All Skills

Turns a one-line objective into a step-by-step construction plan any coding agent can execute cold, with each step containing a self-contained context brief.

Converts text to speech and speech to text using fal.ai audio models.

Query, filter, transform, and aggregate JSON data using jq, with practical patterns for shell pipelines and integration with CLI tools.

Explains machine learning model predictions using SHAP values, covering feature importance, visualization plots, model debugging, bias analysis, and production deployment.

Routes quality reviews to specialized critic agents based on file type or flags, covering peer review, code review, and manuscript polish.

Create publication-quality statistical graphics in Python with dataset-oriented plotting, semantic mapping, and built-in statistical estimation.

Evaluates machine learning classifiers on their ability to distinguish signal from background in particle physics simulations, measuring how well algorithms rank signal events above background ones using the AUC metric.

Computes bibliometric indices for AI/NLP conferences, including QQE, average/median citations, and citation inequality, from annual publication and citation data.

Process large ML datasets in parallel across CPU or GPU clusters, with streaming execution, multi-format I/O, and integration with Ray Train, PyTorch, and TensorFlow for batch inference and preprocessing pipelines.

Evaluates geometric consistency in text-to-video generation by measuring structural and motion coherence across camera trajectories, detecting deformation and occlusion artifacts in static scenes.

Evaluates the throughput and resource allocation efficiency of RIS-aided mobile edge computing systems by measuring the total computation task bits successfully completed under varying network conditions.

Computes CIDEr and related metrics to score how well generated image descriptions align with human consensus, using reference sentences and triplet annotations.

Evaluates image captions by converting them into scene graphs and computing an F-score over semantic propositions, measuring how well a generated caption captures the meaning of an image compared to human references.

Pretrains large language models at scale using PyTorch-native torchtitan with 4D parallelism, Float8, and distributed checkpointing.

Benchmarks long-context language models across 20 sub-tasks spanning 3k–200k tokens, covering retrieval, reasoning, summarization, and instruction understanding, with exact-match accuracy as the primary metric.

Evaluates spatial realism and temporal flow consistency of AI-generated videos using embedding spaces and Fourier transforms, producing bounded STREAM-S and STREAM-T scores.

Benchmarks mobile GUI agents on multi-step tasks across 20 Android apps, measuring task completion and essential-state navigation with Task Success Rate and Essential State Achieved Rate.

Measures inference latency of binarized, 8-bit, and 32-bit convolutional layers on edge devices to evaluate the efficiency and speedup of the Larq Compute Engine framework compared to standard implementations.

Computes Theil's U (uncertainty coefficient) between predictions and ground truth using the torchmetrics implementation, handling categorical data and NaN strategies.

Evaluates an AI judge system's pairwise ranking accuracy on generated commit messages against a heuristic ground truth from five automatic text metrics, using the MCMD dataset.

Benchmarks medical AI agents on synthetic EHR tasks, measuring success rates for data retrieval, temporal aggregation, and threshold-based conditional logic with exact-match scoring.

Benchmarks energy-function-based safe control algorithms on the BIS (Benchmark of Interactive Safety) dataset, scoring safety, efficiency, and hybrid performance in human-robot and robot co-working scenarios.

Delegates a task to OpenAI's Codex CLI for an independent review or second opinion, with guidance on prompt construction and handling output.

Creates a GitHub pull request with an auto-generated summary, running mandatory pre-commit and code-quality review gates, plus optional deep-review subagents, and posts findings into the PR body.

Submit one or more wandb-logged training/finetuning runs to the HPC scheduler. `WANDB_PROJECT` is fixed per repo (snake_case basename); `WANDB_RUN_GROUP` is picked per invocation. The training script must take the experiment/group name as a config key (e.g. Hydra `meta.experiment_name=<group>`); the skill passes it on the command line. The working tree is committed first so each run pins to a real SHA. Delegates SLURM/PBS templating to `cluster-instructions`. Use when the user asks to submit, queue, launch, or kick off a wandb training/finetuning job.

Office-document renderers for pursuit deliverables — Markdown to DOCX (Pandoc/OpenXML) and JSON envelopes to styled XLSX (openpyxl). USE WHEN the user asks to export a Studio markdown file to Word, convert compliance matrix JSON to Excel, render proposal outline as DOCX, or run a one-off format conversion on files under pursuits/. Consumer skills (proposal-generator, subcontractor-sow-builder, compliance-auditor) call these scripts internally; users can also run renderers directly from Agent Skills or chat. DO NOT USE FOR drafting content (use proposal-generator), visual decks/PDF/PPTX (use huashu-design), or domain analysis.

Create or enrich a pursuit capture brief from USASpending bulk data, optional SAM live intel, and optional LLM narrative. Use when opening a recompete workspace, scaffolding admin paperwork, or when the user asks for a one-page pursuit snapshot with citations.

Thin orchestrator — runs capture-brief, sam-scan, and competitive-snapshot in order for a new pursuit row. Use when user wants standard admin kickoff without running three buttons manually.

Labor-hour and time-and-materials cost buildup with fully burdened hourly rates (BLS OEWS + GSA CALC+ + per diem MCPs). USE WHEN the user asks to "build a T&M IGCE", "labor hour estimate", "fully burdened hourly rate", "LH IGCE", "time and materials pricing", or "burden multiplier stack". Exports JSON + XLSX to Studio. DO NOT USE FOR FFP wrap rates (`igce-builder-ffp`), cost-reimbursement fee caps (`igce-builder-cr`), or OT bids (`ot-prototype-strategist`).

Build a USASpending relationship snapshot for the incumbent and buying agency on a pursuit row. Use when user needs award flows and rel counts before battlecard or teaming work — deterministic from DuckDB bulk.

Drafts a federally-defensible SOW or PWS the prime issues to a subcontractor / teaming partner — same FAR 37.102(d) / 37.602 / 16.601(c)(2) / 16.306(d) discipline a contracting officer applies, opposite seat. USE WHEN the user asks to "write a SOW for our sub", "draft a PWS for [Partner]", "build the teaming-partner statement of work", "convert this SOO into a sub SOW", "we need a SOW the sub will sign", or any variant of authoring a downstream work statement. Walks the upstream 3-phase tree (acquisition intake → 6 scope blocks → 14-section assembly), pulls scope from the active Theseus KG (requirements, deliverables, work_scope_items, performance_standards), enforces FAR 37.102(d) "no FTEs in body", emits a chat-only staffing handoff for the prime's cost build, writes Markdown for `renderers` → .docx. DO NOT USE FOR prime proposal prose (`proposal-generator`), reverse-engineering an RFP (`rfp-reverse-engineer`), pricing the sub (`price-to-win`), or clause audit (`compliance-auditor`).

Algebra Based Testing Skill

Botany Based Analysis Skill

Advanced Logic Testing Skill

Applied Algebra Design Skill

Botany Analysis Expert Skill