...
Implement a new variant in Fairy-Stockfish, either as built-in or variants.ini config
Control the Grabbit CLI to record browser interactions (HAR) and generate API workflows. Use this skill when the...
Generate Chinese official document (公文) Word files from controlled Markdown or JSON. Use when producing or updating...
Run the full dev loop for the current feature with guardrails. Feature-first and git/local safe.
Perform CI-parity self-review for the current feature. Feature-first, git/local safe.
Mode-aware PR open for current feature: commit (if needed) + push + open PR via gh.
Generate a PR-ready draft from TASKS, diff, and review status. Feature-first and git-aware.
Auto-merge PR via gh and fully clean up feature worktree/branch/metadata. Feature-first, safe, idempotent.
Plan the current feature (feature-first). Resolve registry/spec, detect Mode, and write tasks.
Save durable session handoff for a feature to WORKING.md plus history snapshot. Feature-first, safe.
Show resolved feature mapping and paths. No changes.
Select an existing feature as current without modifying registry data.
Create or update a feature registry entry and seed feature files. Feature-first, safe, idempotent.
Implement the current plan from TASKS (feature-first). Git-aware; no git ops in local mode.
Create or refresh AGENTS.md + .dev-docs baseline (feature registry, templates, commands, checklists) so Codex can...
Feature-first init: create or reuse worktree/branch and seed per-feature context. Git-aware and idempotent.
调用ima的skill方式
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an...
Use for Python project setup and structure. Enforce uv with pyproject.toml (use workspaces when applicable) and...
Logger setup and usage guidance. Use when logging is needed and no logger is present.
Review code quality standards after code is written, especially Python typing, logging, and import style.
Reviews code changes for bugs, style issues, and best practices. Use when reviewing PRs or checking code quality.