Loading...
Loading...
Found 104 Skills
Select the most appropriate pipeline for a user goal, lock it in `PIPELINE.lock.md`, and route checkpoint questions into `DECISIONS.md`. **Trigger**: pipeline router, choose pipeline, workflow selection, PIPELINE.lock.md, 选择流程. **Use when**: 用户目标/交付物不清晰，需要在 snapshot/survey/tutorial/systematic-review/peer-review 中选一个并设置最小 HITL 问题集。 **Skip if**: pipeline 已锁定（`PIPELINE.lock.md` 存在）且所需问题已回答/签字完成。 **Network**: none. **Guardrail**: 尽量一次性提问；信息不足就写 `DECISIONS.md` 并停下等待。
Create and work with Meta SAM 3 (facebookresearch/sam3) for open-vocabulary image and video segmentation with text, point, box, and mask prompts. Use when setting up SAM3 environments, requesting Hugging Face checkpoint access, generating inference scripts, integrating SAM3 into Python apps, fine-tuning with sam3/train configs, running SA-Co or custom evaluations, or debugging CUDA/checkpoint/prompt pipeline issues.
Save progress and generate a continuation prompt. Updates PRD status markers, captures git state, and writes checkpoint.md for the next session.
Concurrency safety patterns for distributed pueue + mise + systemd-run job pipelines. TRIGGERS - queue pueue jobs, deploy to remote host, concurrent job collisions, checkpoint races, resource guards, cgroup memory limits, systemd-run, autoscale, batch processing safety, job parameter isolation.
Test-Driven Development workflow with session integration. Use when implementing features/bugfixes to enforce RED-GREEN-REFACTOR discipline. Integrates with session-management for enhanced TDD session tracking, checkpoints, and metrics.
Standard implementation workflow for all coding tasks. Executes a systematic 5-phase cycle: Investigate → Plan → Implement → Verify → Complete. Integrates Serena think checkpoints, introspection markers, and quality gates. Supports --frontend-verify flag for browser/app/CLI visual verification. Use when: - User asks to implement a feature, fix a bug, or refactor code - User provides a task that requires code changes - User says "do this", "build this", "fix this", "add this" - Any implementation work involving code editing Keywords: task, implement, build, fix, add, create, refactor, update, change
Configure Lakebase for agent memory storage. Use when: (1) Adding memory capabilities to the agent, (2) 'Failed to connect to Lakebase' errors, (3) Permission errors on checkpoint/store tables, (4) User says 'lakebase', 'memory setup', or 'add memory'.
Use when "training LLM", "finetuning", "RLHF", "distributed training", "DeepSpeed", "Accelerate", "PyTorch Lightning", "Ray Train", "TRL", "Unsloth", "LoRA training", "flash attention", "gradient checkpointing"
Design state schemas, implement reducers, configure persistence, and debug state issues for LangGraph applications. Use when users want to (1) design or define state schemas for LangGraph graphs, (2) implement reducer functions for state accumulation, (3) configure persistence with checkpointers (InMemorySaver/MemorySaver, SqliteSaver, PostgresSaver), (4) debug state update issues or unexpected state behavior, (5) migrate state schemas between versions, (6) validate state schema structure, (7) choose between TypedDict and MessagesState patterns, (8) implement custom reducers for lists, dicts, or sets, (9) use the Overwrite type to bypass reducers, (10) set up thread-based persistence for multi-turn conversations, or (11) inspect checkpoints for debugging.
Locate the latest checkpoint for a run id and provide a follow-up play/eval command. Use when asked to find a checkpoint.
Use when managing Crunch coordinators, competitions (crunches), rewards, checkpoints, staking, or cruncher accounts via the crunch-cli.
FORGE Autopilot — Intelligent autonomous mode. FORGE analyzes the project state, automatically decides the next action, and orchestrates all agents until completion. Configurable checkpoints for human review. Usage: /forge-auto or /forge-auto "specific objective"