run-experiment SKILL.md skillA
run-experiment from tomzx/agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add tomzx/agents/run-experiment@git:20261007.b35fc4bPins git:20261007.b35fc4b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- tomzx/agents
- Path
skills/pdlc/skills/run-experiment/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261007.b35fc4b, committed Oct 7, 2026
- First version recorded
- Aug 5, 2026
- Size
- 2,328 bytes
- Repository stars
- 12
- License
- MIT
Execute an experiment plan, collect data, and record a proceed/kill verdict against the pre-set threshold. End of the PDLC Validate phase.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Run Experiment Executes the `experiment-plan.md`, collects the data, and records a verdict against the threshold that was set *before* the test. This is where the PDLC proves its value: a negative result here is a successful kill, not a failure. ## Prerequisites - Apply the shared PDLC conventions in `skills/pdlc/references/shared.md`. - `experiment-plan.md` with a pre-set decision threshold. ## Steps 1. Run the test per the plan: stand up the fake-door, run the concierge flow, deploy the prototype, or field the survey. 2. Collect the raw data and observations. Keep both quantitative results and qualitative surprises. 3. Compare the result to the pre-set threshold. State the verdict explicitly: `proceed`, `kill`, or `inconclusive`. 4. If `inconclusive`, diagnose why (sample too small, test not decisive, threshold wrong) and decide whether to re-run with a better test or proceed with lower confidence (recorded as an assumption). 5. Capture learnings: what surprised you, what you now believe that you didn't before. 6. Watch for false positives: would you have seen this result even if the assumption were false? 7. Write `experiment-result.md` to the initiative directory. …
Read the whole file at its exact version.
How to install
mdr add tomzx/agents/run-experiment@sha256:3a2551b8441d967cThe line at the top of this page pins the label git:20261007.b35fc4b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_gho42hor5tafbazw)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Aug 5, 2026 and Oct 7, 2026, about one every 31 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261007.b35fc4b latest | 2026-10-07 | b35fc4b | 2,328 B | A | view · diff |
| git:20261004.00bb0c5 | 2026-10-04 | 00bb0c5 | 2,322 B | A | view · diff |
| git:20260805.6b62307 | 2026-08-05 | 6b62307 | 2,325 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2328 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
tomzx/agents · 12 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_gho42hor5tafbazw GET https://markdownregistry.com/api/v1/resolve?ref=tomzx/agents/run-experiment GET https://markdownregistry.com/api/v1/blob/3a2551b8441d967c96109edfbdf2421d07cf02c9c456793b28e9612714896d52
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.