Create validate-review-decisions Skill#2224
Merged
Trecek merged 4 commits intoMay 8, 2026
Merged
Conversation
- Create new validate-review-decisions skill with 7 evidence-gathering rules: Rule 1: Docstring-as-contract recognition Rule 2: Deliberate-change detection Rule 3: Test-as-intent-signal Rule 4: Consumer-impact verification Rule 5: Architectural feasibility check Rule 6: Behavioral simulation Rule 7: Symmetry-as-design recognition - Add mandatory intent analysis requiring 6 techniques before verdict: docstring check, git provenance, test coverage, contract analysis, architectural constraint check, behavioral simulation - Route review-decisions validation through new specialized skill in full-audit.yaml (previously routed through generic validate-audit) - Add 33 contract tests (T-VRD-001 through T-VRD-033) - Update all test manifests and documentation Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
T-VRD-021: Remove trivial 'or "test" in text' disjunction — 'test' appears in any skill document, making the second branch always pass and the first branch dead. Assert only 'test coverage' which is the meaningful phrase being checked. T-VRD-027: Replace three separate assertions (including trivially-true 'test' in text) with a single compound assertion on 'test-as-intent-signal', the exact concept name used in SKILL.md Rule 3 (line 157).
…e-* entries in catalog Placing it on its own line between validate-test-audit and audit-claims broke the cohesive validate-* grouping in the Audit suite section.
Trecek
deleted the
create-validate-review-decisions-skill-review-decision-valid/1962
branch
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Create a new
validate-review-decisionsskill atskills_extended/validate-review-decisions/SKILL.mdthat adds mandatory intent analysis and seven evidence-gathering rules to the validation workflow for review-decisions audit reports. Updatefull-audit.yamlto route review-decisions validation through this new skill instead of the genericvalidate-audit. Add contract tests and update all test manifests.The skill follows the architecture established by
validate-test-audit(domain-specific semantic rules + intent analysis) while preserving full output compatibility withvalidate-audit(same directory, naming convention,validated: truesentinel,AUTOSKILLIT_AUDIT_RUN_DIRsupport).Requirements
REQ-VRD-1: Skill structure
The skill MUST be placed at
skills_extended/validate-review-decisions/SKILL.mdwithcategories: [audit]frontmatter.REQ-VRD-2: Intent analysis as mandatory step
Code validation subagents MUST perform intent analysis (docstring check, git provenance, test coverage, contract analysis, architectural constraint check, behavioral simulation) before assigning a verdict to ANY finding. This is not optional — every finding must have an intent analysis section in the subagent's reasoning.
REQ-VRD-3: Evidence-gathering rules in subagent instructions
The skill MUST include the seven evidence-gathering rules in the code validation subagent prompt. Rules MUST be generalizable (no references to specific finding IDs).
REQ-VRD-4: Output compatibility
Output files MUST use the same directory, naming convention, and format as
validate-audit.REQ-VRD-5: Standalone invocability
The skill MUST accept an
{audit_report_path}argument and auto-discover the most recent review-decisions audit report when omitted.REQ-VRD-6: Full-audit recipe routing
Update
full-audit.yamlto dispatch review-decisions audit validation tovalidate-review-decisionsand all other audit types tovalidate-audit(orvalidate-test-auditfor tests).REQ-VRD-7: No pack changes
The skill MUST use the existing
auditpack.REQ-VRD-8: Consider generalizing intent analysis to validate-audit (follow-up)
After
validate-review-decisionsandvalidate-test-auditboth establish intent analysis patterns, evaluate merging the common intent analysis rules back into the genericvalidate-auditskill. This is a follow-up, not a blocker.Implementation Plan
Plan file:
/home/talon/projects/autoskillit-runs/impl-20260508-010014-405487/.autoskillit/temp/make-plan/validate_review_decisions_skill_plan_2026-05-08_010600.md🤖 Generated with Claude Code via AutoSkillit
Token Usage Summary
* Step used a non-Anthropic provider; caching behavior may differ.
Token Efficiency
Model Usage Breakdown