Simple English
moeru-ai/airi
Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop.
Check that a change to the user-facing docs covers both clients (the TUI and the desktop app) unless the feature exists in only one, and decide whether it needs a new or updated screenshot, then…
$ npx skills add vfarcic/dot-agent-deck --skill docs-screenshots-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install vfarcic/dot-agent-deck docs-screenshots-review --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/vfarcic/dot-agent-deck.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/docs-screenshots-review .claude/skills/docs-screenshots-review && 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 "docs-screenshots-review" agent skill from https://github.com/vfarcic/dot-agent-deck/tree/main/.claude/skills/docs-screenshots-review into .claude/skills/docs-screenshots-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docs-screenshots-review", 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/vfarcic/dot-agent-deck/tree/main/.claude/skills/docs-screenshots-reviewType 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 vfarcic/dot-agent-deck --skill docs-screenshots-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install vfarcic/dot-agent-deck docs-screenshots-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vfarcic/dot-agent-deck.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/docs-screenshots-review .agents/skills/docs-screenshots-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "docs-screenshots-review" agent skill from https://github.com/vfarcic/dot-agent-deck/tree/main/.claude/skills/docs-screenshots-review into .agents/skills/docs-screenshots-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docs-screenshots-review", 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 vfarcic/dot-agent-deck --skill docs-screenshots-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install vfarcic/dot-agent-deck docs-screenshots-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vfarcic/dot-agent-deck.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/docs-screenshots-review .cursor/skills/docs-screenshots-review && 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 "docs-screenshots-review" agent skill from https://github.com/vfarcic/dot-agent-deck/tree/main/.claude/skills/docs-screenshots-review into .cursor/skills/docs-screenshots-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docs-screenshots-review", 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/vfarcic/dot-agent-deck.git --path .claude/skills/docs-screenshots-review--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 vfarcic/dot-agent-deck --skill docs-screenshots-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install vfarcic/dot-agent-deck docs-screenshots-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vfarcic/dot-agent-deck.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/docs-screenshots-review .gemini/skills/docs-screenshots-review && 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 "docs-screenshots-review" agent skill from https://github.com/vfarcic/dot-agent-deck/tree/main/.claude/skills/docs-screenshots-review into .gemini/skills/docs-screenshots-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docs-screenshots-review", 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 vfarcic/dot-agent-deck docs-screenshots-reviewInstalls 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 vfarcic/dot-agent-deck --skill docs-screenshots-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/vfarcic/dot-agent-deck.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/docs-screenshots-review .github/skills/docs-screenshots-review && 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 "docs-screenshots-review" agent skill from https://github.com/vfarcic/dot-agent-deck/tree/main/.claude/skills/docs-screenshots-review into .github/skills/docs-screenshots-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docs-screenshots-review", 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 vfarcic/dot-agent-deck --skill docs-screenshots-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install vfarcic/dot-agent-deck docs-screenshots-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vfarcic/dot-agent-deck.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/docs-screenshots-review .opencode/skills/docs-screenshots-review && 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 "docs-screenshots-review" agent skill from https://github.com/vfarcic/dot-agent-deck/tree/main/.claude/skills/docs-screenshots-review into .opencode/skills/docs-screenshots-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "docs-screenshots-review", 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.
docs-screenshots-reviewCheck that a change to the user-facing docs covers both clients (the TUI and the desktop app) unless the feature exists in only one, and decide whether it needs a new or updated screenshot, then…
Docs Screenshots Review is an agent skill from vfarcic/dot-agent-deck. Check that a change to the user-facing docs covers both clients (the TUI and the desktop app) unless the feature exists in only one, and decide whether it needs a new or updated screenshot, then produce it or say exactly which one to capture. Use whenever you create, edit, move or delete any file under docs/ that is NOT under docs/develop/ (the pages published to agent-deck.devopstoolkit.ai), or the home page (site/landing/), in any task, including when the docs edit is a side effect of a code change, a…
Its SKILL.md is about 1.9k 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 Development, covering Changelog and release notes. The repository describes itself as: A rich terminal dashboard for monitoring and controlling multiple AI coding agent sessions. The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 9cc3e60. 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.
Shell commands in SKILL.md call:
cargoFrom 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.
Docs Screenshots Review loads about 1.9k tokens when it runs. Until then it costs about 182 tokens; SKILL.md has 1,046 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 vfarcic/dot-agent-deck at commit 9cc3e60, republished under its MIT licence (© vfarcic). 1,046 words, ~1,874 tokens.
.claude/skills/docs-screenshots-review/SKILL.md (or your agent's skills folder).The user docs under docs/ (not docs/develop/, which is never published) and the site's home page describe two clients of one daemon, the TUI and the desktop app. Screenshots are part of those docs, they go stale, and they are generated from code by cargo docs-screenshots so that fixing a stale one is a command, not a manual session. This skill makes sure every docs change covers both clients and gets a deliberate screenshot decision.
The rule: every page shows and explains both the TUI and the desktop app, unless the feature works in only one of them. Most features live in the daemon, so both clients have them; they just present them differently (a card or a row, a tab or a group, Ctrl+n or New agent). Name both where they differ, in the prose and in the screenshots. Do not write a page, a paragraph or a caption that describes only the TUI and leaves the desktop app implied, or the other way round.
A feature one client lacks is the exception, and it is stated, not left implicit: say which client has it, so a reader of the other client knows why they do not see it. Known examples when this was last checked: the Schedules manager is TUI-only; voice control and several daemons on one dashboard are desktop-only. Treat that list, and the desktop feature inventory in prds/done/1321-user-docs-both-clients.md, as a starting point that goes stale as features move, not the source of truth: check "both have it" or "only one has it" against the code before writing it (CLAUDE.md rule 17).
How to show both depends on the page. In the docs, a screenshot of a feature both clients have is one image per client, under a **TUI:** and a **Desktop:** label (section 2). On the home page, the reader should not have to choose a client, so both clients' images sit side by side, each labelled (the story rows in site/landing/index.html are the pattern).
Read the diff of the docs pages you touched and answer, for each changed section:
 or ./img/…) and open the image file. If the change you made — or the code change behind it — alters what that screen shows (a label, a column, a button, a status word), the image is stale.Write the decision down in your report either way — "no screenshot needed: this section is about the TOML schema" is a valid outcome. Do not add images for their own sake.
cargo docs-screenshots first. docs/develop/docs-screenshots.md is the reference: prerequisites, the command, the registered scenarios, and how to add one. In short:
cargo docs-screenshots --list # what exists
cargo docs-screenshots --scenario <name> # regenerate one into docs/img//img/<scenario>-<client>.png.xtask/screenshots/src/scenarios.rs, its TUI capture in tests/e2e_docs_screenshots.rs, its desktop capture in desktop/screenshots/desktop.shot.ts (with fixture state in desktop/src/data/fixture.ts when it must mirror a TUI scene). A feature both clients have uses one scenario name on both, depicting the same state, so the two images pair up.docs/img is a symlink to site/static/img; the PNGs are committed there. Never commit a screenshot that shows a real home path, host name, token or someone else's project — scenarios run in a sandbox for that reason.Embed a two-client screenshot as two labelled blocks, TUI first. The published docs are plain Markdown, served as is and printed by dot-agent-deck docs, so there are no tabs or other MDX components:
**TUI:**

**Desktop:**
The blank lines around each image are required. Write alt text that says what is in the frame.
Where no scenario can reach the screen, use the run-dot-agent-deck skill to drive the TUI in an isolated sandbox and capture it, and say on the page, in the PRD or in your report that this image is not reproducible from a scenario and why.
That sandbox isolates the capture from your own deck; it redacts nothing. A frame with a real agent in it can show credentials, prompts or someone else's content, so apply the rule for agent-backed scenarios in docs/develop/docs-screenshots.md: redact before the image is written, then inspect the final image yourself for tokens, real home paths, host names, user names, prompts and anyone else's content before committing or publishing it. If it cannot be made clean, do not commit it; tell the user what to capture instead, as section 3 describes.
Then build the site — cargo xtask site <a-new-directory> — which fails on a broken image or link.
When producing it is out of reach (no display, the desktop app's Playwright dependencies missing, a screen that needs a real agent or a remote host), do not skip silently. Tell the user, in your final report: the page and section, the client(s), the exact state to show (which screen, which dialog open, what data on screen), the file name it should have (docs/img/<scenario>-<client>.png), and whether a scenario should be added for it.
Most tasks never touch docs/ or the home page, so this is a skill rather than a CLAUDE.md rule that every session would load. If agents turn out not to invoke it reliably, the fallback is a hook scoped to edits under docs/** that prompts for this review. That hook is not built; it is the next step only if this skill is observed being skipped (PRD #1321).
© vfarcic, MIT. 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 .claude/skills/docs-screenshots-review of vfarcic/dot-agent-deck.
Open the folder on GitHubat commit 9cc3e60
Docs Screenshots Review 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 |
|---|---|---|---|---|---|---|
| Docs Screenshots Review this skillvfarcic/dot-agent-deck | 109 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Simple Englishmoeru-ai/airi | 50k | 2 repos | ~4.6k | Automated safety check: Pass | MIT | |
| StarRocks Release NotesStarRocks/starrocks | 12k | — | ~1.9k | Automated safety check: Notes | Apache-2.0 | |
| Cutting A ReleaseTriliumNext/Trilium | 38k | — | ~3.2k | Automated safety check: Pass | AGPL-3.0 | |
| Mole CLI Release Flowtw93/Mole | 70k | — | ~2.6k | Automated safety check: Pass | GPL-3.0 | |
| React Router Release Notes Prepremix-run/react-router | 57k | — | ~1.1k | Automated safety check: Pass | MIT |
moeru-ai/airi
Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop.
StarRocks/starrocks
Drafts English release notes for a StarRocks patch release from the PRs merged into its release branch, then opens a documentation PR and hands translation to /translate.
TriliumNext/Trilium
A skill your agent uses when cutting, preparing, or debugging a Trilium release — bumping the monorepo version, tagging, or diagnosing a failed "Release" workflow run.
tw93/Mole
Runbook for assessing and executing a Mole CLI release: distribution channels, pre-flight checks, capital-V tags, build artifacts and the handoff to curated release notes.
remix-run/react-router
Polishes pending React Router change files before the versioning scripts run, and decides whether a long-form What's Changed section is warranted.
PrefectHQ/fastmcp
Cut a FastMCP release end to end. An agent skill from PrefectHQ/fastmcp.
vfarcic/dot-agent-deck
Choose the shape of a unit you are about to dispatch in this repo — one agent (--single) or a team (--orchestration '<name') — from divisibility criteria instead of asking, and report the shape you…
vfarcic/dot-agent-deck
Generate a feature request prompt for another dot-ai project.
vfarcic/dot-agent-deck
Take committed work from a branch to a verified pull request — push, open the PR, settle CI and the automated review, answer and resolve every finding, and hand off.
vfarcic/dot-agent-deck
Publish the docs site to GHCR with a main-<sha tag and bump site/helm/values.yaml so Argo CD picks it up — without cutting a SemVer release.
vfarcic/dot-agent-deck
Run, build, smoke-test, and screenshot the dot-agent-deck binary against an isolated sandbox.
vfarcic/dot-agent-deck
Stitch a manifest of terminal recordings into one narrated MP4 (title/description card, then clip, repeated) and optionally upload it privately to YouTube.
Categories
Check that a change to the user-facing docs covers both clients (the TUI and the desktop app) unless the feature exists in only one, and decide whether it needs a new or updated screenshot, then…. Docs Screenshots Review is an agent skill from vfarcic/dot-agent-deck. Check that a change to the user-facing docs covers both clients (the TUI and the desktop app) unless the feature exists in only one, and decide whether it needs a new or updated screenshot, then produce it or say exactly which one to capture.
Docs Screenshots Review fits situations like: delete any file under docs/ that is NOT under docs/develop/ (the pages published to agent-deck.devopstoolkit.ai); the home page (site/landing/); including when the docs edit is a side effect of a code change; A changelog-driven update.
Run `npx skills add vfarcic/dot-agent-deck --skill docs-screenshots-review -a claude-code`. Or copy the skill folder (.claude/skills/docs-screenshots-review in vfarcic/dot-agent-deck) into .claude/skills/docs-screenshots-review in your project. Claude Code loads it when a task matches its description.
Run `npx skills add vfarcic/dot-agent-deck --skill docs-screenshots-review -a codex`. Or copy the skill folder (.claude/skills/docs-screenshots-review in vfarcic/dot-agent-deck) into .agents/skills/docs-screenshots-review 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 vfarcic/dot-agent-deck --skill docs-screenshots-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/docs-screenshots-review, .gemini/skills/docs-screenshots-review, .github/skills/docs-screenshots-review and .opencode/skills/docs-screenshots-review in your project.
Going by SKILL.md and its folder, Docs Screenshots Review needs the command-line tools its instructions call (cargo).
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.
Docs Screenshots Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.9k tokens (SKILL.md is roughly 7.5k 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 Docs Screenshots Review: Simple English (moeru-ai/airi, 50k stars), StarRocks Release Notes (StarRocks/starrocks, 12k stars), Cutting A Release (TriliumNext/Trilium, 38k stars) and Mole CLI Release Flow (tw93/Mole, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
vfarcic (a GitHub user) maintains it in vfarcic/dot-agent-deck, which has 109 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 10, 2026.
Source: vfarcic/dot-agent-deck on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.