grahama1970/agent-skills

Shared skills for AI agents (Claude Code, Codex, Gemini)

6Stars on the repository
210Mods indexed here, across every type
todayLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

create-intent-map

121

grahama1970/agent-skills

Skill Claude Code

Train LoRA intent mappers for structured query generation using GRPO with execution feedback. Uses DeepSeek-R1-Distill-Qwen-7B as base model. Supports SFT warmup, GRPO training with ArangoDB rewards, and iterative improvement with automatic retry on eval failure.

not rated 6 +1 today A 64 tokens

create-journal-entry

122

grahama1970/agent-skills

Skill Claude Code

Nightly journal entry creation for all personas. Wraps persona-journal generation with dream pipeline integration -- journal entries feed into create-movie dream residue and dreams feed back into future journals.

not rated 6 +1 today A 42 tokens

create-ksml

123

grahama1970/agent-skills

Skill Claude CodeCodex

Convert project manifests into Kling Shot Markup Language (KSML) for video generation.

not rated 6 +1 today A 22 tokens

create-lut

124

grahama1970/agent-skills

Skill Claude Code

Generate or bake cinematic 3D LUTs (.cube) from reference/source pairs or presets.

not rated 6 +1 today A 23 tokens

create-midi

125

grahama1970/agent-skills

Skill Claude Code

Compose MIDI arrangements and convert between JSON spec and MIDI files. Two modes: 'compose' uses LLM (via /prompt-lab prompt) to create a full arrangement from annotated lyrics + reference MIDI fragments + heart tags. 'from-spec' and 'to-spec' are mechanical JSON↔MIDI conversion via prettymidi. The arrangement is the…

not rated 6 +1 today A 91 tokens

create-mockup

126

grahama1970/agent-skills

Skill Claude Code

Canonical front door for design creation and redesign. Routes new mockups, multi-model bakeoffs, design improvement, and ship-stage verification through mockup-lab, ask, review-design, create-image, ux-lab, best-practices-react, and test-interactions instead of making users choose among fragmented entrypoints.

not rated 6 +1 today A 69 tokens

create-movie

127

grahama1970/agent-skills

Skill Claude Code

Orchestrated movie creation for Horus persona. Guides through phases: Research → Script → Build Tools → Generate → Assemble. Uses Docker-isolated coding environment, free/open-source tools only, with full memory integration.

not rated 6 +1 today A 47 tokens

create-music

128

grahama1970/agent-skills

Skill Claude Code

AI-assisted music creation for Horus persona. Voice conversion (RVC) and music generation (MusicGen/AudioCraft). Stem separation uses create-stems skill. Local-first with GPU acceleration.

not rated 6 +1 today A 43 tokens

create-paper

129

grahama1970/agent-skills

Skill Claude Code

Orchestrate paper writing from project analysis. Composes assess, dogpile, arxiv, and review-code skills. Interview-driven workflow with frequent human collaboration to resolve ambiguity and validate each stage.

not rated 6 +1 today A 42 tokens

create-pdf-fixture

130

grahama1970/agent-skills

Skill Claude Code

Create complete PDF test fixtures combining ReportLab tables and AI-generated images. Orchestrates create-table and create-image skills. Creates PDFs designed to test/expose extractor bugs.

not rated 6 +1 today A 40 tokens

create-peer-review

131

grahama1970/agent-skills

Skill Claude Code

Automated peer review of research papers using Shadow-LEGO's self-improving cascade. Multiple fictional reviewer personas score papers against arxiv exemplars on standard rubrics (soundness, novelty, clarity, significance, presentation). The cascade learns from teacher reviews to produce increasingly accurate local…

not rated 6 +1 today A 67 tokens

create-persona

132

grahama1970/agent-skills

Skill Claude CodeCodex

Deliberate persona creation for client modeling, expert profiles, and stakeholder mapping. Integrates with /interview for collaborative creation and /ask for knowledge enrichment. Supports Theory of Mind (BDI), voice training, and simulacrum validation.

not rated 6 +1 today A 53 tokens

create-qras

133

grahama1970/agent-skills

Skill Claude CodeCodex

Generate QRA (Question-Reasoning-Answer) pairs from controls, documents, or text. Three modes: native (framework definitions), relationship (crosswalk chains), standalone (documents).

not rated 6 +1 today A 42 tokens

create-react-designs

134

grahama1970/agent-skills

Skill Claude Code

Create production-grade React/Tailwind/ShadCN designs with a multi-persona feedback loop. Generates "ready to connect" front-ends, uses a Persona Council (Simulacrum + Taxonomy) to critique designs, consults experts if confidence is low, and iterates until production quality is reached.

not rated 6 +1 today A 68 tokens

create-regressor

135

grahama1970/agent-skills

Skill Claude Code

Train task-specific regression models from tabular data. Supports linear, ridge, lasso, gradient boosting, random forest, and XGBoost. Auto-selects best model via cross-validation. JSONL/CSV input, joblib output.

not rated 6 +1 today A 52 tokens

create-report

136

grahama1970/agent-skills

Skill Codex

Create project-aware evidence reports and report UIs from a given project, surface, artifact, or question. Use when the user asks to create a report, HTML/CSS report, project status report, page-purpose report, implementation/readiness report, source-of-truth audit, application inventory, review readout, or…

not rated 6 +1 today A 124 tokens

create-score

137

grahama1970/agent-skills

Skill Claude Code

Generate scene-specific music using ACE-Step 1.5 via Dockerized FastAPI. Supports reference audio for theme continuity across scenes. Integrates with Federated Taxonomy (HMT) for multi-hop graph traversal in /memory.

not rated 6 +1 today A 49 tokens

grahama1970/agent-skills

Skill Claude Code

Grammarly-like sentence decomposition with NVIS confidence colors. Decomposes question text into annotated fragments showing which entities resolved, which are misspelled, which are fabricated, and which are unknown. Composes /extract-entities for grounding data and /interview for "Did you mean?" clarify prompts.

not rated 6 +1 today A 68 tokens

create-sound-design

139

grahama1970/agent-skills

Skill Claude Code

Orchestrate sound effects (SFX) selection and placement per scene. Integrates with sfx-catalog for library access and memory for learning. Multi-round collaborative workflow with auto-approve for pipeline mode.

not rated 6 +1 today A 47 tokens

create-status-surface

140

grahama1970/agent-skills

Skill Codex

Create receipt-backed status surfaces and Tau DAG handoff contracts from local progress, gate, and checker receipts. Use when a workflow needs a global progress bar, evidence status board, local readiness surface, or robust Tau connection without claiming provider readiness or live completion.

not rated 6 +1 today A 56 tokens

create-stems

141

grahama1970/agent-skills

Skill Claude Code

Audio stem separation using Demucs (4-stem or 6-stem) and optional UVR ensemble. Uses the Python API entrypoint for clean error handling. GPU-accelerated, local-first.

not rated 6 +1 today A 45 tokens

create-story

142

grahama1970/agent-skills

Skill Claude Code

Creative writing orchestrator for Horus persona. Multi-phase workflow: Initial Thought → Research (movies, books, memory, past) → Dogpile Context → Iterative Writing (2-3 drafts with critiques). Supports all formats: short stories, screenplays, podcast scripts, novellas, flash fiction.

not rated 6 +1 today A 64 tokens

create-storyboard

143

grahama1970/agent-skills

Skill Claude CodeCodex

Transform screenplay output from /create-story into animatics with camera framing, visual panels, and timing. Highly collaborative - the skill acts as a creative cinematographer, making suggestions and asking questions throughout the process. Integrates with /memory for learned techniques.

not rated 6 +1 today A 54 tokens

grahama1970/agent-skills

Skill Claude CodeCodex

Create, iterate, and deploy dynamic Stream Deck button pages. Design context-aware layouts that auto-switch based on active window, voice mode, or running skills. Evaluate layouts against ground truth, self-correct, and store winners as memory-backed templates with taxonomy tags. Triggers: create streamdeck page…

not rated 6 +1 today A 73 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: