contract-validate

Contract Validate Skill

Validate a skill chain before running it — check that every requires: input is satisfied by an upstream ensures: output or declared as an external input.

Triggers

• "validate the contract chain for [skill1] → [skill2]"
• "check if this workflow is wired correctly"
• "will [skill] have everything it needs?"
• "pre-flight check the skill chain"
• "validate workflow contracts"

Parameters

Skills list (positional)

Ordered list of skill names to validate as a chain:

/contract-validate issue-planner address-issues
/contract-validate prose-detect prose-run

--workflow <file> (optional)

Path to a YAML workflow definition listing the skill chain.

--external input1,input2 (optional)

Comma-separated names of inputs that will be provided by the calling workflow or user. Any requires: that matches an external input is treated as satisfied.

/contract-validate issue-planner address-issues --external objective,tracker

--strict (optional)

Treat semantic matches as failures (require exact name matches). Default: semantic matches pass with warnings.

Behavior

Step 1: Resolve and Extract Contracts

Same as contract-manifest Step 1–2: resolve each skill, extract contract fields.

Step 2: Validate Each Requires:

For each skill's requires: entry:

1. Satisfied by external input (--external list) → ✓ SATISFIED (external)
2. Satisfied by exact match (upstream ensures: same name) → ✓ SATISFIED
3. Satisfied by semantic match (upstream ensures: same meaning, different name) → ⚠️ WARN (semantic)
4. Not satisfied (nothing provides it) → ❌ UNRESOLVED

Step 3: Determine Verdict

Condition	Verdict
All requires: satisfied (exact or external)	VALID
All requires: satisfied but some are semantic matches	VALID WITH WARNINGS
Any requires: unresolved	INVALID
No contract fields found on any skill	NO CONTRACTS (cannot validate)

Step 4: Output Report

## Contract Validation Report

**Workflow**: issue-planner → address-issues
**Verdict**: VALID WITH WARNINGS

### Skill: issue-planner
| Requires | Source | Status |
|----------|--------|--------|
| objective | external | ✓ satisfied (external) |
| tracker | external | ✓ satisfied (external) |

### Skill: address-issues
| Requires | Source | Status |
|----------|--------|--------|
| issues | issue-planner.issues-filed | ⚠️ semantic match (name differs — verify intent) |
| tracker | issue-planner.tracker | ✓ satisfied (exact match) |

### Warnings (1)
- `address-issues.requires.issues` satisfied by `issue-planner.ensures.issues-filed` via semantic match.
  If these are not equivalent, rename one to match or add an explicit mapping.

### Errors (0)
None

### Recommendation
Workflow is likely correct. Confirm that `issue-planner.issues-filed` and `address-issues.issues` refer to the same thing. If so, rename one for an exact match to eliminate the warning.

Using in CI / Pre-Flight

Before running a multi-skill orchestration, validate the chain:

/contract-validate issue-planner address-issues --external objective tracker
# → VALID — safe to proceed
# → INVALID — check report before running

Relationship to contract-manifest

• contract-manifest — generates a full manifest for human inspection
• contract-validate — gives a pass/fail verdict for pre-flight checks

Use contract-manifest to understand a workflow; use contract-validate to gate its execution.

Model

Runs on Sonnet — contract matching is structural analysis, not complex reasoning.

References

• @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/README.md — SDLC framework context and skill catalog
• @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/vague-discretion.md — Measurable validation verdicts and criteria
• @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/research-before-decision.md — Research-first for contract dependency resolution
• @$AIWG_ROOT/docs/extensions/overview.md — Extension system and skill architecture
• @$AIWG_ROOT/docs/cli-reference.md — CLI reference