run
Skill1 starsChanged 33 days agoMITView on GitHub
Trigger: "run", "run my prompt", "ejecuta mi prompt", /run. Executes the latest active prompt from the project PROMPTS.md in the Obsidian vault as if typed in chat, then strikes it through.
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 6 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
MicrosoftSkillreport
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 repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- capture-insightsSkill
- create-runbookSkill
- datadog-logs-analyzerSkill
- datadog-metrics-investigatorSkill
- datadog-report-publisherSkill
- datadog-service-healthSkill
- datadog-triageSkill
- k8s-error-analyzerSkill
- k8s-optimizer-costSkill
- meeting-notes-enhanceSkill
- second-opinionSkill
- stack-updaterSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 7 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 41 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 63
Check that {{OBSIDIAN_VAULT}}/meridian/<slug>/ exists.
- Distinctive: line 65
If it does not exist -> stop with an error:
- Very specific: line 76
If the project folder exists but PROMPTS.md is missing, create it from the template below, then tell the user "Created PROMPTS.md for …
- Very specific: line 95
Read PROMPTS.md. Find the last ## section whose heading line does NOT contain <!-- run:.
- Very specific: line 99
If there is no active section -> tell the user "No pending prompts in <slug>." and stop.
- Distinctive: line 104
Treat the extracted body as a new user instruction and execute it directly in the current session, with full access to the current context, …
- Very specific: line 110
After execution, edit PROMPTS.md so the executed section's heading becomes:
- Distinctive: line 116
Use the current local date/time.
- Distinctive: line 126
Never guess the slug from anything other than the current directory basename.
- Distinctive: line 127
Never auto-create the Meridian project folder — error out instead (Step 1).
- Very specific: line 128
Never execute a section that already has a <!-- run: --> marker.
- Distinctive: line 129
Never modify, reorder, or delete other sections or the frontmatter.
- Distinctive: line 130
Never strip or rewrite the prompt body when striking it through.
“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 — execute my own prompt from the PKM
This skill lets you drive a session by writing in your Obsidian PKM instead of the
chat box. You keep a PROMPTS.md file inside each Meridian project; run finds the
one matching the current repo, reads the latest active prompt, and executes it in
the current session exactly as if you had typed it. After running, it strikes the
prompt through so the file becomes a conversational history.
When to Use
Trigger when the user says run, /run, "ejecuta mi prompt", "run my prompt", or
similar. This is manual-only.
This is a different skill from mdn-run (Meridian task execution). run does not
touch tasks or plans — it only reads/executes free-form prompts from PROMPTS.md.
PROMPTS.md format
Path: {{OBSIDIAN_VAULT}}/meridian/<slug>/PROMPTS.md
Each prompt is a ## <title> section. The section body is the full prompt
(multi-line, code, anything). New prompts are appended at the bottom.
---
project: data-charts
type: prompts
---
# PROMPTS - data-charts
> Write a new prompt as a `## <title>` section at the bottom.
> `run` executes the last ACTIVE section (no `<!-- run: -->` marker) and then strikes it.
## fix the date parser
Your full prompt here...
multiple lines, code, whatever.- Active prompt = the last (bottom-most)
##section whose heading does NOT contain a<!-- run: ... -->marker. - An executed prompt's heading looks like:
## ~~fix the date parser~~ <!-- run: 2026-06-05 11:44 -->The<!-- run: -->marker is the source of truth for "already executed"; the~~...~~strikethrough is for visual history.
Workflow
Step 0 — Resolve the vault and project slug
- The vault is
{{OBSIDIAN_VAULT}}(substituted at install time). - Determine the current project: take the basename of the current workspace /
working directory (e.g.
/Users/me/projects/data-charts->data-charts). This basename is the<slug>. Match is exact.
Step 1 — Locate the Meridian project
Check that {{OBSIDIAN_VAULT}}/meridian/<slug>/ exists.
- If it does not exist -> stop with an error:
Do nothing else.No Meridian project found for "<slug>". Create it first, e.g. /mdn-init name:<slug>
Step 2 — Locate PROMPTS.md
Look for {{OBSIDIAN_VAULT}}/meridian/<slug>/PROMPTS.md.
- If the project folder exists but
PROMPTS.mdis missing, create it from the template below, then tell the user "Created PROMPTS.md for<slug>— write your first prompt as a## <title>section and run again." and stop.
Template:
---
project: <slug>
type: prompts
---
# PROMPTS - <slug>
> Write a new prompt as a `## <title>` section at the bottom.
> `run` executes the last ACTIVE section (no `<!-- run: -->` marker) and then strikes it.Step 3 — Extract the active prompt
Read PROMPTS.md. Find the last ## section whose heading line does NOT contain
<!-- run:. That section's body (everything between its heading and the next ##
heading or end of file, excluding the frontmatter and the # title) is the prompt.
- If there is no active section -> tell the user "No pending prompts in
<slug>." and stop.
Step 4 — Execute
Treat the extracted body as a new user instruction and execute it directly in the current session, with full access to the current context, exactly as if the user had typed it in chat. Do not summarize it back first — just do it.
Step 5 — Strike through / history
After execution, edit PROMPTS.md so the executed section's heading becomes:
## ~~<original title>~~ <!-- run: YYYY-MM-DD HH:MM -->Use the current local date/time. Leave the section body untouched so the prompt stays readable in history. Write the file back, preserving frontmatter and all other sections exactly.
Step 6 — Confirm
Report a one-line summary: which prompt was executed (its title) and what it did.
Anti-Patterns
- Never guess the slug from anything other than the current directory basename.
- Never auto-create the Meridian project folder — error out instead (Step 1).
- Never execute a section that already has a
<!-- run: -->marker. - Never modify, reorder, or delete other sections or the frontmatter.
- Never strip or rewrite the prompt body when striking it through.
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.

