skills.rest
kapilvirenahuja
kapilvirenahujaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

diff-context-baseline

Compare context baselines against implementation outcomes to classify context drift into tiered learnings.

3|Updated Jan 25, 2026
Search Tags:#SDLC#ADR#taxonomy#knowledge extraction#context diff#enterprise delivery#YAML reporting
One-click install
npx skills add https://github.com/kapilvirenahuja/garura --skill diff-context-baseline
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: diff-context-baseline
Source: https://github.com/kapilvirenahuja/garura/tree/main/core/components/skills/diff-context-baseline
Command: npx skills add https://github.com/kapilvirenahuja/garura --skill diff-context-baseline

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It resolves the ambiguity of whether an implementation followed the planned intent by comparing the prepare-time context baseline against post-epic implementation outcomes and converting divergences into structured, tiered learnings.

Core Features & Use Cases

  • Baseline vs outcome diffing: Loads context artifacts captured by prepare and compares them against milestone and optional arbiter verdict evidence from the implementation phase.
  • Tiered learning classification: Routes each meaningful divergence into Tier 1 (ADR-worthy), Tier 2 (enrichment-worthy), or Tier 3 (addition-worthy) so follow-on skills know what to propose and where it matters most.
  • Two-level KB-aligned taxonomy: Emits a learning_category + sub_category taxonomy aligned to the core memory knowledge base structure, replacing the prior single dimension approach, and produces context-diff.yaml for downstream enrichment drafting.
  • Knowledge-extractor stage workflow: Designed as the first of three knowledge-extractor skills, feeding results into draft-enrichment-proposals.

Quick Start

Use the diff-context-baseline skill to generate context-diff.yaml by diffing context_baseline_path against milestone_verdicts_paths (and optional arbiter_verdicts_paths) while writing results under output_base using stm_evidence_root for taxonomy-justified routing.

Frequently Asked Questions about diff-context-baseline

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I classify context drift between planned software design and actual implementation outcomes?▼

Classify context drift by comparing the prepare-time context baseline against post-epic implementation outcomes, routing divergences into ADR-worthy, enrichment-worthy, or addition-worthy tiers for downstream proposals.

What is the best way to generate a structured YAML report for enterprise delivery learnings?▼

Generate structured YAML reporting by diffing context baselines against milestone verdicts and arbiter evidence, enforcing a two-level taxonomy aligned to core components, and writing results to a context-diff.yaml file.

How do I track architecture decisions and knowledge extraction across an epic-level software delivery review?▼

Track architecture decisions by evaluating changed artifacts, libraries, patterns, and enforced invariants during epic-level reviews, converting meaningful divergences into tiered learnings for downstream knowledge extraction proposals.

Do I need baseline and arbiter verdict inputs to enforce deterministic output for context diffing?▼

Yes, deterministic output requires baseline and verdict inputs, optionally including arbiter evidence, to justify the taxonomy routing and accurately classify divergences into structured learning categories.

Can I use a single-level taxonomy for routing context drift into a knowledge base?▼

No, you must use a two-level learning_category and sub_category taxonomy aligned to the core memory knowledge base structure, replacing the prior single dimension approach, to properly route findings.

Related Skills

Explore More Software Engineering Skills→
OceanEyeFFOceanEyeFF
29

repo-status-skill

Summarize repository baseline, branches, and milestone context from standard artifacts.

Community
Advanced
lshtramlshtram

context-management

Automates token and memory organization with tiered context management.

Community
Advanced
kapilvirenahujakapilvirenahuja
3

normalize-proposals-for-enrichment

Normalize extractor-specific proposals.yaml into reconciliation-proposals.yaml with taxonomy validation.

Community
Advanced
jeremylongshorejeremylongshore
2.6k

detecting-infrastructure-drift

Detect infrastructure drift between current state and desired configuration.

Community
Advanced