composition-validate SKILL.md skillA

composition-validate from jmagly/aiwg is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jmagly/aiwg/composition-validate@git:20260822.b3a31c0

Pins git:20260822.b3a31c0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jmagly/aiwg
Path
agentic/code/addons/composition-engine/skills/composition-validate/SKILL.md
Versions recorded
1
Latest version
git:20260822.b3a31c0, committed Aug 22, 2026
Size
1,571 bytes
Repository stars
229
License
MIT

Validate a Flow graph manifest, explain semantic diagnostics, and emit one provider-neutral normalized composition contract.

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

# Validate a Flow graph

Use this skill when an operator needs to author or validate
**flow.aiwg.io/v1alpha1 FlowGraph**.

## Process

1. Confirm the manifest uses **apiVersion: flow.aiwg.io/v1alpha1** and
   **kind: FlowGraph**.
2. Run **aiwg composition validate MANIFEST --format json**.
3. When an AIWG index export is available, add **--catalog INDEX.json** so
   stable candidate IDs are proven against that captured catalog.
4. Repair every error diagnostic. Do not weaken permissions, ceilings,
   approval boundaries, retry modes, or cycle guards merely to pass validation.
5. Pass the returned normalized envelope to an adapter or runtime. Do not add
   provider-specific fields to the source graph.

## Contract rules

- Every non-gate node resolves through the authorized candidate set.
- Every cycle has a CEL guard and finite iteration limit.
- Node permissions are a subset of both graph and declared-capability scopes.
- Approval-required side effects are never automatically retried.
- Trace policy covers declared execution metadata and bindings, never private
  chain-of-thought.

See **schemas/flow-graph.schema.json**, **README.md**, and
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jmagly/aiwg/composition-validate@sha256:52326ab02e7e4fc3

The line at the top of this page pins the label git:20260822.b3a31c0, 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_5vssycw2ioate7h3.svg)](https://markdownregistry.com/a/art_5vssycw2ioate7h3)

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

Versions

The registry has recorded 1 version of this file, committed on Aug 22, 2026.

versioncommittedcommitsizeaudit
git:20260822.b3a31c0 latest2026-08-22 b3a31c0 1,571 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 (1571 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

jmagly/aiwg · 229 stars · license MIT · pushed 2026-11-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_5vssycw2ioate7h3
GET https://markdownregistry.com/api/v1/resolve?ref=jmagly/aiwg/composition-validate
GET https://markdownregistry.com/api/v1/blob/52326ab02e7e4fc3ca6de54f1afc93e8f87269b60d06544136d0b591b9d063fd

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 jmagly/aiwg

AGENTS.md AGENTS.md file
jmagly/aiwg · AGENTS.md
git:20261106.8df3a09 · audit A · 229 stars
CLAUDE.md CLAUDE.md file
jmagly/aiwg · CLAUDE.md
git:20261029.5a19a2d · audit A · 229 stars
agent-loop-ext SKILL.md skill
jmagly/aiwg · agentic/code/addons/agent-loop/skills/agent-loop-ext/SKILL.md · Crash-resilient external agent loop with state persistence and CI/CD integration
git:20261028.1b612a5 · audit A · 229 stars
agent-loop SKILL.md skill
jmagly/aiwg · agentic/code/addons/agent-loop/skills/agent-loop/SKILL.md · Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
v3.1.0 · audit A · 229 stars
auto-test-execution SKILL.md skill
jmagly/aiwg · agentic/code/addons/agent-loop/skills/auto-test-execution/SKILL.md · Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
git:20260913.7be8bcf · audit A · 229 stars
cross-task-learner SKILL.md skill
jmagly/aiwg · agentic/code/addons/agent-loop/skills/cross-task-learner/SKILL.md · Enable agent loops to learn from similar past tasks and share patterns across loops
v2.0.0 · audit A · 229 stars
debug-memory SKILL.md skill
jmagly/aiwg · agentic/code/addons/agent-loop/skills/debug-memory/SKILL.md · Query and manage the executable feedback debug memory
git:20261028.1b612a5 · audit A · 229 stars
execute-feedback SKILL.md skill
jmagly/aiwg · agentic/code/addons/agent-loop/skills/execute-feedback/SKILL.md · Execute tests on generated code and iterate until passing
git:20260913.7be8bcf · audit A · 229 stars
infer-completion-criteria SKILL.md skill
jmagly/aiwg · agentic/code/addons/agent-loop/skills/infer-completion-criteria/SKILL.md · Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user…
git:20261028.1b612a5 · audit A · 229 stars
mission-control SKILL.md skill
jmagly/aiwg · agentic/code/addons/agent-loop/skills/mission-control/SKILL.md · Orchestrate multi-loop background operations via the Mission Control dashboard — start sessions, dispatch missions…
git:20260710.9fe5af0 · audit A · 229 stars
ralph-abort SKILL.md skill
jmagly/aiwg · agentic/code/addons/agent-loop/skills/ralph-abort/SKILL.md · Abort a running agent loop and optionally revert changes
git:20261028.1b612a5 · audit A · 229 stars
ralph-analytics SKILL.md skill
jmagly/aiwg · agentic/code/addons/agent-loop/skills/ralph-analytics/SKILL.md · Show analytics and metrics from agent loop execution history
git:20260913.7be8bcf · audit A · 229 stars

Every file in jmagly/aiwg

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