Skill Retro
kenneth-liao/ai-launchpad-marketplace
A skill your agent uses when reviewing how skills performed during a session, when the user wants to analyze skill invocations and identify improvements, or when the user says "skill retro", "review…
Required for visualized output. An agent skill from OpenLoaf/OpenLoaf.
$ npx skills add OpenLoaf/OpenLoaf --skill visualization-ops-skill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install OpenLoaf/OpenLoaf visualization-ops-skill --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/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/visualization-ops/en .claude/skills/visualization-ops-skill && 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 "visualization-ops-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/visualization-ops/en into .claude/skills/visualization-ops-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visualization-ops-skill", 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/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/visualization-ops/enType 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 OpenLoaf/OpenLoaf --skill visualization-ops-skill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install OpenLoaf/OpenLoaf visualization-ops-skill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .agents/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/visualization-ops/en .agents/skills/visualization-ops-skill && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "visualization-ops-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/visualization-ops/en into .agents/skills/visualization-ops-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visualization-ops-skill", 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 OpenLoaf/OpenLoaf --skill visualization-ops-skill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install OpenLoaf/OpenLoaf visualization-ops-skill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/visualization-ops/en .cursor/skills/visualization-ops-skill && 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 "visualization-ops-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/visualization-ops/en into .cursor/skills/visualization-ops-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visualization-ops-skill", 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/OpenLoaf/OpenLoaf.git --path apps/server/src/ai/builtin-skills/visualization-ops/en--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 OpenLoaf/OpenLoaf --skill visualization-ops-skill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install OpenLoaf/OpenLoaf visualization-ops-skill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/visualization-ops/en .gemini/skills/visualization-ops-skill && 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 "visualization-ops-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/visualization-ops/en into .gemini/skills/visualization-ops-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visualization-ops-skill", 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 OpenLoaf/OpenLoaf visualization-ops-skillInstalls 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 OpenLoaf/OpenLoaf --skill visualization-ops-skill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .github/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/visualization-ops/en .github/skills/visualization-ops-skill && 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 "visualization-ops-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/visualization-ops/en into .github/skills/visualization-ops-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visualization-ops-skill", 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 OpenLoaf/OpenLoaf --skill visualization-ops-skill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install OpenLoaf/OpenLoaf visualization-ops-skill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/visualization-ops/en .opencode/skills/visualization-ops-skill && 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 "visualization-ops-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/visualization-ops/en into .opencode/skills/visualization-ops-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visualization-ops-skill", 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.
visualization-ops-skillRequired for visualized output. An agent skill from OpenLoaf/OpenLoaf.
Visualization Ops Skill is an agent skill from OpenLoaf/OpenLoaf. Required for visualized output. When the prompt involves news/briefings/market updates/rankings/reports/summaries/analyses/comparisons/selection/recommendations/roundups/retrospectives, or is expected to return 3+ structurable items, this skill must be loaded before (or in the same turn as) the data-fetching tool. Once loaded, do not finish with plain markdown text—you must render via JsxCreate or ChartRender. Typical examples: "search the latest news about Iran", "compare Obsidian/Notion/Logseq", "recommend a…
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Product & Project Management, covering Stock and market analysis, Subagents and Retrospectives. It works with Obsidian and Notion. The repository describes itself as: 🍞Open-source, local-first AI workspace with Agents, multi-model chat (GPT/Claude/Gemini/DeepSeek), Notion-like docs, AI image & video generation, email, calendar & terminal…. The licence is AGPL-3.0.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit f7eccf6. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are json and javascript).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Visualization Ops Skill loads about 2.5k tokens when it runs. Until then it costs about 181 tokens; SKILL.md has 1,006 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.
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.
The full file from OpenLoaf/OpenLoaf at commit f7eccf6, republished under its AGPL-3.0 licence (© OpenLoaf). 1,006 words, ~2,506 tokens.
.claude/skills/visualization-ops-skill/SKILL.md (or your agent's skills folder).| Tool | Responsibility | Read-only |
|---|---|---|
JsxCreate | Live JSX component rendering (cards / lists / tables / rich text and other structured output) | No |
ChartRender | ECharts chart rendering (line / bar / pie / scatter / radar / heatmap / map) | Yes |
Loading: both are deferred tools. Before calling, activate their schemas via
ToolSearch(names: "JsxCreate,ChartRender").
Think of your output as two parallel channels:
JsxCreate / ChartRender appears as standalone bubbles directly shown to the user in chatThe user sees both channels at once. So just like a person who finishes writing a letter doesn't add "I just finished writing the letter"—do not pre-announce before calling these tools ("let me organize the data first / I'll create a line chart / now let me make another summary card"), and do not summarize afterward ("chart rendered / card generated"). The user already saw it; those words are just noise.
Correspondingly, your step-level text should in most cases be empty, until after the final tool call, when you write a single concluding passage of text—and only in one of the following situations:
If none of those apply, writing no text at all is perfectly fine—the tool bubbles themselves are the answer.
Anti-pattern (an actual play-by-play from a real session, to be avoided):
step 2: "The search results returned some stock market information, but mostly landing pages of market centers, missing concrete stock data. Let me search for something more specific…" step 3: "Good, now I have some concrete stock market data. Let me organize the past week's stock data…" step 4: "Now I've loaded ChartRender and JsxCreate. Let me create a line chart…" step 5: "Chart rendered. Now let me use JsxCreate to make a summary card…" step 6: "Done. I used ChartRender to render … and used JsxCreate to create …"
All 5 of those text passages should be deleted, keeping only the final genuine interpretation like "Looking at the data, the A-share market has oscillated upward over the past week…".
Needs visualized output
├── Data chart (line/bar/pie/scatter/radar/heatmap/map)?
│ └── ChartRender (ECharts option)
├── Custom card/panel/layout/status display/information summary?
│ └── JsxCreate (JSX component)
└── Unsure?
├── Has numeric trends/comparisons/distributions → ChartRender
└── Other structured information display → JsxCreateSubmit an ECharts option to render a chart inside the message. The frontend uses the ECharts library and supports all ECharts chart types.
Parameters:
option (required): complete ECharts option object or a JSON stringtitle (optional): chart titleheight (optional): chart height (pixels)Key points for writing an ECharts option:
xAxis/yAxis/series etc.tooltip and legend is recommended for readabilityExamples:
Bar chart:
{
"option": {
"xAxis": { "type": "category", "data": ["Mon", "Tue", "Wed", "Thu", "Fri"] },
"yAxis": { "type": "value" },
"series": [{ "type": "bar", "data": [120, 200, 150, 80, 70] }],
"tooltip": { "trigger": "axis" }
},
"title": "Weekly Data"
}Pie chart:
{
"option": {
"series": [{
"type": "pie",
"radius": "60%",
"data": [
{ "value": 335, "name": "Direct" },
{ "value": 234, "name": "Email" },
{ "value": 154, "name": "Search" }
]
}],
"tooltip": { "trigger": "item" },
"legend": { "orient": "vertical", "left": "left" }
}
}Renders JSX components live inside the chat interface. Suitable for displaying custom cards, status panels, information summaries, and other structured content.
Parameters:
content (required): JSX stringCore rules:
import/export/const/let/function/function definitions.{() => { ... return (...) }()} or {(function(){...})()}—the validator will reject it. This is the single most common anti-pattern from models such as MiniMax.{[{name:'A'},{name:'B'}].map(x => <div key={x.name}>{x.name}</div>)}{} expressions, map, conditional rendering, and style={{...}} are allowed{...props} spread syntax is not supportedWrong vs. correct example:
// ❌ Wrong: top level is a function, validation fails
{() => {
const items = [{title: 'A'}, {title: 'B'}]
return <div>{items.map(i => <p>{i.title}</p>)}</div>
}()}
// ✅ Correct: top level is an element, data expressed inline
<div className="flex flex-col gap-2 p-3">
{[{title: 'A'}, {title: 'B'}].map((item, i) => (
<div key={i} className="rounded-lg bg-card p-2 text-sm">{item.title}</div>
))}
</div>After validation fails: the tool returns an absolute path and the error reason. Prefer re-calling JsxCreate with a full corrected content (a complete rewrite is less error-prone than a partial Edit). Only use Edit on that absolute path when the issue is clearly an isolated character-level problem. Do not Glob/Read to look for the file—the absolute path is already in the error message.
Color scheme conventions:
OpenLoaf uses an Apple-style flat palette. All colors are routed through semantic tokens that adapt to light/dark themes. Writing bg-white or text-gray-800 directly will turn into a harsh white block or invisible text in dark mode—so only use semantic tokens:
Base colors: bg-card, bg-muted, text-foreground, text-muted-foreground
Semantic accent colors (low-opacity background + flat text, legible in both themes):
bg-ol-blue/10 text-ol-bluebg-ol-green/10 text-ol-greenbg-ol-amber/10 text-ol-amberbg-ol-red/10 text-ol-redbg-ol-purple/10 text-ol-purpleTags / badges: rounded-full px-2.5 py-0.5 text-xs combined with the flat colors above.
Do not use gradients (bg-gradient-*), shadows (shadow-*), or outer borders (border/ring)—JSX components are embedded inside the chat message stream, and such decorations make the card look like a standalone popup rather than part of the message, breaking reading flow.
Style conventions:
rounded-lg/rounded-xl, tight spacing (p-3p-4, gap-2gap-3)text-sm/text-xs and wide horizontal layouts—chat window width is limited, and overly tall content forces the user to scroll for a long time.Allowed component whitelist (case-sensitive): Message, MessageContent, Panel, Snippet, SnippetAddon, SnippetText, SnippetInput, SnippetCopyButton, CodeBlock, Checkpoint, Task, TaskTrigger, TaskContent, TaskItem, TaskItemFile, Image, Attachments, Attachment, AudioPlayer, AudioPlayerElement, AudioPlayerControlBar, AudioPlayerPlayButton, AudioPlayerSeekBackwardButton, AudioPlayerSeekForwardButton, AudioPlayerTimeDisplay, AudioPlayerTimeRange, AudioPlayerDurationDisplay, AudioPlayerMuteButton, AudioPlayerVolumeRange, WebPreview, WebPreviewNavigation, WebPreviewNavigationButton, WebPreviewUrl, WebPreviewBody, WebPreviewConsole
Using bordered components such as Message/Panel/Snippet as outer containers is not recommended.
Validation and correction:
Edit and the preview will refreshEdit—do not call JsxCreate againWrite location: [<sessionId>]/asset/jsx/<messageId>.jsx (inside the session's asset directory; Edit can patch it in place).
Interactive forms: when you need to collect user input, ask the user directly in plain text and wait for a reply. JsxCreate is for display only.
| Scenario | Recommended tool |
|---|---|
| Numeric trends / comparisons / distributions | ChartRender |
| Custom cards / panels | JsxCreate |
| Mixed statistics + charts | First ChartRender for the chart, then JsxCreate for the summary card |
| Simple data (2–3 metrics) | JsxCreate alone, no chart needed |
| Complex interactive charts | ChartRender (ECharts has built-in interactions) |
© OpenLoaf, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in apps/server/src/ai/builtin-skills/visualization-ops/en of OpenLoaf/OpenLoaf.
Open the folder on GitHubat commit f7eccf6
Visualization Ops Skill 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 |
|---|---|---|---|---|---|---|
| Visualization Ops Skill this skillOpenLoaf/OpenLoaf | 107 | — | ~2.5k | Automated safety check: Pass | AGPL-3.0 | |
| Skill Retrokenneth-liao/ai-launchpad-marketplace | 126 | — | ~2.1k | Automated safety check: Pass | None | |
| RetrospectiveSzotasz/marveen | 115 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Personal Assistant Reviewedonyzpc/personal-assistant | 148 | — | ~3.2k | Automated safety check: Pass | AGPL-3.0 | |
| Oracle PrismSoul-Brews-Studio/arra-oracle-skills-cli | 122 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Set Workflow Statesandgardenhq/sgai | 137 | — | ~1.2k | Automated safety check: Pass | Custom licence |
kenneth-liao/ai-launchpad-marketplace
A skill your agent uses when reviewing how skills performed during a session, when the user wants to analyze skill invocations and identify improvements, or when the user says "skill retro", "review…
Szotasz/marveen
Analyze the current session for improvement opportunities in skills, memory, and workflow.
edonyzpc/personal-assistant
Review uncommitted or PR diffs in the personal-assistant Obsidian plugin with project-specific risk lanes, second-layer future-risk checks, severity discipline, subagent review routing, and…
Soul-Brews-Studio/arra-oracle-skills-cli
Multi-perspective analysis — one agent transforms through 5 lenses (Archaeologist, Bug Hunter, Skeptic, Architect, Auditor) inline, no subagents.
sandgardenhq/sgai
Coordinator and retrospective workflow-state protocol. An agent skill from sandgardenhq/sgai.
OpenHands/extensions
Create an automation that drafts incident retrospectives. An agent skill from OpenHands/extensions.
OpenLoaf/OpenLoaf
Triggers when the master Agent faces a multi-step complex task and is deciding whether / how to outsource sub-tasks to built-in subagents (browser / doc-editor / data-analyst / extractor /…
OpenLoaf/OpenLoaf
Triggered when the user asks for page-level interaction with a specific webpage: login, form filling, button clicks, pagination scraping, screenshots, downloading page images, handling CAPTCHAs or…
OpenLoaf/OpenLoaf
Triggered when the user wants lifecycle management of OpenLoaf canvases / whiteboards: create, open, filter, duplicate, delete, rename, or change ownership.
OpenLoaf/OpenLoaf
Reads, edits, converts and reviews Word documents through three dedicated tools, covering tracked changes, comments, tables, images and format conversion.
OpenLoaf/OpenLoaf
Handles a real email account through query and mutate tools: check the inbox, read, search, reply, forward, compose and organize, with sending always confirmed first.
OpenLoaf/OpenLoaf
Guides an agent to operate native macOS apps by surveying an app first, acting through intents, menus or keystrokes, and verifying each step, in OpenLoaf Desktop only.
Required for visualized output. An agent skill from OpenLoaf/OpenLoaf. Visualization Ops Skill is an agent skill from OpenLoaf/OpenLoaf. Required for visualized output.
Visualization Ops Skill fits situations like: tasks that involve Stock and market analysis; tasks that involve Subagents; tasks that involve Retrospectives.
Run `npx skills add OpenLoaf/OpenLoaf --skill visualization-ops-skill -a claude-code`. Or copy the skill folder (apps/server/src/ai/builtin-skills/visualization-ops/en in OpenLoaf/OpenLoaf) into .claude/skills/visualization-ops-skill in your project. Claude Code loads it when a task matches its description.
Run `npx skills add OpenLoaf/OpenLoaf --skill visualization-ops-skill -a codex`. Or copy the skill folder (apps/server/src/ai/builtin-skills/visualization-ops/en in OpenLoaf/OpenLoaf) into .agents/skills/visualization-ops-skill in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OpenLoaf/OpenLoaf --skill visualization-ops-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/visualization-ops-skill, .gemini/skills/visualization-ops-skill, .github/skills/visualization-ops-skill and .opencode/skills/visualization-ops-skill in your project.
SKILL.md names no scripts, command-line tools or credentials: Visualization Ops Skill is instructions for the agent only.
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.
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.
Visualization Ops Skill is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Visualization Ops Skill: Skill Retro (kenneth-liao/ai-launchpad-marketplace, 126 stars), Retrospective (Szotasz/marveen, 115 stars), Personal Assistant Review (edonyzpc/personal-assistant, 148 stars) and Oracle Prism (Soul-Brews-Studio/arra-oracle-skills-cli, 122 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
OpenLoaf (a GitHub organization) maintains it in OpenLoaf/OpenLoaf, which has 107 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on May 14, 2026.
Source: OpenLoaf/OpenLoaf on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.