theclaymethod

theclaymethod/unslop

Instructions file CodexOpenCode

AGENTS.md instructions for theclaymethod/unslop, covering agent instructions, product rule, add or change a pattern, check the repository and interpret results.

theclaymethod/unslop

Instructions file

Claude Code instructions for theclaymethod/unslop, covering claude instructions, product rule, add or change a pattern, check the repository and interpret results.

theclaymethod/unslop

Skill Claude CodeCodex

Remove AI writing patterns from prose using either audit-only detection or a two-pass rewrite flow (diagnosis then reconstruction). Use this skill when editing, reviewing, or rewriting AI-generated content to make it sound human. Triggers on requests to "humanize", "de-slop", "fix AI text", "make it sound human"…

theclaymethod/unslop

Command

Surface AI patterns as reviewable edits the user accepts or rejects, rather than a finished rewrite. Agent-invoked, never a background daemon. Route here on /unslop cleanup or when the user wants suggestions instead of a silent rewrite. Set $INPUT to the source.

theclaymethod/unslop

Command

Turn one AI-ism caught in the wild into a scanner contract example and a structured PR. Route here on "contribute a pattern", "add this tell", or "I found a new AI-ism". Everything stays offline until the user approves both publication and the final PR body. Read references/contribute.md for the precheck exit codes…

theclaymethod/unslop

Command

Single-pass voiced writing. Draft or rewrite in a taught voice, then clear the full gate battery. Route here on "write this like me", "match my voice", or "mimic this author" once a voice card exists. Read references/mimic.md for card anatomy, scoring, and failure modes.

theclaymethod/unslop

Command

The default command. Read references/core-contract.md; it is authoritative. Use two passes: diagnose, then repair confirmed findings and validate.

theclaymethod/unslop

Command

Build a reusable voice from a writer's samples. Agent-driven end to end: the user supplies only approvals and answers, never a directory or a command. Route here on "teach my voice", "learn how I write", or when the user offers samples to learn from. Any samples the user provides are fair game; there are no rights or…

theclaymethod/artifacture

Plugin Claude Code

Plugin marketplace listing 1 plugin: visual-explainer.

theclaymethod/artifacture

Plugin Claude Code

Plugin distribution for visual-explainer.

theclaymethod/artifacture

Plugin Claude Code

Generate beautiful HTML pages for diagrams, diff reviews, plan reviews, and data tables.

theclaymethod/artifacture

Agent Claude Code

Build one visual-explainer diagram fragment. Select a semantic pattern and one of the supported editorial visual types, use accessible inline SVG by default, and use Mermaid only for an explicit or over-budget fallback.

theclaymethod/artifacture

Agent Claude Code

Build the Mono-Industrial hero section — the single moment-of-surprise (oversized Geist Pixel number, display word, or break-the-grid element). Invoked by the visual-explainer orchestrator as part of fan-out. Produces one HTML fragment + scoped CSS, never a full page.

theclaymethod/artifacture

Agent Claude Code

Build a Mono-Industrial data-table section — sticky header, no zebra, hairline above each row, status colors on values only. Invoked by the visual-explainer orchestrator as part of fan-out. Produces one HTML fragment + scoped CSS, never a full page.

theclaymethod/artifacture

Agent Claude Code

Run the visual-explainer preset/aesthetic LLM verification pass for only the active preset. Returns only verdict JSON.

theclaymethod/artifacture

Agent Claude Code

Judge only curated explanatory-artifact decorations that falsely imply sequence, state, confidence, or provenance. Returns only verdict JSON.

theclaymethod/artifacture

Agent Claude Code

Run the visual-explainer source-vs-render completeness LLM verification pass. Returns only verdict JSON.

theclaymethod/artifacture

Agent Claude Code

Judge rendered slide truth, annotation mapping, reading path, structural variety, and every click-in/progressive state. Returns only verdict JSON.

theclaymethod/artifacture

Agent Claude Code

Run the visual-explainer diagram LLM verification pass over per-figure screenshots. Returns only verdict JSON.

theclaymethod/artifacture

Agent Claude Code

Run the visual-explainer layout LLM verification pass over screenshots and layout candidates. Returns only verdict JSON.

theclaymethod/artifacture

Agent Claude Code

Route each slide or coherent page section to the minimum explanatory treatment and judge operating-model fidelity only where applicable. Returns only verdict JSON.

theclaymethod/artifacture

Agent Claude Code

Run the visual-explainer poster PNG LLM verification pass. Returns only verdict JSON.

theclaymethod/artifacture

Skill Claude CodeCodex

Generate beautiful, self-contained HTML artifacts from MDX/React sources that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, code walkthrough, or any visual explanation of technical…

theclaymethod/artifacture

Command

Open an existing visual explainer in the developer preview for click-to-comment review and safe direct text edits.