build-in-public-launcher SKILL.md skillA
This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.
build-in-public-launcher from fairy123456789/human-edge-agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add fairy123456789/human-edge-agent-skills/build-in-public-launcher@git:20260908.449ec5cPins git:20260908.449ec5c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- fairy123456789/human-edge-agent-skills
- Path
skills/build-in-public-launcher/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260908.449ec5c, committed Sep 8, 2026
- First version recorded
- Sep 5, 2026
- Size
- 2,833 bytes
- Repository stars
- 108
- License
- MIT
Turn a finished or nearly finished Skill, plugin, repository, micro-tool, research utility, or AI project into a credible public launch that can earn real users and feedback. Use when the work exists but nobody outside the creator has tried it, the README is weak, the launch has no demo or proof metric, or the user wants a GitHub-first build-in-public plan without fake traction or vanity metrics.
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
# Build in Public Launcher ## Purpose Launch for evidence, not applause. This Skill turns a finished artifact into a bounded release and feedback loop without inventing adoption. ## Instructions 1. Define the exact user and painful moment the artifact addresses. 2. Audit whether the artifact is actually ready for a stranger: installation, first-run path, example input, example output, license, privacy and security notes, and failure handling. 3. Write a one-line value proposition that names the job, not the technology stack. 4. Build a launch pack using `references/launch-pack.md`. 5. Create one comparison or task-completion demo. Do not cherry-pick an impossible-to-reproduce showcase. 6. Choose one primary proof metric and one secondary distribution metric. 7. Recruit the first testers from existing communities, peers, contributors, or target-user groups. Prefer 10 relevant people over 1,000 generic impressions. 8. Ask testers to perform a task before explaining the solution. Capture confusion and failure. 9. Publish a changelog entry after each evidence-driven revision. …
Read the whole file at its exact version.
How to install
mdr add fairy123456789/human-edge-agent-skills/build-in-public-launcher@sha256:4d975b6e6c7a972dThe line at the top of this page pins the label git:20260908.449ec5c, 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_jdujjz46shurujgm)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 5, 2026 and Sep 8, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260908.449ec5c latest | 2026-09-08 | 449ec5c | 2,833 B | A | view · diff |
| git:20260905.a694da1 | 2026-09-05 | a694da1 | 1,926 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 (2833 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
fairy123456789/human-edge-agent-skills · 108 stars · license MIT · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_jdujjz46shurujgm GET https://markdownregistry.com/api/v1/resolve?ref=fairy123456789/human-edge-agent-skills/build-in-public-launcher GET https://markdownregistry.com/api/v1/blob/4d975b6e6c7a972dc61e19403f8eb842282b4b5c1263e9acab7d042c9830e6ad
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.
More from fairy123456789/human-edge-agent-skills
Every file in fairy123456789/human-edge-agent-skills