Neeeophytee

Draft, rewrite, or audit evidence-based public-health communication using an independently expressed interpretation of the CDC Clear Communication Index. Use for patient explanations, health campaigns, risk and emergency messages, public-safety notices, and…

Draft, restructure, or audit evidence-led scientific and engineering reports using an independently expressed reference-only interpretation of official NASA technical-publication guidance. Use for test and experiment reports, design descriptions, technical…

Draft, rewrite, or audit patient-facing health and service content using an independently expressed reference-only interpretation of official NHS content guidance. Use for symptoms and conditions pages, appointment messages, treatment explanations,…

Draft, rewrite, or audit investor-facing financial and legal disclosure using an independently expressed interpretation of official SEC plain-English guidance. Use for prospectus summaries, risk factors, shareholder letters, offering materials, and securities…

Draft, restructure, or audit specification-style technical reports using an independently expressed reference-only interpretation of W3C editorial guidance. Use for protocols, standards, interoperability documents, conformance requirements, and technical…

Draft, rewrite, or audit inclusive US digital-government content using an independently expressed interpretation of the 18F Content Guide. Use for public-service websites, forms, applications, transactional messages, help content, notices, and government…

Draft, rewrite, or audit concise interface text using an independently expressed reference-only interpretation of Apple's Human Interface Guidelines for writing. Use for buttons, labels, settings, alerts, errors, onboarding, notifications, permissions, empty…

Draft, rewrite, or audit approachable developer product documentation using an independently expressed interpretation of the GitHub Docs style. Use for product workflows, how-to guides, conceptual overviews, troubleshooting, security guidance, and…

Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples. Use when building an MCP server or tool definition, writing an agent-facing script, or when an agent keeps misusing a tool…

Audit the instructions an agent already carries — CLAUDE.md, AGENTS.md, skills, tool descriptions — for contradictions, over-constraint, and duplication, then propose a cut list. Use when an agent ignores its own instructions, when a CLAUDE.md has grown…

Split an oversized skill, CLAUDE.md, or spec into an entry file plus files that load only when they're needed.

After a working session, produce a report on what changed plus a quiz the user must pass before merging. Use when the user asks "what did we actually do," wants to review a large change, or invokes a quiz before merge.

Write an implementation plan that leads with the decisions the user is most likely to change, and buries the mechanical work at the bottom. Use when planning is requested before a build, especially after brainstorming or an interview.

Surface the user's unknown unknowns before work starts. Use when the user is entering an unfamiliar codebase area, an unfamiliar domain (design, video, infra), or explicitly asks for a "blindspot pass" or to find their "unknown unknowns."

Generate several genuinely different throwaway variations (designs, approaches, drafts) for the user to react to. Use when the user can only recognize what they want by seeing it — visual design, UX flows, naming, tone — or asks to brainstorm or prototype…

Keep a running implementation-notes.md during a build, logging every deviation from the plan and every discovered edge case. Use whenever implementing against an agreed plan or spec, especially in long autonomous sessions.

Enforce a hard cap and a drift-check when a cheap executor model consults an expensive advisor model, and compute the effective cost from actual call counts instead of a benchmark's assumed rate. Use when the user adopts the advisor or orchestrator pattern,…

Before swapping any workload to a cheaper model, declare the cases the premium model still dominates and prove they keep routing to premium. Use when the user wants to "just switch" to a cheaper model (text, image, or video), or asks whether a cheap model is…

Cut agent token spend by shrinking what enters the context window. Index the repo or corpus once and query it instead of re-reading files on every question. Use when the user complains their coding agent burns tokens, the context fills up fast, the same files…

Route high-volume, low-stakes triage (reading piles, inbox summaries, needs-reply flags) to a free model with a strict output schema. Use when the user wants one-line summaries of many items cheaply, asks to triage email, articles, or reports with AI, or…

Size a big one-time batch job against a free tier's rate limit and token budget BEFORE starting it, with a proven wall-clock ETA. Use when the user wants to label a dataset, summarize an archive, or process a large backlog for free (or on a tiny rate limit),…

Choose a model with evidence by running the few prompts that actually matter across candidate models inside a free tier's caps, picking by a stated criterion. Use when the user asks "which model should I use", wants to evaluate a newly launched model, or is…

Stop paying for deep reasoning on easy turns by setting a modest default reasoning effort and escalating per task. Use when the user runs a reasoning model in an agent and the bill is dominated by output or thinking tokens, or asks about reasoning_effort,…

Cut LLM spend by routing bulk work to a cheap model and escalating only the hard turns to a premium one. Use when the user says their AI bill is too high, asks to "use a cheaper model", or wants two-tier model routing without losing quality on the hard tasks.

Compare an original asset with resized, converted, uploaded, or downloaded derivatives and produce a JSON, Markdown, or HTML provenance-survival report. Use when testing whether a CMS, image optimizer, social network, editor, screenshot, watermark-removal…

Audit supported metadata surfaces in images, SVG, PDF, and OOXML assets for privacy signals such as GPS, author, device, software, comments, and timestamps. Use when preparing a public release and metadata exposure must be assessed without altering or…

Answer the five provenance questions for a single asset in one pass - was provenance located, verified, and trusted, was the scan complete, and what remains unknown. Use when a user asks for an overall provenance verdict on a file and does not want to…

Review a structured record of AI-generated outputs for provenance evidence, human-readable disclosure, model identification, and documented edits. Use when preparing for publication or policy review and teams need gaps and next actions without a legal…

Run every available text-provenance detector over a document or string and report per-detector states, including hidden Unicode channels and detached C2PA manifests. Use when a user asks whether text carries an AI watermark, contains invisible or smuggled…

Inspect local files or text for observable provenance metadata, possible C2PA markers, hashes, and text control characters. Use when a user asks whether an asset contains Content Credentials, an AI mark, provenance metadata, or suspicious invisible characters…

Verify C2PA Content Credentials in a local asset with the official c2patool, separating manifest presence, cryptographic integrity, and signer trust. Use when a user needs defensible validation instead of byte-marker guesses, including offline and…