DTPR for AI
Taxonomy
Claude plugin

Claude plugin

Seven-skill authoring studio for describing AI systems as DTPR datachains, iterating on the DTPR schema, drafting element icons, translating locales, and grading content for public comprehension.

The DTPR authoring plugin packages seven Agent Skills, the DTPR MCP auto-registration, and a file-based research corpus into a drop-in installation for Claude Code, Claude Cowork, and Claude.ai. It turns the integration surfaces documented elsewhere on this site — MCP tools, REST, concepts — into a workflow for writing and auditing DTPR content.

The skills are Agent Skills — the standard SKILL.md + frontmatter format, not Claude-specific. The packaging is a Claude plugin (uses claude-plugin.json and the Claude marketplace), which is what makes one-line install possible. See Other harnesses for ways to reach the same skills outside Claude.
Source of truth: plugin/dtpr/ in the repository. The plugin bundles its own SKILL.md files, rubric, and research corpus — this site is the hosted reference.

The seven skills

SkillTierUse when
dtpr-describe-systemInstanceDescribe a specific AI system as a validated DTPR datachain, optionally from a PDF, URL, or verbal description.
dtpr-datachain-structureMeta-structureCritique or propose changes to the datachain-type shape itself (categories, requirements, retirement, the locale allow-list).
dtpr-category-auditCategoryAudit one category's element collection for coherence, overlap, and gaps.
dtpr-element-designElementDraft, edit, or retire one element — its title, description, variables, and symbol disposition.
dtpr-symbol-designSymbolPropose or refine an SVG symbol for an element — three variants per round, local HTML preview, finalized markup.
dtpr-translateLocaleFill in non-English locale rows on an element, category, or pasted English fragment, against the active manifest's locale allow-list.
dtpr-comprehension-auditComprehensionGrade any DTPR content against the public-comprehension rubric.

The seven are peers — there is no runtime router. Users (and the agent's description-based skill selector) pick based on the judgment tier the question lives at. Each schema-tier skill emits a pnpm --filter ./api schema:new <type> <YYYY-MM-DD>-beta handoff line; a human edits YAML in the resulting beta directory, validates with schema:validate, and opens a PR. dtpr-element-design hands off the SVG step to dtpr-symbol-design, which writes a local HTML preview but never into app/public/dtpr-icons/symbols/ — the user saves the chosen variant themselves.

In this section

  • Install — per-host install instructions and the capability matrix.
  • Skills — one page per skill.
  • Research corpus — the file-based knowledge base that compounds across authoring sessions.
  • Comprehension rubric — the seven-item rubric schema-tier skills inline and dtpr-comprehension-audit grades against.

Other harnesses

The skills are written as portable Agent Skills. Today's primary distribution is the Claude plugin documented above; the same SKILL.md files reach other harnesses through these paths:

  • Anthropic Agent SDK. Both @anthropic-ai/claude-agent-sdk (TypeScript) and claude-agent-sdk (Python) load Agent Skills directly from a directory. Point the SDK at plugin/dtpr/skills/ and the same description-based dispatch works in any application built on the SDK.
  • MCP prompts/ capability. The DTPR MCP server registers each skill's body (and the two shared reference documents) as a named MCP prompt. Any MCP-aware client (Cursor, Continue, Cline, Claude Desktop, custom clients, the Anthropic Agent SDK) lists and loads them via prompts/list + prompts/get against the existing remote MCP at https://api.dtpr.io/mcp — no per-harness packaging, no skill-side changes required. The bundle is regenerated from plugin/dtpr/skills/ on each API deploy, so the prompts and the Claude plugin install stay in lock-step.
  • Harness-native instruction files. The skills can be projected into AGENTS.md, CLAUDE.md, .cursorrules, or .github/copilot-instructions.md for harnesses that read those formats. This loses description-based dispatch (the user has to invoke each skill explicitly) but works in any harness that can read a project-level instructions file.
  • Plain HTTPS. Each SKILL.md file is a static markdown document. A harness with a fetch capability can pull them directly from the GitHub raw URL on demand.

The MCP at https://api.dtpr.io/mcp is harness-agnostic from day one — every skill's tool calls work the same way no matter how the skill itself is loaded.

Related

  • MCP server — the 9-tool API the skills drive.
  • Concepts — DTPR vocabulary used across every skill.
  • Changelog — release notes for the plugin and the API.

Subchains

Named, ordered groupings of categories at the datachain-type level, and their realizations on a datachain instance.

Install

Install the DTPR plugin in Claude Code, Claude Cowork, or Claude.ai, and the capability matrix that determines which skills work fully on each host.