show-me
Skill138 starsChanged 7 months agoMITView on GitHub
Explains a topic visually with a focused diagram, decision tree, or sketch. Use for /show-me or when the user asks to see or visualize an explanation.
We split this skill into the rules it gives an agent
8 rules. 0 are common, 3 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 66 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Read referenced material first.
- Distinctive: line 21
Before and after: matched views that expose the meaningful change.
- Very specific: line 24
Use the host's supported plain-text diagram format by default.
- Very specific: line 25
Use Mermaid only when explicitly requested.
- Distinctive: line 27
Do not make HTML, a presentation, or a new UI merely to explain a small flow.
- Distinctive: line 33
Place a short explanation and source references beside the visual.
- Very specific: line 34
Check that the diagram and explanation agree and no important failure path is hidden.
- Very specific: line 35
Keep output in chat unless the user asks to save it.
“Common” is measured: kept by at least 6 in 10 of the 66 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/show-me — Visual Understanding
Show the smallest visual that answers the user's question. Adapted from the personal show-me skill.
Input
/show-me [topic or current discussion]
Read referenced material first. Apply _core/knowledge.md; do not invent relationships, states, or measured values.
Choose the Form
- Relationships or ownership: a component tree or box diagram.
- Sequence or handoffs: a flow with actors, conditions, and returns.
- Decisions: a decision tree or pseudocode with explicit branches.
- Before and after: matched views that expose the meaningful change.
- Product behavior: a user flow with entry, success, failure, and recovery states.
Use the host's supported plain-text diagram format by default. Use square-corner boxes and readable labels.
Use Mermaid only when explicitly requested; follow .claude/skills/mermaid-visualizer/SKILL.md.
For an explicitly requested editable Excalidraw file, follow .claude/skills/excalidraw/SKILL.md.
Do not make HTML, a presentation, or a new UI merely to explain a small flow.
Output Checks
Answer one visual question at a time. Label conditions and approval boundaries when they affect the flow.
Mark hypothetical flows as proposed; distinguish them from verified behavior.
Place a short explanation and source references beside the visual. Do not repeat every arrow in prose.
Check that the diagram and explanation agree and no important failure path is hidden.
Keep output in chat unless the user asks to save it; use /doc conventions when saving a note.
Other versions72 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 72
- withcoral/coral★ 4.9ksame name
- deadlock-mod-manager/deadlock-mod-manager★ 489same name
- Dimon94/dverity★ 107same name
- Dimon94/skills★ 107same name
- charlie947/show-me★ 70same name
- IgorGanapolsky/ThumbGate★ 29same name
- Melvynx/ai-maxxing-skills★ 23same name
- emiliosheinz/agent-skills★ 20same name
- ivanrvpereira/.agents★ 19same name
- kv0906/cc-skills★ 16same name
62 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use eli5, maintain-verification-skill and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AnthropicSkilleli5
Explain a topic like I'm a 5 year old. Use when the user types /eli5 <topic> or asks for a dead-simple picture explainer of how something works.
Also in 10 projects that use this
jaydubya818Skillmaintain-verification-skill
Use when a project's verification driver or feature map may be stale.
Also in 6 projects that use this
jaydubya818Skillcreate-verification-skill
Use when a repository needs a repeatable driver that proves real UI, CLI, or service behavior.
Also in 7 projects that use this
magnusrodsethSkillstacked-prs
Manage a stack of dependent pull requests (a chain where each PR's base is the branch below it, up to main). Covers GitHub's native stacked pull requests via the gh stack CLI extension, and hand-rolled stacks built with plain git + gh. Use when creating or planning a stack of dependent PRs, merging the bottom of a stack, retargeting a PR's base to main, propagating main or a review fix up a chain of branches, rebasing or restructuring a stack, resolving conflicts across a PR stack, or recovering a stacked PR that was auto-closed when its base branch was deleted.
Also in 3 projects that use this
ninehillsSkillherdr
Control herdr from inside it. Manage workspaces and tabs, split panes, run commands, read output, and wait for state changes — all via CLI commands that talk to the running herdr instance over a local unix socket. Use when running inside herdr (HERDR_ENV=1).
Also in 5 projects that use this
SentrySkilllogging-best-practices
Logging best practices focused on wide events (canonical log lines) for powerful debugging and analytics
Also in 3 projects that use this
- +1 more from jaydubya818
In this repository41 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- askSkill
- blockSkill
- dailySkill
- decideSkill
- discoverSkill
- docSkill
- docxSkill
- excalidraw-generatorSkill
- explainSkill
- gwsSkill
- healthSkill
- helpSkill
- inboxSkill
- interviewSkill
- jiraSkill
- journeySkill
- json-canvasSkill
- linearSkill
- meetSkill
- mermaid-visualizerSkill
- notionSkill
- obsidian-basesSkill
- obsidian-cliSkill
- obsidian-markdownSkill
- onboardSkill
- pdfSkill
- pptxSkill
- previewSkill
- prioritizeSkill
- progressSkill
- pushSkill
- reportSkill
- skill-creatorSkill
- todaySkill
- updateSkill
- vault-opsSkill
- weeklySkill
- xlsxSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

