ModLens Image Vision Bridge
liustack/modlens
Gives text-only models sight by running the modlens CLI on an image path or URL and returning structured JSON evidence with transcribed text, layout and semantics.
Search the EvalDock dsh-Top100 catalog and recommend suitable DeepSeek Harness plugins or Skills.
MITAuto-check passed
Install Recommend Dsh Plugins
$ npx skills add evaldock-account/dsh-top100 --skill recommend-dsh-plugins -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install evaldock-account/dsh-top100 recommend-dsh-plugins --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/evaldock-account/dsh-top100.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugin/skills/recommend-dsh-plugins .claude/skills/recommend-dsh-plugins && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "recommend-dsh-plugins" agent skill from https://github.com/evaldock-account/dsh-top100/tree/main/plugin/skills/recommend-dsh-plugins into .claude/skills/recommend-dsh-plugins/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recommend-dsh-plugins", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/evaldock-account/dsh-top100/tree/main/plugin/skills/recommend-dsh-pluginsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add evaldock-account/dsh-top100 --skill recommend-dsh-plugins -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install evaldock-account/dsh-top100 recommend-dsh-plugins --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/evaldock-account/dsh-top100.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugin/skills/recommend-dsh-plugins .agents/skills/recommend-dsh-plugins && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "recommend-dsh-plugins" agent skill from https://github.com/evaldock-account/dsh-top100/tree/main/plugin/skills/recommend-dsh-plugins into .agents/skills/recommend-dsh-plugins/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recommend-dsh-plugins", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add evaldock-account/dsh-top100 --skill recommend-dsh-plugins -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install evaldock-account/dsh-top100 recommend-dsh-plugins --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/evaldock-account/dsh-top100.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugin/skills/recommend-dsh-plugins .cursor/skills/recommend-dsh-plugins && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "recommend-dsh-plugins" agent skill from https://github.com/evaldock-account/dsh-top100/tree/main/plugin/skills/recommend-dsh-plugins into .cursor/skills/recommend-dsh-plugins/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recommend-dsh-plugins", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/evaldock-account/dsh-top100.git --path plugin/skills/recommend-dsh-plugins--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add evaldock-account/dsh-top100 --skill recommend-dsh-plugins -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install evaldock-account/dsh-top100 recommend-dsh-plugins --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/evaldock-account/dsh-top100.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugin/skills/recommend-dsh-plugins .gemini/skills/recommend-dsh-plugins && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "recommend-dsh-plugins" agent skill from https://github.com/evaldock-account/dsh-top100/tree/main/plugin/skills/recommend-dsh-plugins into .gemini/skills/recommend-dsh-plugins/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recommend-dsh-plugins", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install evaldock-account/dsh-top100 recommend-dsh-pluginsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add evaldock-account/dsh-top100 --skill recommend-dsh-plugins -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/evaldock-account/dsh-top100.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugin/skills/recommend-dsh-plugins .github/skills/recommend-dsh-plugins && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "recommend-dsh-plugins" agent skill from https://github.com/evaldock-account/dsh-top100/tree/main/plugin/skills/recommend-dsh-plugins into .github/skills/recommend-dsh-plugins/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recommend-dsh-plugins", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add evaldock-account/dsh-top100 --skill recommend-dsh-plugins -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install evaldock-account/dsh-top100 recommend-dsh-plugins --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/evaldock-account/dsh-top100.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugin/skills/recommend-dsh-plugins .opencode/skills/recommend-dsh-plugins && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "recommend-dsh-plugins" agent skill from https://github.com/evaldock-account/dsh-top100/tree/main/plugin/skills/recommend-dsh-plugins into .opencode/skills/recommend-dsh-plugins/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recommend-dsh-plugins", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
recommend-dsh-plugins- GitHub stars
- 495
- Token cost
- ~583 tokens
- SKILL.md length
- 287 words
- Files
- 2
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Search the EvalDock dsh-Top100 catalog and recommend suitable DeepSeek Harness plugins or Skills.
- Works in 7 steps: Identify the user's goal and important… → Call dsh_top100_search with a concise… → If the first search returns no useful… → …
- The user asks which DSH plugin to install
- SKILL.md covers Workflow and Guardrails
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Recommend Dsh Plugins is an agent skill from evaldock-account/dsh-top100. Search the EvalDock dsh-Top100 catalog and recommend suitable DeepSeek Harness plugins or Skills. Use when the user asks which DSH plugin to install, requests plugin recommendations or comparisons, describes a capability they want to add, or asks questions such as ‘我该装哪个插件’, ‘推荐几个插件’, or ‘有没有能做某件事的插件’.
Its SKILL.md is about 580 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It works with DeepSeek. The licence is MIT.
When your agent uses it
- The user asks which DSH plugin to install
- Requests plugin recommendations
- Describes a capability they want to add
- Asks questions such as 我该装哪个插件
Example prompts
- “/recommend-dsh-plugins”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Identify the user's goal and important constraints. Ask one short clarifying question only when a missing constraint would materially…
- Call dsh_top100_search with a concise capability query. Keep useful product terms such as OCR, browser, memory, Git, security, or workflow.
- If the first search returns no useful match, retry once with a shorter query or a Chinese/English synonym.
- Recommend 3–5 results based primarily on functional fit and compatibility. Use trust level, evidence signals, Stars, recent growth…
- For every recommendation, state
- Identify at least one reasonable alternative when multiple results are close, and explain the tradeoff without claiming that a catalog…
- Mention that the results come from the EvalDock Top100 market and include its catalog link.
What it can do on your machine
Read from SKILL.md and the folder at commit ab01178. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Recommend Dsh Plugins loads about 583 tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 287 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from evaldock-account/dsh-top100 at commit ab01178, republished under its MIT licence (© evaldock-account). 287 words, ~583 tokens.
Download SKILL.mdSave it as
.claude/skills/recommend-dsh-plugins/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- recommend-dsh-plugins
- description
- Search the EvalDock dsh-Top100 catalog and recommend suitable DeepSeek Harness plugins or Skills. Use when the user asks which DSH plugin to install, requests plugin recommendations or comparisons, describes a capability they want to add, or asks questions such as ‘我该装哪个插件’, ‘推荐几个插件’, or ‘有没有能做某件事的插件’.
Recommend DSH plugins
Find recommendations from the live EvalDock dsh-Top100 catalog instead of relying on memory.
Workflow
- Identify the user's goal and important constraints. Ask one short clarifying question only when a missing constraint would materially change the recommendation.
- Call
dsh_top100_searchwith a concise capability query. Keep useful product terms such as OCR, browser, memory, Git, security, or workflow. - If the first search returns no useful match, retry once with a shorter query or a Chinese/English synonym.
- Recommend 3–5 results based primarily on functional fit and compatibility. Use trust level, evidence signals, Stars, recent growth, category, and installation support as supporting evidence rather than choosing by Stars alone.
- For every recommendation, state:
- why it fits the stated need;
- its form factor, category, Stars, and installation availability;
- its trust level, supporting signals, and the returned trust caveat;
- the repository link returned by the tool.
- Identify at least one reasonable alternative when multiple results are close, and explain the tradeoff without claiming that a catalog signal is a security review.
- Mention that the results come from the EvalDock Top100 market and include its catalog link.
Guardrails
- Never invent a plugin or claim a capability absent from the returned description, tags, topics, or categories.
- Say clearly when the catalog has no strong match and suggest a refined search.
- Treat
installed: trueas an existing installation and avoid recommending a duplicate install. - Treat
install-sourceas “the install target can be parsed,” not as publisher verification or a security audit. - Do not install anything unless the user explicitly asks to install it. When installation is requested, confirm the selected result before starting any state-changing action.
- Do not execute installation commands copied from a repository README.
© evaldock-account, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in plugin/skills/recommend-dsh-plugins of evaldock-account/dsh-top100.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit ab01178
Compare with similar skills
Recommend Dsh Plugins next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Recommend Dsh Plugins this skillevaldock-account/dsh-top100 | 495 | — | ~583 | Automated safety check: Pass | MIT | |
| ModLens Image Vision Bridgeliustack/modlens | 4.2k | 1 repos | ~1.3k | Automated safety check: Notes | MIT | |
| Vision SkillsAnionex/agent-vision-toolkit | 1.2k | 1 repos | ~4k | Automated safety check: Pass | MIT | |
| Distilly Person Profile Buildertitanwings/distilly | 25k | — | ~15k | Automated safety check: Notes | MIT | |
| Evals Contextzgsm-ai/costrict | 4.4k | 1 repos | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| J SpaceTiger3807861189/J-Space-Cognition-Suite | 3k | — | ~3k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Vision Skills
Anionex/agent-vision-toolkit
Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and…
Distilly Person Profile Builder
titanwings/distilly
Distills source material about a colleague, a relationship or a celebrity into reusable Person Profiles that an agent can later work from, in English or Chinese.
Evals Context
zgsm-ai/costrict
Provides context about the CoStrict evals system structure in this monorepo.
J Space
Tiger3807861189/J-Space-Cognition-Suite
Operate a selective workspace for complex reasoning, long tasks, repository engineering, coordinated agents, and authorized security analysis.
Modsearch
liustack/modsearch
Plug-in web search, X (Twitter) search, and page fetch for models without native web access.
Related
Works with
Questions about Recommend Dsh Plugins
What does Recommend Dsh Plugins do?
Search the EvalDock dsh-Top100 catalog and recommend suitable DeepSeek Harness plugins or Skills. Recommend Dsh Plugins is an agent skill from evaldock-account/dsh-top100. Search the EvalDock dsh-Top100 catalog and recommend suitable DeepSeek Harness plugins or Skills.
When should I use Recommend Dsh Plugins?
Recommend Dsh Plugins fits situations like: the user asks which DSH plugin to install; requests plugin recommendations; describes a capability they want to add; asks questions such as 我该装哪个插件.
How do I install Recommend Dsh Plugins in Claude Code?
Run `npx skills add evaldock-account/dsh-top100 --skill recommend-dsh-plugins -a claude-code`. Or copy the skill folder (plugin/skills/recommend-dsh-plugins in evaldock-account/dsh-top100) into .claude/skills/recommend-dsh-plugins in your project. Claude Code loads it when a task matches its description.
How do I install Recommend Dsh Plugins in Codex?
Run `npx skills add evaldock-account/dsh-top100 --skill recommend-dsh-plugins -a codex`. Or copy the skill folder (plugin/skills/recommend-dsh-plugins in evaldock-account/dsh-top100) into .agents/skills/recommend-dsh-plugins in your project. Codex loads it when a task matches its description.
Can I use Recommend Dsh Plugins in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add evaldock-account/dsh-top100 --skill recommend-dsh-plugins -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recommend-dsh-plugins, .gemini/skills/recommend-dsh-plugins, .github/skills/recommend-dsh-plugins and .opencode/skills/recommend-dsh-plugins in your project.
What does Recommend Dsh Plugins need to run?
SKILL.md names no scripts, command-line tools or credentials: Recommend Dsh Plugins is instructions for the agent only.
Does Recommend Dsh Plugins access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Recommend Dsh Plugins safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Recommend Dsh Plugins use?
Recommend Dsh Plugins is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Recommend Dsh Plugins use?
About 583 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Recommend Dsh Plugins?
Skills that share tags, products or a category with Recommend Dsh Plugins: ModLens Image Vision Bridge (liustack/modlens, 4.2k stars), Vision Skills (Anionex/agent-vision-toolkit, 1.2k stars), Distilly Person Profile Builder (titanwings/distilly, 25k stars) and Evals Context (zgsm-ai/costrict, 4.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Recommend Dsh Plugins?
evaldock-account (a GitHub user) maintains it in evaldock-account/dsh-top100, which has 495 GitHub stars. The repository was last updated on October 6, 2026.
Source: evaldock-account/dsh-top100 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.