Claude Md Slim

Use when CLAUDE.md has grown bloated and is taxing every session's context — the inverse of claude-md-improver. Triages each block into session-invariant rules (stay always-on) vs feature/subsystem detail (page out to docs/ behind a plain-path pointer), moving — never deleting — the detail so nothing is lost and the always-on token bill drops. Triggers on: slim claude.md, minimal claude.md, claude.md is bloated, shrink claude.md, split claude.md, make claude.md minimal, page out claude.md, claude.md too long, reduce project memory, point claude.md to docs, trim claude md.

5 starsAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add adelrioj/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 adelrioj/claude-skills --skill claude-md-slim
Manual install
git clone --depth 1 https://github.com/adelrioj/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/claude-md-slim ~/.claude/skills/claude-md-slim

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 Slim — Page Out the Bloat

Makes the **root `CLAUDE.md` minimal** by keeping only what every session needs
always-on and **moving everything else to `docs/`** behind one-line pointers. The
inverse objective of `claude-md-improver`: that skill's gradient points at
*completeness* (it adds), this one's points at *minimal always-on context* (it
extracts). Opposite gradients, so opposite skills — don't ask the improver to slim,
it structurally can't.

**Why this exists (the evidence).** *"Less Context, Better Agents"* (Lodha et al.,
arXiv:2606.10209) found that full always-on history hit 71% task completion at 1.48M
tokens, while **pruned + summarized** context hit 91.6% at ~553K — less always-on
context, detail retrieved on demand, is both *cheaper and more reliable*. `CLAUDE.md`
is loaded into **every** session whether or not the task touches it; it is the
always-on-history problem in miniature.

**The load-time fact that makes or breaks this.** Paging out only helps if the pointer
is loaded **lazily**:

| Mechanism | Loaded when | Reduces always-on context? |
|---|---|---|
| Prose in `CLAUDE.md` | every session, eagerly | no |
| `@path` import | every session, eagerly (expanded at load) | **no — reorganizes only** |
| Plain path reference (`see docs/x.md for X`) | on demand, when the task needs it | **yes** |

**This skill uses plain-path pointers, NEVER `@`-imports.** An `@`-import feels like
Read the full skill on GitHub

Details

Skill name
claude-md-slim
Path
skills/claude-md-slim/SKILL.md
Repo updated
24 August 2026

FAQ

What does the Claude Md Slim skill do?

Use when CLAUDE.md has grown bloated and is taxing every session's context — the inverse of claude-md-improver. Triages each block into session-invariant rules (stay always-on) vs feature/subsystem detail (page out to docs/ behind a plain-path pointer), moving — never deleting — the detail so nothing is lost and the always-on token bill drops. Triggers on: slim claude.md, minimal claude.md, claude.md is bloated, shrink claude.md, split claude.md, make claude.md minimal, page out claude.md, claude.md too long, reduce project memory, point claude.md to docs, trim claude md.

How do I install the Claude Md Slim skill?

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

Is Claude Md Slim popular?

It lives in adelrioj/claude-skills, which has 5 GitHub stars and 0 forks.

Related skills

Architect Review PR

5

adelrioj/claude-skills

Use after a feature is built — e.g. the final step of a ship-it run, right after review-pr — to check it is actually complete and wired, not just line-correct. Dispatches a fresh-context Claude subagent that traces the whole repo to hunt completeness and integration gaps in the branch's changes, reports ranked, evidence-backed findings, then fixes the CRITICAL ones and verifies with a fresh re-review (capped at 3 passes; pass report-only to skip fixing). Triggers on: architect review, architecture review, completeness review, wiring review, is this wired, did we finish this, find the gaps, inc

Git & Code Review

Blind Spot

5

adelrioj/claude-skills

Use BEFORE starting work on a task to surface the unknown-unknowns you're about to walk into but can't see. Dispatches a fresh-context Claude subagent that hunts what you don't know you don't know about the codebase, the domain, and the decisions ahead, calibrated to your stated experience, then reports ranked, evidence-backed findings and fixes nothing. Triggers on: blind spot pass, blindspot, unknown unknowns, what don't I know, what am I missing, help me prompt better, I know nothing about, teach me my unknowns, before I start, de-risk this task, surface my blind spots.

AI, LLMs & Agents

Linear Groom Ticket

5

adelrioj/claude-skills

Use when a Linear ticket needs to be made ready to work on, or judged not worth working on. Analyses one ticket across four dimensions — whether its claims hold in the code, whether it is complete against the team template, whether it duplicates another ticket, and whether it is implementable — then proposes a corrected description and applies it to Linear only after you approve. Triggers on: groom this ticket, prepare NBS-123, is this ticket ready, revisa este ticket, ¿este ticket está listo?, deja el ticket listo para trabajar, candidato a borrar, dedupe this ticket.

Software Development

Agent Discoverability

9

sandbaseai/workbuddy-skill

Use when publishing or auditing an MCP or agent endpoint so third-party agents can find it, understand its capabilities, and complete its authorized authentication flow.

AI, LLMs & Agents

Agent Document Design

9

sandbaseai/workbuddy-skill

Use when creating or editing Skills, agent instruction files, or referenced documents so triggers, steps, disclosure, completion criteria, and maintenance remain predictable.

AI, LLMs & Agents

Watch Release

9

flurdy/agent-skills

Start a recurring release-gatekeeper loop — runs /release-manager on an adaptive cadence (fast when something is in flight, backing off when settled) until end of day. Prompts to push / defer / cancel as services become ready; runs attended.

AI, LLMs & Agents

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