Condense

Deduplicate and consolidate CLAUDE.md memory files. Trigger when user says "condense my CLAUDE.md files", "deduplicate CLAUDE.md", "clean up my memory files", or "consolidate my instructions". Removes redundancy within files and across the file hierarchy.

42 stars 2 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add robbyt/claude-skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add robbyt/claude-skills --skill condense
Manual install
git clone --depth 1 https://github.com/robbyt/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/plugins/claude-md/skills/condense ~/.claude/skills/condense

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

From the SKILL.md

# CLAUDE.md Condensation

Deduplicate and consolidate CLAUDE.md memory files to remove redundancy.

## Workflow

### Phase 1: Discovery

**Find all CLAUDE.md files:**
```bash
python ../reflect/scripts/find_claude_md.py
```

**Read all discovered files and analyze for:**
1. Intra-file duplication (same instruction repeated within a file)
2. Cross-file duplication (same instruction in multiple files)
3. Misplaced instructions (subdirectory files containing project-wide content)

### Phase 2: Analysis

**Intra-file duplication:**
- Identify repeated bullet points or instructions
- Find semantically similar content (different wording, same meaning)

**Cross-file duplication:**
- Root CLAUDE.md should contain project-wide instructions
- Subdirectory CLAUDE.md should only contain directory-specific instructions
- If an instruction appears in both root and subdirectory, keep only in root
- If an instruction in subdirectory applies to whole project, move to root

**Misplaced instructions:**
- Subdirectory file contains instructions that apply project-wide → move to root
- Root file contains instructions only relevant to one directory → move to subdirectory

### Phase 3: Interaction

Present findings using AskUserQuestion with checkboxes.

**For each issue found:**
1. Show the duplicated or misplaced content
2. Identify which files are affected
3. Propose the consolidation (delete, move, or merge)

**Example:**
Read the full skill on GitHub

Details

Skill name
condense
Path
plugins/claude-md/skills/condense/SKILL.md
Repo updated
18 November 2026

FAQ

What does the Condense skill do?

Deduplicate and consolidate CLAUDE.md memory files. Trigger when user says "condense my CLAUDE.md files", "deduplicate CLAUDE.md", "clean up my memory files", or "consolidate my instructions". Removes redundancy within files and across the file hierarchy.

How do I install the Condense skill?

Claude Code plugin: /plugin marketplace add robbyt/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Condense popular?

It lives in robbyt/claude-skills, which has 42 GitHub stars and 2 forks.

Related skills

Actions

42

robbyt/claude-skills

GitHub Actions workflow management using GitHub CLI. Trigger when user wants to check CI status ("check CI", "is the build passing"), view workflow runs ("show recent runs", "view action logs"), watch running workflows ("watch CI"), or rerun failed workflows ("rerun the build").

Productivity & Notes

Adversarial Review

42

robbyt/claude-skills

Have Codex try to break a change before it ships — a skeptical review that challenges the design, assumptions, and failure modes of a diff or branch and returns structured findings (verdict, severity, file:line, confidence). Trigger on "adversarial review", "challenge this change/design with Codex", "pressure-test this before I ship", "have Codex try to break this", "is this safe to merge", or a review focused on a risk area (auth, data loss, rollback, race conditions, retries). Do NOT use for a routine bug/style pass over a diff (that's diff-review), for critiquing a plan before code exists (

Software Development

API Review

42

robbyt/claude-skills

This skill should be used when reviewing API designs, auditing REST or gRPC endpoints, designing backend APIs, evaluating BFF architecture, or discussing API best practices. Also triggers on: "review this API", "API design review", "is this API correct", "REST API audit", "gRPC API review", "PATCH vs PUT", "etag", "idempotency", "pagination design", "API error handling", "backward compatibility", "BFF architecture", "resource-oriented design", "TOCTOU", "race condition", "optimistic concurrency", "field mask", "long-running operation", "custom method", "soft delete", "API naming conventions",

Software Development

Plan Review

42

robbyt/claude-skills

Get Google Antigravity's (`agy`) review of Claude's implementation plans. Trigger when user wants a second opinion on a plan ("have agy review this plan", "get a second opinion from Google Antigravity", "critique this plan with agy"), or after Claude creates a plan file that needs validation before implementation. Replaces the deprecated gemini-cli plan-review workflow.

AI, LLMs & Agents

Review Panel

37

iamneilroberts/claude-skills

Run multiple independent code reviewers (Codex + Gemini + a fresh Claude) on the current diff or a plan, merge their structured verdicts, and apply a consensus-gated challenge round — returning a pass/fail exit code. Use for "panel review this", "get a multi-model review before I ship", "second-opinion review this diff", or /review-panel. Complements single-reviewer /codex-review.

AI, LLMs & Agents

Plan Review

42

robbyt/claude-skills

Get Codex's review of an implementation plan before the user starts building — trigger when they want Codex (or a named GPT model like gpt-6.2-sol) to review, critique, or pressure-test a plan. Applies to any plan-shaped artifact — a plan file, plan-mode plan, a migration/rearchitecture/integration/checkout write-up, or a doc describing how they intend to do something (pasted, at a repo path, or just described). Fire on any second-opinion phrasing — "poke holes in it", "sanity-check my plan", "run this past Codex", "get Codex's take", "flag the biggest risks", "look this over before I start",

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.