Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

skill-pipeline

Pipeline orchestrator that classifies incoming coding tasks and routes them through the correct combination of skills at the right depth. Implements two feedback loops: the inner loop (detect, verify, recover) runs within a session via plan-interview, intent-framed-agent, context-surfing, verify-gate, self-healing (active recovery on failure), simplify-and-harden, and self-improvement. The outer loop (inspect, encode, regress-test) runs across sessions via learning-aggregator, harness-updater, and eval-creator. pre-flight-check bridges the two by surfacing accumulated knowledge — past heals and learnings — at session start. Handles standard, team-based, CI, and outer-loop pipeline variants. Does not replace individual skills; dispatches to them.

260 repo starsObserved in 1 repos
Agent Building

using-science-superpowers

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

260 repo starsObserved in 1 repos
Agent Building

analyze-id-eval-ranking

Given a list of models (HF name stubs) that have valid agentic ID eval scores in Supabase, build a ranking table: raw per-benchmark accuracy on the 3 ID benchmarks (SWE-Bench-100, OT-TBLite=dev_set_v2, Terminal-Bench-2.0=tb2), HF links to each eval's trace dataset, and a NORMALIZED column = average per-benchmark z-score, ranked. Normalization matches the OpenThoughts-Agent paper (otagent-paper/02_arXiv/otagent.tex §Pipeline): per-benchmark z over the candidate set, averaged. Read-only. Use when asked to rank models / ablation arms by their ID evals the way the paper does.

259 repo starsObserved in 1 repos
Agent Building

analyze-rl-behavior

Run the full RL behavioral-analysis pipeline (scripts/analysis/analyze_rl_behavior.py) on a trained RL model to understand WHAT changed vs its pre-RL baseline, WHY, whether it PERSISTS, and its EVAL impact. Use when asked to "analyze RL behavior", "compare pre/post RL", "what did RL change", or to produce the Q1–Q4 behavioral report + GPT-5 judge for an `laion/...` (or any) RL checkpoint. Runs LOCALLY on the Mac (no GPU).

259 repo starsObserved in 1 repos
Agent Building

crud-otagent-supabase

Read, aggregate, and (carefully) write OT-Agent eval/model data in the Supabase registry. Use when asked to look up a model's ID/OOD benchmark scores, build/refresh an ablation or paper table from eval results, find unevaluated models, register a model/eval, or reconcile duplicate rows. Covers the sandbox_jobs/models/benchmarks schema, the metrics-field shape gotchas, the ID/OOD benchmark master list + per-benchmark task counts (for binomial SE), and the multiple-entries-per-model rule.

259 repo starsObserved in 1 repos
Agent Building

eval-agentic-cleanup

Audit + recover a finished agentic eval. ALWAYS start with the read-only, idempotent completeness/health audit (§0): job finished? score present + non-zero + not obviously broken? HF traces present + linked? trial count ≈ n_rep × benchmark_size? — it writes nothing and recommends an action per check. Then run only the flagged remediations: manual HF-trace upload + Supabase DB-registration via manual_db_eval_push.py, the vLLM-numeric-ID → real-HF-model-name fix (with cross-user FK safety), verify, free disk. Use to verify an eval is truly complete, when a sweep finds an eval that didn't upload/register or has a broken/zero score or short trial count, or to re-register/correct an eval's model/traces. Distinct from the model- publishing cleanups (rl-agentic-job-cleanup / sft-job-cleanup) and datagen-job-cleanup — this is the EVAL path.

259 repo starsObserved in 1 repos
Agent Building

eval-agentic-launch

Launch agentic Harbor evals through the OT-Agent unified eval listener (eval/unified_eval_listener.py) on any cluster: select models (query_unevaled_models.py / priority lists), wire the pinggy served-model tunnel, submit with the right preset + flags in tmux, then VERIFY the launch actually works via the 15-min infra sanity check (pinggy auth, Daytona→cluster api_base, vLLM POSTs, trial progression — catches "RUNNING but silently dead" jobs). Cluster-AGNOSTIC: per-cluster particulars (sbatch script, gpu-mem ceiling, concurrency, cert/tunnel, conda env, paths, Daytona key, pre-download) live in `.claude/ops/<cluster>/`. Use when asked to launch/relaunch agentic evals, or eval a model on a benchmark (terminal_bench_2 / dev_set_v2 / swebench / bfcl / aider).

259 repo starsObserved in 1 repos
Agent Building

eval-agentic-launch-iris

Launch, monitor, and manually clean up an eval job on Marin's Iris TPU or CoreWeave H100x8 GPU cluster via the OpenThoughts-Agent entrypoint. Use when asked to start, watch, or kill a model evaluation (evalchemy / agent-harness benchmarks) on Iris.

259 repo starsObserved in 1 repos
Agent Building

integrate-with-yalc

Points at the user's existing Claude Code repo, analyses what's already there, and produces a plan for how to make it work alongside YALC without conflicts. Covers workspace layout, skill trigger collisions, context migration, and orchestration examples. Read-only by default — a separate apply step moves files only after the user confirms. Use when someone says 'integrate my repo with YALC', 'I have my own Claude Code setup, how do I add YALC', 'merge my repo with YALC', 'how do I bolt YALC onto my existing skills', or 'I want to use my own skills alongside YALC'.

259 repo starsObserved in 1 repos
Agent Building

list-adapters

Show every capability the engine knows about and which provider backs it (built-in TypeScript, bundled YAML, or user-installed YAML), with availability flags reflecting whether each provider's API key is set. Use when the user says 'list adapters', 'show me which providers are configured', 'which providers are available', 'what capabilities can YALC use right now', or 'show capability coverage'. Read-only — never writes anything.

259 repo starsObserved in 1 repos
Agent Building