grahama1970/agent-stack-public

best-practices-prompt

Rules for writing clear, testable LLM prompts. Eliminates vagueness, enforces concrete output specs, grounding in source material, and deterministic verifiability. Gate before /review-prompt.

monitor-website

Audit, sync, and update the public grahama.co site and resume surfaces from README.md and RESUME.md. Report-only audit detects drift between README's curated projects/inventory and site/content.json, plus live-site health; apply regenerates content.json from…

pitchdeck

Convert a product README into a source-controlled pitch-deck bundle and editable PPTX for Google Slides, PowerPoint for the web, Keynote, or other presentation editors; use when asked to make a deck from a README, create a pitch deck manifest, build…

agent-inbox

File-based inter-agent messaging with headless dispatch. Check inbox, send bugs/requests to other projects, automatically spawn headless agents to fix bugs, and track progress via task-monitor.

agent-status

Artifact-driven status surfaces for long-running project-agent work. Maintains status.json, events.jsonl, proof manifests, and a stale-aware STATUS.html so humans can tell where the agent is, what passed, what is still unproven, and what decision or action is…

agentic-evals

Agentic evaluation of skills using multi-trial fixtures, deterministic command assertions, trajectory checks, safety constraints, and evidence-backed readiness scoring. Use when users ask for agentic evals, multi-trial skill evaluation, skill trajectory…

agents-registry

Generate and query the centralized agent identity registry. Scans .pi/agents/*/AGENTS.md, parses frontmatter, outputs agents-registry.json and optionally syncs to /memory for semantic search.

align

Round-based context alignment before execution. Use when the human, project agent, WebGPT, scillm, ask, dogpile, memory, or project-knowledge may each hold different facts about a task; especially before ambiguous design, infographic, product workflow,…

analytics

Flexible data science analytics for any dataset. Auto-discovers schema, recommends charts, exports to create-figure. Works with JSONL, JSON, CSV from any source.

analyze-elf

Reverse-engineer features from ELF binaries. Extracts CLI commands, state machines, protocols, Zod schemas, and data models. Automatically generates a /create-walkthrough prosecution brief with Mermaid diagrams. Uses /treesitter for AST analysis of bundled…

anvil

Heavy-duty "No-Vibes" debugging and hardening orchestrator. Use this for complex, stubborn bugs where `review-code` has failed, or for "Red Teaming" (hardening) a codebase. Runs multiple agents in parallel (Thunderdome) using git worktree isolation.

argue

Multi-persona structured debate orchestrator. Personas research via /dogpile, consult colleagues via /ask, and argue toward nuanced synthesis on complex questions.

arxiv

Search arXiv for papers and extract knowledge into memory. Use `search` to find papers, `learn` to extract knowledge.

ask

Use when the user asks to query project memory, ask an oracle, use supported browser-backed reviewers, run Tau roundtable/single-handler workflows, ask Pi-native subagents from within Pi, run persona/deep-review workflows, generate image prompts, check…

assess

Step back and critically reassess project state. Use when asked to "assess", "step back", "fresh eyes", "check alignment", "sanity check", "health check", "prune documentation", or "evaluate what's working". Offers documentation pruning and doc-code alignment…

assistant-lab

Self-improvement workbench for /assistant. All the tools needed to diagnose, train, evaluate, and promote models in a continuous loop. The "warm pond" where /assistant evolves its own inference stack.

assistant

Shared GPT + classifier inference gateway for persona monitor tasks. Routes validation and classification through a 4-tier cascade: heuristic → classifier → local GPT → scillm.

batch-quality

Pre-flight validation and quality gates for batch LLM operations. ACTUALLY tests samples through LLM before burning tokens. Uses SPARTA contracts for DuckDB validation queries. Integrates with task-monitor for enforced quality gates.

batch-report

Generate post-run analysis reports for batch processing jobs. Analyzes manifests, timings, and failures to produce comprehensive markdown reports. Optionally sends to agent-inbox for cross-project communication.

battle

Red vs Blue team security competition orchestrator. Runs long-running overnight battles with 1000s of interactions, scoring, and insight generation.

benchmark-models

Standardized compliance QRA benchmarks against candidate LLMs

best-practices-agent

Non-negotiable agent behavior rules. Covers: no silent failures, no error bypassing, no raw AQL, no direct imports, no parallel infrastructure, no swallowed exceptions, use existing skills, fix errors don't dodge them, transparency in verdicts, no simulated…

best-practices-arangodb

Repo-specific ArangoDB best practices: leverage text_en analyzer (stop words, stemming, BM25), use AQL functions (LEVENSHTEIN_DISTANCE, TOKENS, NGRAM_SIMILARITY, COSINE_SIMILARITY), store domain knowledge in collections not Python code, and never duplicate DB…

best-practices-bespoke-design

Advisory-first, evidence-grounded art direction and review rules for creating digital experiences that feel genuinely custom to one brand instead of template-derived. Use when a user asks for bespoke web design, a distinctive visual world, personality-led art…

best-practices-chat

Keep Sparta Chat usable as a modern chat interface while preserving evidence-gated compliance semantics. Use when designing, reviewing, or implementing ChatWell, InlineEvidenceCase, EvidenceWorkspace, ArtifactPanel, distance modes, voice/qid interactions,…

best-practices-chat-ux

Best practices for designing, reviewing, and implementing operator chat, evidence chat, run-card chat, artifact-inspector chat, and compliance-review chat surfaces. Use when users ask for chat UX, operator console UX, agent run UX, evidence receipts, trace…

best-practices-chatterbox-agent

Best practices for Chatterbox or Chatterbox-Turbo voice agents, especially interruptible Embry-style agents that run memory, search, LLM, or other long-running skills concurrently. Use when designing, reviewing, or coding a voice coordinator, async task…

best-practices-competition

Best practices for leading Ask compete and bakeoff workflows. Use when a user asks for competing models, isolated candidate implementations, winner selection, feature harvesting, approach comparison, model bakeoffs, or a creator competition where $ask should…

best-practices-converse

Best practices for conversational response behavior in voice-first agents: conversation tone, emotional steering, paralinguistic cue injection such as [laughter], wait/delay handling, interruption handling, identity-aware memory grounding, and…

best-practices-cots

Automated COTS defense UX compliance scanner. Tests against WCAG 2.1 AA, Section 508, MIL-STD-1472H, and NIST 800-53 UI controls via CDP interaction + VLM visual analysis.

best-practices-d3

D3.js visualization best practices for performant, responsive, accessible data visualizations. Covers data joins, scales, axes, transitions, responsive SVG, interaction patterns, and accessibility. Use when writing, reviewing, or refactoring D3 visualizations.

best-practices-delivery-proof

Delivery-proof discipline for agents driving external effects: browser submits, pane messages, file writes, pushes, API calls. Use when an agent is about to claim something was sent, submitted, delivered, landed, or running; when a transport reports success…

best-practices-design

Product UX and design-practice guardrails for classifying design work, selecting applicable best-practices-* skills, preventing dashboard theater, defining mockup-first acceptance criteria, and deciding when to involve memory, dogpile, ask/scillm reviewers,…

best-practices-font

Evidence-first typography and font-system guidance for digital products, websites, portfolios, dashboards, and design systems. Use when choosing or changing fonts, pairing typefaces, auditing overused font warnings, creating meaningful typographic hierarchy,…

best-practices-github-ticket

Best practices for agent-resolved GitHub tickets, including bugs, feature requests, optimizations, maintenance, questions, and triage: filing contracts, route and subagent metadata, resolver leases, deterministic verification, review evidence, WebGPT…

best-practices-kde

Repo-specific KDE/QML best practices for agentic coding: singleton design systems, property ordering, accessibility, performance (binding loops, delegate recycling), Plasma integration, and D-Bus patterns.

best-practices-kling-contact-sheet

Create, audit, and package AI-video-ready reference packs for Kling-style element binding. Use when users ask for Kling contact sheets, Kling-ready assets, element reference packs, character reference sheets, prop sheets, scene sheets, or consistent AI-video…

best-practices-one-shot

Best practices for Ask one-shot runs: the same question to N seats concurrently, answers returned per seat with no consensus, no judge, and no quorum. Use when a user asks several models one question and wants to read each answer, when partial answers are…

best-practices-pitchdeck

Deck ARCHITECTURE rules for building pitch decks from source material — measured from a real 263-slide corpus, not invented. Use when planning a deck's sections and slide sequence, when deciding which source images become slides, or when reviewing whether a…

best-practices-plan

Best practices for orchestration-ready task files. Enforces adversarial testing, skill chain syntax, definition-of-done requirements, gate definitions, persona routing, and /model directives. Referenced by /plan and /review-plan.