Rectify

Deep investigation of test gaps and architectural weaknesses following an investigation, then devise a plan for architectural immunity rather than direct fixes. Use when user says "rectify", "rectify this", or wants to address root architectural causes after an investigation.

5 stars 1 forksFinance & Crypto

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add TalonT-Org/AutoSkillit --skill rectify
Manual install
git clone --depth 1 https://github.com/TalonT-Org/AutoSkillit.git /tmp/AutoSkillit
mkdir -p ~/.claude/skills
cp -r /tmp/AutoSkillit/src/autoskillit/skills_extended/rectify ~/.claude/skills/rectify

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Rectify Skill

Based on your investigation report, use subagents to investigate further how our tests missed this and if there are any other similar or related bugs. Walk over the codebase carefully.

Then devise a plan to resolve these issues. No bandaids, fallbacks, or other approaches that just fix the direct exact issue.

The approach should make it so the architecture, structure and/or pattern is innately immune to the issue in the first place and/or results in the issue being easily and instantly surfaced as an error caught by testing.

Explore the architecture of the systems involved very carefully and map the components they connect to with subagents.

Find what the architectural solution would be instead of just applying a direct fix to the immediate issue. The solution should solve more than just the issue at hand.

Do not change any code.

## When to Use

- After an investigation has been completed (usually via the `/autoskillit:investigate` skill)
- User says "rectify", "rectify this", or "address root cause"
- User wants to understand why tests missed something and how to prevent it architecturally

## Critical Constraints

**NEVER:**
- Modify any source code files
- Propose bandaid fixes, fallbacks, or direct-only fixes
- Suggest backward compatibility shims
- Create files outside `{{AUTOSKILLIT_TEMP}}/rectify/` directory
- Run subagents in the background (`run_in_background: true` is prohibited)

**ALWAYS:**
- Use subagents for parallel exploration
Read the full skill on GitHub

Details

Skill name
rectify
Path
src/autoskillit/skills_extended/rectify/SKILL.md
License
MIT
Repo updated
8 November 2026

FAQ

What does the Rectify skill do?

Deep investigation of test gaps and architectural weaknesses following an investigation, then devise a plan for architectural immunity rather than direct fixes. Use when user says "rectify", "rectify this", or wants to address root architectural causes after an investigation.

How do I install the Rectify skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add TalonT-Org/AutoSkillit --skill rectify. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Rectify popular?

It lives in TalonT-Org/AutoSkillit, which has 5 GitHub stars and 1 forks.

Related skills

Analyze Prs

5

TalonT-Org/AutoSkillit

Analyze all open PRs targeting a base branch — determine merge order, identify file overlaps, and tag each PR as simple or needs_check for complexity. Use at the start of a PR consolidation workflow.

Git & Code Review

Arch Lens C4 Container

5

TalonT-Org/AutoSkillit

Create C4 Container architecture diagram showing static structure, building blocks, and technology choices. Anatomical lens answering "How is it built?

Software Development

Arch Lens Concurrency

5

TalonT-Org/AutoSkillit

Create Concurrency architecture diagram showing parallel execution patterns, thread pools, synchronization, and barriers. Physiological lens answering "How does parallelism work?

Software Development

Report Bug

5

TalonT-Org/AutoSkillit

Investigate a bug from provided error context, write a structured markdown report to the given path, and output a deduplication fingerprint. Lightweight — no parallel subagents.

Finance & Crypto

Investigate

5

TalonT-Org/AutoSkillit

Deep investigation of errors, bugs, or codebase questions without making any code changes. Use when user mentions investigate, understand, explore, analyze, or pastes error tracebacks. Spawns parallel subagents for comprehensive exploration.

Finance & Crypto

20 Andruia Niche Intelligence

5

lucaspmarie-a11y/claude-skills-vault

Estratega de Inteligencia de Dominio de Andru.ia. Analiza el nicho específico de un proyecto para inyectar conocimientos, regulaciones y estándares únicos del sector. Actívalo tras definir el nicho.

Finance & Crypto

Browse the most popular Claude skills, all finance & crypto skills, or write your own with the skills generator.