Source

wshobson/agents

183 skills · 2.1M combined installs

Skills from this source

#

Skill

Source

8W Activity

Installs

protect-mcp-setup Configure Cedar policy enforcement and Ed25519 signed receipts for Claude Code tool calls. Use when setting up projec…

wshobson/agents

signed-audit-trails-recipe Step-by-step cookbook for setting up cryptographically signed audit trails on Claude Code tool calls. Use when explai…

wshobson/agents

review-agent-setup Configure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an…

wshobson/agents

scan Scans the codebase to generate project-doc.md and AGENTS.md. Use when bootstrapping a new agent-driven repo, refreshi…

wshobson/agents

recsys-pipeline-architect Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selec…

wshobson/agents

social-publishing Schedule and publish social media posts across 13 platforms (X, LinkedIn, Instagram, Facebook Pages, TikTok, Discord,…

wshobson/agents

before-you-build Pre-build product and feature risk review for founders, product managers, and AI-assisted builders. Use this skill wh…

wshobson/agents

file-conversion Convert files between formats — PDF to Word, HEIC to JPG, MP4 to MP3, CSV to JSON, EPUB to MOBI, and 999 total routes…

wshobson/agents

ai-debt-detector Use after generating code, after accepting AI suggestions, or when reviewing AI-written modules. Also use when code w…

wshobson/agents

session-guard Use when working on complex multi-step tasks, when a session is getting long (40+ tool calls), when the agent starts …

wshobson/agents

visual-edit-precision Use when making UI/frontend changes guided by visual context, when the user selects elements visually, draws annotati…

wshobson/agents

hermes-tweet Install and operate Hermes Tweet, a Hermes Agent plugin for X/Twitter research, timeline reading, tweet analysis, and…

wshobson/agents

dataset-curation Prepare, format, and validate datasets for supervised fine-tuning and preference training. Use when converting raw da…

wshobson/agents

eval-harness-first Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibrat…

wshobson/agents

finetuning-method-selection Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretrainin…

wshobson/agents

lora-qlora-recipes Configure LoRA and QLoRA supervised fine-tuning with current best-practice hyperparameters. Use when writing or revie…

wshobson/agents

checkpoint-promotion Gate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion. Use after …

wshobson/agents

preference-optimization Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO. Use when preference pairs or thumbs-up/…

wshobson/agents

quantized-export Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix,…

wshobson/agents

grpo-rlvr-training Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use…

wshobson/agents

vision-sft Fine-tune vision-language models (VLMs) with supervised learning on image+text data. Use when adapting a VLM to a vis…

wshobson/agents

trace-to-training-data Convert evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failu…

wshobson/agents

spark-training-gotchas Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DG…

wshobson/agents

pptx-deck-context Use when preparing the narrative, sources, and design context for a new editable PPTX deck.

wshobson/agents

pptx-quality-gates Use when validating or repairing an editable PPTX deck for geometry, accessibility, native editability, source lineag…

wshobson/agents

pptx-reference-deck-analysis Use when analyzing a reference PPTX for read-only structure, theme, typography, layout rhythm, diagnostics, derived t…

wshobson/agents

pptx-slide-specification Use when authoring or repairing a coordinate-explicit JSON specification for an editable PPTX deck.

wshobson/agents

pptx-visual-assets Use when selecting and placing approved supporting icons, images, SVGs, diagrams, or infographics in an editable PPTX…

wshobson/agents

spark-environment-setup Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing …

wshobson/agents

spark-memory-thermal-ops Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom…

wshobson/agents

avoid-ai-writing Audit and rewrite prose so it stops reading as machine-generated. Use this skill when asked to remove AI-isms, clean …

wshobson/agents

superself Use when a project keeps its state in Superself (a `<!-- superself:begin` block in AGENTS.md or CLAUDE.md, or `self s…

wshobson/agents

grounded-vault Use when maintaining a durable Markdown knowledge store that agents compile from sources, when every number or quote …

wshobson/agents