run
Skill2 starsChanged 55 days agoApache-2.0View on GitHub
Launch and drive the current project's real runtime surface so a human-visible or programmatic behavior can be observed. Use when asked to run the app, try a change, open the UI, exercise a CLI/TUI/API, or capture runtime evidence. Prefer an existing project run-* skill; otherwise infer the smallest safe launch path.
45 other projects use a version of this.
Adopted by
Most recently taken up by
- stunt-double/stuntdouble-mcptheir own version, first seen Nov 8, 2026
- chryzxc/cpipetheir own version, first seen Nov 8, 2026
- jorgenschaefer/skillstheir own version, first seen Nov 1, 2026
- ccomkhj/product-demotheir own version, first seen Nov 1, 2026
- Zmoki/zmoki-astro-startertheir own version, first seen Oct 27, 2026
- phnx-labs/agi-clitheir own version, first seen Oct 26, 2026
Used with
Projects with it also use init, report and 5 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.
MicrosoftSkillinit
Also in 4 projects that use this
- MicrosoftSkill
report
Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.
Also in 3 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 4 projects that use this
VercelSkillsetup
Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".
Also in 5 projects that use this
AnthropicSkillstatus
Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.
Also in 3 projects that use this
Hugging FaceSkillimplement
Make tests pass. Invoke after /write-tests produces failing tests.
Also in 4 projects that use this
- +1 more from microsoft
Other versions45 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 45
- perber/leafwiki★ 1.2ksame name
- NVIDIA/nvcf★ 261same name
- jjanczur/tyran★ 81same name
- Decentralized-LM/delm-agent-plugin★ 47same name
- microsoft/Employee-Self-Service-Agent-Developer-Kit★ 29same name
- phnx-labs/agi-cli★ 26same name
- doem97/cvsm★ 23same name
- JinukMoon/oh-my-mlip★ 20same name
- Hassaan146/claude-skills★ 18same name
- Aloim/phaneslightplugin★ 5same name
35 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.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- chatcut-production-mirror/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- run-skill-generatorSkill
- verifySkill
- html-artifactsSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 41 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Before inventing commands, search the relevant repo/package scope for project skills.
- Distinctive: line 14
If no usable project recipe exists, inspect the smallest set of authoritative launch hints: package/build manifests, README/developer docs, …
- Distinctive: line 28
Do not substitute an internal function call for the public surface when a public surface exists.
- Very specific: line 32
Use the project's documented install/build/launch steps.
- Distinctive: line 34
Never perform destructive external writes just to prove the app starts.
“Common” is measured: kept by at least 6 in 10 of the 41 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
Run the real application
The goal is not merely that a command exits zero. The goal is a live handle on the surface a user or downstream program actually touches.
Find the project recipe first
Before inventing commands, search the relevant repo/package scope for project skills. Prefer the most specific matching run-* recipe for the files or package being worked on.
If no usable project recipe exists, inspect the smallest set of authoritative launch hints: package/build manifests, README/developer docs, container config, executable entrypoints, and server config. If the launch path is unusual or took real discovery, use run-skill-generator after you get it working.
Identify the runtime surface
| Product shape | Runtime surface |
| Web/desktop GUI | pixels plus browser/window interaction |
| CLI | command line, stdout/stderr, exit status |
| TUI/REPL | interactive terminal session |
| HTTP/API/server | listening socket plus real request/response |
| Library/SDK | public package boundary from a consumer process |
| Agent/prompt | real agent invocation and resulting behavior |
| Workflow/CI | actual workflow run |
Do not substitute an internal function call for the public surface when a public surface exists.
Launch safely
Use the project's documented install/build/launch steps. Reuse existing dependencies and credentials; do not invent secrets. Isolate shared state with ephemeral ports, temporary directories, named tmux sessions, and test/sandbox accounts where practical.
Never perform destructive external writes just to prove the app starts. Use a dry run, sandbox, disposable target, or stop at the risky boundary and report it.
Drive the smallest meaningful flow
Exercise the smallest path that reaches the intended behavior:
- UI change -> navigate to the changed screen and interact with it.
- CLI flag -> invoke the shipped/public CLI with the flag.
- API handler -> send a real request through the listening server.
- error handling -> trigger the actual error from the public surface.
- persistence -> perform the action, reload/reopen, and observe persisted state.
Capture evidence as you go: screenshot, pane capture, stdout/stderr, response body, or another runtime artifact.
Report
Return the launch method, exact surface driven, observed result, evidence, any environment limitation, and cleanup status. Tests/typecheck are not proof that the application itself ran.
See references/surfaces.md when the project has multiple possible runtime surfaces.
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.