Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Recover CCB agents, panes, mounts, provider contexts, API/provider failures, config reload aftermath, clear operations, and guarded single-agent restarts. Use when the user asks to fix, recover, restart if safe, clear context, reload, remount, or keep work going after provider/API failure.
Draft a new release. Bumps version, generates CHANGELOG.md from git history, and creates a PR.
Use this skill to cut an APM release from the current worktree: assess whether the cycle since the last tag warrants a patch or minor bump (semver discipline against the merged-since-last-tag diff), sanitize the [Unreleased] CHANGELOG block into a dated version block with one concise "so what" entry per merged PR (drop internal-only churn, consolidate duplicates), bump pyproject.toml + uv.lock, run the CI-mirror lint chain, and open the release PR. Activate on "ship a release", "cut v0.x", "release prep", "bump and PR", "open release PR", "what kind of release do we need", or any phrasing that ends in opening a release PR -- even when the user does not say "skill". Stops BEFORE tagging; tagging stays a human gate that triggers the release workflow. Refuses to bump to a major (>= 1.0.0) version without explicit operator confirmation.
Activate when reviewing or modifying dependency resolution, lockfile schema, package downloaders, signature/integrity checks, file integration cleanup, or anything that could expose APM to dependency confusion, typosquatting, malicious packages, or token leakage.
Deterministic end-to-end driver for day-0 quantized-checkpoint releases — chains PTQ → evaluation → comparison with enforced gates between stages (the evaluation stage deploys the checkpoint itself), and returns a publish decision (ACCEPT / REGRESSION / ANOMALOUS / INFEASIBLE). Use when the user asks to "release a model at day-0", "quantize and validate model X is within N% of baseline and tell me if it's publishable", or "run the full day-0 workflow". Do NOT use for single-stage requests — quantizing only (use ptq), serving only (use deployment), evaluating only (use evaluation), or comparing two existing runs (use compare-results).
Serve a quantized or unquantized LLM checkpoint as an OpenAI-compatible API endpoint using vLLM, SGLang, or TRT-LLM. Use when user says "deploy model", "serve model", "start vLLM server", "launch SGLang", "TRT-LLM deploy", "AutoDeploy", "benchmark throughput", "serve checkpoint", or needs an inference endpoint from a HuggingFace or ModelOpt-quantized checkpoint. Do NOT use for quantizing models (use ptq) or evaluating accuracy (use evaluation).
Add a new model to the EAGLE3 offline pipeline. Generates an hf_offline_eagle3.yaml launcher config for a new model checkpoint, choosing the right hidden state dump backend (TRT-LLM / HF / vLLM) and GPU configuration. Use when user wants to run EAGLE3 on a model that does not yet have a YAML in tools/launcher/examples/ or asks how to configure the pipeline for a new checkpoint.
Monitor submitted jobs (PTQ, evaluation, deployment) on SLURM clusters. Use when the user asks "check job status", "is my job done", "monitor my evaluation", "what's the status of the PTQ", "check on job <slurm_job_id>", or after any skill submits a long-running job. Also triggers on "nel status", "squeue", or any request to check progress of a previously submitted job.
The L2 Channel Separation and Prompt Firewall defense mechanisms to prevent injection attacks and Helpful Assistant regression.
Configure Serverpod — YAML config, environment variables, passwords, run modes, generator.yaml, TLS. Use when setting up environments, API/database/Redis settings, managing secrets or overriding configurations for tests.