Loading...
Loading...
Found 10,123 Skills
Execute complete FPF cycle from hypothesis generation to decision
Fix GitHub issues end-to-end — from analysis through branch creation, implementation, testing, and PR submission. Use this skill whenever the user mentions fixing a GitHub issue, resolving a bug from an issue tracker, working on a GitHub issue number, or says things like "fix issue
Investigate LLM analytics clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into individual traces within clusters.
Use prefered practices when using git. Use when Codex needs to perform actions with git or Github.
Add items (research objects) to existing research outline.
Harness Engineering Phase 3: Establish cross-session state management to solve the problem of agents forgetting previous conversations. Create three files: tasks.json (task list), progress.md (progress record), and init.sh (environment initialization script). Use this skill immediately when the user says phrases like "establish task management", "make agent remember progress", "create tasks.json", "maintain state across sessions", "agent doesn't remember what was done last time", "create progress file", or "initialize state management". Prerequisites: harness-step1 and harness-step2 have been completed (the project has AGENTS.md and docs/ knowledge base).
Multi-perspective adversarial review. 4 Agents are spawned in parallel (full mode), each identifying issues from different perspectives, and the main thread makes a comprehensive ruling. Trigger methods: /story-review, /审查, "审查一下", "帮我审一下"
Execute the currently claimed task end-to-end and move it to review with verifiable output.
Use when a Beat change is implemented and ready to archive — not for verifying implementation
Move completed local GitHub issue work to a ready-for-merge pull request. Use when development is complete, the user says finish PR, publish this branch, open a ready PR, or an agent has objective evidence the branch is ready for review.
Plan a migration onto MotherDuck. Use when moving from Snowflake, Redshift, PostgreSQL, dbt-heavy stacks, or lakehouse tooling and the key decisions are target pattern, cutover slices, validation, rollback, and native-versus-DuckLake posture.
Agent-optimized CLI for Bluesky (ATProto) and X (Twitter). YAML in, YAML out, exit codes for automation. Use when the task involves posting, replying, reading feeds, searching, annotating URLs, or running a sync/check/dispatch agent loop across social platforms.