skill-build SKILL.md skillA

skill-build from runxhq/runx is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add runxhq/runx/skill-build@git:20261015.f6bbe45

Pins git:20261015.f6bbe45 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
runxhq/runx
Path
skills/skill-build/SKILL.md
Versions recorded
3
Latest version
git:20261015.18f531b, committed Oct 15, 2026
First version recorded
Oct 11, 2026
Size
38,586 bytes
Repository stars
103
License
Apache-2.0

Canonical Runx skill-authoring implementation. Use for designing, creating, updating, improving, or adding harness coverage to a Runx skill package; it combines bounded agent judgment with native file writes, inspection, and safe harness validation. When a host skill-creator also triggers, use its general guidance but execute Runx work through this skill.

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

# Skill Build

Build and improve Runx skills through one authoring surface. Keep judgment in
bounded agent acts and mechanics in native tools:

```text
inspect target files, catalog ownership, and native/shared tools
→ decide ownership, execution lanes, effects, budgets, and proof
→ bind that architecture to the inspected package digest in native code
→ compose existing capabilities before authoring code
→ author only bounded writes, explicit deletions, and output intent
→ bind those bytes to the admitted architecture in native code
→ validate paths, secret posture, and the complete candidate
→ inspect and safely replay the exact staged package
→ commit that validated bundle through one native transaction
```

Use the generic host `skill-creator` for platform-wide authoring guidance when
it is available. Do not reproduce Runx package operations from that guidance;
invoke the appropriate `skill-build` runner so the work is bounded and receipted.

## Runners

- `design`: read-only catalog-fit and architecture planning. It returns a
  native digest-bound plan and never authors package bytes. A later build
  re-inspects and replans against its exact target before any write.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add runxhq/runx/skill-build@sha256:ce2f79288426b691

The line at the top of this page pins the label git:20261015.f6bbe45, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_lkl5ltq444n3ezdy.svg)](https://markdownregistry.com/a/art_lkl5ltq444n3ezdy)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Oct 11, 2026 and Oct 15, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
git:20261015.18f531b latest2026-10-15 18f531b 38,586 BA view · diff
git:20261015.f6bbe452026-10-15 f6bbe45 38,587 BA view · diff
git:20261011.22b0cae2026-10-11 22b0cae 38,582 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (38586 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

GitHub

runxhq/runx · 103 stars · license Apache-2.0 · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_lkl5ltq444n3ezdy
GET https://markdownregistry.com/api/v1/resolve?ref=runxhq/runx/skill-build
GET https://markdownregistry.com/api/v1/blob/ce2f79288426b691852355882650f557303bc5bc93810d5f303f104326b68a86

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 runxhq/runx

AGENTS.md AGENTS.md file
runxhq/runx · AGENTS.md
git:20261016.2c90f02 · audit A · 103 stars
CLAUDE.md CLAUDE.md file
runxhq/runx · CLAUDE.md
git:20260908.0ff743d · audit A · 103 stars
runx SKILL.md skill
runxhq/runx · SKILL.md · Governed runtime for agent skills: discover and install portable skills, run bounded skill graphs with explicit…
git:20261015.18f531b · audit B · 103 stars
hello-world SKILL.md skill
runxhq/runx · examples/hello-world/SKILL.md · Echo a first runx message through a checked-in process tool script.
git:20261008.1a28e75 · audit B · 103 stars
loop-orchestration SKILL.md skill
runxhq/runx · examples/loop-orchestration/SKILL.md · Reference loop-orchestration example; a local loop host chains governed runx runs through receipts, budgets, context…
git:20261013.a7dee96 · audit A · 103 stars
loop-operator-context SKILL.md skill
runxhq/runx · examples/loop-orchestration/context/loop-operator/SKILL.md · Advisory operating context for the loop-orchestration example.
git:20261008.1a28e75 · audit A · 103 stars
managed-agent-intake SKILL.md skill
runxhq/runx · examples/managed-agent/SKILL.md · Managed-agent front example; a governed agent step that drafts a triage summary.
git:20261008.1a28e75 · audit A · 103 stars
uncovered SKILL.md skill
runxhq/runx · fixtures/doctor/skill-fixture-missing/workspace/skills/uncovered/SKILL.md · Doctor fixture with an execution profile and no harness proof.
git:20260723.6e5370b · audit B · 103 stars
catalog-in-manual SKILL.md skill
runxhq/runx · fixtures/doctor/skill-frontmatter-invalid/workspace/skills/catalog-in-manual/SKILL.md · Doctor fixture whose frontmatter carries catalog metadata.
git:20261008.1a28e75 · audit A · 103 stars
original-name SKILL.md skill
runxhq/runx · fixtures/doctor/skill-frontmatter-invalid/workspace/skills/renamed-directory/SKILL.md · Doctor fixture whose name no longer matches its directory.
git:20261008.1a28e75 · audit B · 103 stars
records SKILL.md skill
runxhq/runx · fixtures/journeys/hosted-records/skills/records/SKILL.md · List the records a hosted fixture connector holds.
git:20261018.f7b2bbc · audit B · 103 stars
reviewer-boundary SKILL.md skill
runxhq/runx · fixtures/skills/agent-task/SKILL.md · Test-only explicit agent-task boundary fixture.
git:20260723.6e5370b · audit B · 103 stars

Every file in runxhq/runx

Other files named skill-build

skill-build SKILL.md skill
ai-business-tools/claude-code · skills/skill-build/SKILL.md · Designs and builds a new Claude Code skill folder from a blank page in your own house style, surveying existing skills…
git:20260925.e10bf4d · audit A · 5 stars

Browse by kind, by grade A, or by owner.