AGENT SKILL

dsh-plugin-dev

Establish precise DeepSeek Harness (DSH) and Cordis vocabulary and choose stable architectural seams. Use when designing or reviewing DSH plugins, distinguishing native from application-defined concepts, or deciding among Service, Event, Registry, SessionEvent, Projection, persistence, and execution boundaries.

License 许可
MIT
最近更新
2026-11-15
Stars
★ 852
Forks
63

01 前言 Front Matter

name
dsh-plugin-dev
license
MIT
metadata
{ "sources": "pinned DSH upstream and docs/research authoring reports; dsh_research DSH/Cordis foundations", "verifiedAt": "2026-09-20", "upstreamSha": "ddefc45fbc7f8e46dd73185e68295696d1297887", "skillVersion": "0.3.4", "verifiedAgainst": "dsh 0.1.6-alpha.2" }
description
Establish precise DeepSeek Harness (DSH) and Cordis vocabulary and choose stable architectural seams. Use when designing or reviewing DSH plugins, distinguishing native from application-defined concepts, or deciding among Service, Event, Registry, SessionEvent, Projection, persistence, and execution boundaries.

02 资源文件 8

03 SKILL.md 正文

DSH/Cordis context and decisions

Skill v0.3.4 · verified against DSH 0.1.6-alpha.2 (upstream SHA ddefc45fbc7f8e46dd73185e68295696d1297887).

Foundation-first workflow

  1. Read references/context.md completely. Use its canonical leading words so every important object and boundary maps to one defined DSH/Cordis term. Label downstream concepts as application-defined.
  2. Follow references/decision-tree.md. Give each responsibility one primary seam with explicit ownership and lifecycle.
  3. After choosing the seam, verify version-specific API names, signatures, manifests, build behavior, and runtime details against the current DSH official documentation, pinned upstream source, and the running Host.

Scope boundary

This skill intentionally contains only the stable semantic and architectural layer: Context, canonical vocabulary, concept maps, and decision logic. It does not cache a Host API catalog, Client API catalog, Slot inventory, or community implementation survey. Those details change too quickly to be a trustworthy installed skill.

Historical investigations remain in the canonical BotHarness repository under docs/research/; they are evidence for maintainers, not published guidance. A downstream product's Context, architecture, and ADRs remain outside this skill and own its product vocabulary.

References

  • references/context.md — canonical DSH/Cordis vocabulary, boundaries, and conceptual architecture.
  • references/decision-tree.md — requirement-to-seam decisions for dispatch, persistence, execution, and presentation.

04 同仓库更多 Skills

BotHarness
BotHarness/DeepSeekBot

slide-authoring

Technical reference for writing or editing open-slide pages — file contract, 1920×1080 canvas, type scale, layout, palette/visual direction, assets, speaker notes, stepped reveals, page transitions, and morph transitions. Consult this whenever you are about to write or modify any file under `slides/<id>/`, including from inside the `create-slide` or `apply-comments` workflows, or for any ad-hoc slide edit. Triggers on phrases like "edit slide", "tweak this page", "fix the layout", "change the palette", "reveal one by one", "add a transition", "morph transition", "write the speaker notes", "generate the script / talk track", "investigate the slide framework", "how do slides work here".

★ 852
BotHarness
BotHarness/DeepSeekBot

current-slide

Resolve which slide, page, and (optionally) selected element the user is currently viewing in the open-slide dev server. Consult this whenever the user references "this page", "this slide", "this element", "the slide I'm on", "the current page", or any deictic reference to slide content without naming it. Re-read `node_modules/.open-slide/current.json` at the start of every such turn — the user navigates between turns, so a value you read earlier in the conversation is almost certainly stale.

★ 852
BotHarness
BotHarness/DeepSeekBot

create-theme

Use this skill when the user wants to create, draft, author, or extract a slide theme in this open-slide repo. Triggers on phrases like "create a theme", "make a theme called X", "extract a theme from <slide>", "build a theme from these images". Produces two paired files under `themes/` — `<id>.md` (palette, typography, layout, fixed Title/Footer components, motion) and `<id>.demo.tsx` (a runnable demo slide that the dev-UI Themes panel previews). Do NOT use for editing real slides — only for authoring the theme bundle.

★ 852
BotHarness
BotHarness/DeepSeekBot

create-slide

Use this skill when the user wants to create, draft, author, or generate new slides / a presentation in this open-slide repo. Triggers on phrases like "make slides about X", "make a deck about X", "create a presentation", "draft slides for", "new slide", "a deck with speaker notes / a script", or when the user asks to add content under `slides/`. Do NOT use for editing the framework itself — only for authoring content inside `slides/<id>/`.

★ 852
BotHarness
BotHarness/DeepSeekBot

apply-comments

Apply pending @slide-comment markers written by the open-slide inspector tool. Use when the user asks to "apply comments", "process slide comments", "apply the inspector comments", or references markers left inside `slides/<id>/index.tsx`.

★ 852
BotHarness
BotHarness/DeepSeekBot

writing-shape

Writing, exploit: shape raw material into an article, paragraph by paragraph.

★ 852