Skills extend-signal-schema
📦

extend-signal-schema

Safe

Extend AFI Signal Schemas Safely

Schema changes can break validators, downstream types, and migration paths. This skill guides Claude, Codex, and Claude Code through scoped AFI signal schema updates with tests and governance checks.

Supports: Claude Codex Code(CC)
🥈 80 Silver
1

Download the skill ZIP

2

Upload in Claude

Go to Settings → Capabilities → Skills → Upload skill

3

Toggle on and start using

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/afi-protocol-extend-signal-schema.md Signed manifest GET /api/skills/afi-protocol-extend-signal-schema/manifest Signed lockfile GET /api/skills/afi-protocol-extend-signal-schema/lockfile

Test it

Using "extend-signal-schema". Request to add an optional macro regime field to Enriched signals.

Expected outcome:

A short implementation summary naming the lifecycle stage, field type, optional status, changed schema and test files, passing build results, and compatibility notes.

Using "extend-signal-schema". Request to add PoInsight as a signal field.

Expected outcome:

A refusal to implement the change, with an explanation that PoI and PoInsight belong at the validator level and require human escalation.

Using "extend-signal-schema". Request to make a currently optional field required.

Expected outcome:

A migration plan using an optional-first approach or a safe default, plus tests and open questions for maintainers.

Security Audit

Safe
v6 • 6/28/2026

Static analysis reported many high-risk patterns, but review found they are false positives caused by Markdown inline code, documentation examples, and ordinary words such as description. The skill is a procedural guide for schema changes and contains no executable script, no prompt injection attempt, no credential handling, and no data exfiltration behavior.

1
Files scanned
376
Lines analyzed
3
findings
6
Total audits
Low Risk Issues (3)
SKILL.md:24SKILL.md:89-92SKILL.md:203-207SKILL.md:278-291
False Positive: Markdown Backtick Text Flagged as Command Execution
Static analysis flagged many inline Markdown backtick spans as Ruby or shell backtick execution. These lines document filenames, schema fields, and example commands inside SKILL.md; they are not executable code and do not create command injection risk.
SKILL.md:3-6SKILL.md:59SKILL.md:252-259SKILL.md:299
False Positive: Weak Cryptography Pattern From Plain Text
Static analysis flagged weak cryptography at lines containing prose such as frontmatter description and summary text. No hash, cipher, encryption library, or cryptographic operation appears in the reviewed SKILL.md context.
SKILL.md:20SKILL.md:35-37SKILL.md:172-173SKILL.md:346SKILL.md:366
False Positive: Reconnaissance Terms Are Repository Guidance
Static analysis flagged system and network reconnaissance patterns, but the cited lines instruct the user to read governance files, inspect target schemas, avoid nondeterminism, or avoid external APIs. The skill does not collect host, network, or environment information.
Audited by: codex View Audit History →

Quality Score

55
Architecture
100
Maintainability
87
Content
71
Community
99
Security
83
Spec Compliance

What You Can Build

Add Optional Signal Metadata

Add a backwards-compatible field to an Enriched or Analyzed signal schema with validation and tests.

Review Required Field Changes

Plan a required field change with defaults, migration notes, and explicit approval points.

Keep Validators Aligned

Update schema-adjacent validators and exported types after a schema shape changes.

Try These Prompts

Add a Simple Optional Field 
Add an optional field to the Enriched signal schema. The field name is macro_regime, the values are risk_on, risk_off, and neutral, and it should remain backwards compatible.
Refine an Existing Field 
Refine the action field validation for Scored signals. Keep existing values working, add close and reduce, update tests, and explain any compatibility impact.
Add a Nested Risk Object 
Extend the Scored signal schema with an optional risk_breakdown object containing market_risk, liquidity_risk, and execution_risk scores. Add validator checks and focused tests.
Plan a Breaking Migration 
Evaluate making content required across all signal lifecycle stages. Propose a migration-safe implementation, identify approval points, and do not edit files until the plan is confirmed.

Best Practices

  • Start by confirming the lifecycle stage, field shape, optionality, and migration impact.
  • Prefer optional fields or defaults when existing data may lack the new field.
  • Run the build and focused schema tests before reporting the change as complete.

Avoid

  • Do not add PoI or PoInsight as signal-level fields.
  • Do not change orchestration, token economics, deployment, or agent runtime code through this skill.
  • Do not remove or rename existing fields without an approved migration path.

Frequently Asked Questions

What repository area does this skill target?
It targets afi-core signal schemas, related validators, exported types, and tests.
Can it add fields to Raw, Enriched, Analyzed, and Scored signals?
Yes. The request should identify the lifecycle stage and field purpose before edits begin.
Does it support breaking schema changes?
It can plan them, but it requires clear migration guidance and human approval before risky edits.
Can it modify PoI or PoInsight fields?
No. The skill explicitly treats PoI and PoInsight as validator-level traits, not signal fields.
What verification does it expect?
It expects a build and relevant tests, such as schema or validator tests, when they exist.
Is this skill safe to publish?
Yes. Security review found documentation-only false positives and no executable malicious behavior.

Developer Details

License

MIT

Repository

https://github.com/AFI-Protocol/afi-core/tree/main/.factory/skills/extend-signal-schema

Ref

main

File structure

📄 SKILL.md