Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Dim Setup

ASecurity

Set up a fresh dim-factory clone for coding agents. Use after cloning or when the local installation is incomplete.

5 stars
0 votes
0 copies
0 views
Added 10/5/2026
researchrust

Works with

claude codecli

Security Analysis

A100/100

Scanned 10/5/2026

$npx -y skills add cniska/dim-factory --skill dim-setup --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Dim Setup?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Dim Setup
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/cniska-dim-setup/badge)](https://www.skillsdirectory.com/skills/cniska-dim-setup)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: dim-setup
description: Set up a fresh dim-factory clone for coding agents. Use after cloning or when the local installation is incomplete.
---

# Setup

Set up dim on this machine so coding agents can use its shared skills from other projects. This skill lives in the clone and runs before those skills are installed. [The agent command reference](../../../docs/usage.md) owns the command details. Doctor's observed state determines each repair; an installer exit alone does not establish readiness.

## Entry contract

Run from this repository's root. Confirm it has `package.json`, `bun.lock`, `mise.toml` and `src/cli.ts`. Read the existing installation before changing it. A rerun changes only what is missing or stale; it does not duplicate hooks, links or the sync agent.

## Bootstrap

Run `mise install` and `bun install` to bring the declared toolchain and dependencies into this clone. Resolve the executable behind `dim` on PATH, not just its link name. Run `bun link` if it does not lead to this checkout's `src/cli.ts`, then resolve it again. A different executable still winning PATH is a blocker; use `bun src/cli.ts` for diagnostics and do not install hooks under the wrong executable. Keep the committed lockfile unchanged.

Run `dim sync` to populate the local record. If it refuses a schema mismatch, run `dim rebuild`, then repeat the sync. Run `dim doctor` and read each check's state and repair, not just the command's exit.

## Repair from doctor

Use the doctor's findings to choose only the needed installers. Each writes when run, so read the paths and scope doctor names before running it:

- `dim hooks install` for Claude Code and Codex session hooks.
- `dim skills install` for dim's shared skills in the agent skill directories.
- `dim rules install` when its canonical Claude rules source exists.
- `dim agent install` on macOS when scheduled sync is wanted. Run it even when doctor says the agent is loaded, because the plist names this checkout and the installed Bun path. Its result gives the command to load the launchd agent.

On Linux, run `dim sync` manually; the launchd installer is macOS-specific.

Run an installer when setup was requested and its scope is understood. An occupied skill link is moved aside to the backup the result names; check that it pointed to a previous dim checkout, and take an unrelated occupied path or owner-specific choice to the owner. Keep configuration outside dim's planned change intact. If a loaded launchd job's plist changed, use the installer's returned remove command before its load command, then inspect the loaded job; writing the plist alone does not restart it.

Run `dim doctor` again after repairs. Codex hook trust is granted in Codex, and retention choices may need the owner; name those checks and the action they need. A warning is a stated limitation, not a passing check.

## Exit check

Setup is ready when the executable, hooks, rules and skill checks are healthy, the user's `config.json` names a model for every station role or a `default` ([configuration](../../../docs/usage.md#configuration)), and `dim-factory` resolves from the shared skill directory of each installed harness. Check the executable and skill targets from a separate project checkout; both must still lead to this clone. `dim-factory` operates an existing order id, and `dim-add` creates one from a new request. Report observational doctor failures such as insufficient session-end history separately, with the evidence needed to judge them after more sessions. If an external or owner-dependent action remains, report setup as blocked with its concrete next step. On a second run with the same inputs, the installers make no changes.

## Result

Report which controls were installed or already healthy, the final doctor result, and each unresolved check with its repair or decision. Do not claim setup is complete from a successful installer alone.

## Red flags

- calling a different `dim` from PATH
- writing machine-wide hooks before reading what doctor says they change
- treating a doctor's warning or failure as a successful installation
- concealing a trust or retention decision the owner must make

Attribution

cniskacniska
View sourceSee grades on GitHubMore from cniska →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Competitor Analysis

This skill provides comprehensive analysis of competitor SEO and GEO strategies, revealing what's working in your market and identifying opportunities to outperform the competition.

1823 votes

Deep Research

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report co...

502942 votes

Paperclip Distill

Use when an operation issue is a Paperclip cursor-window, distill, or backfill — `operationType: "distill"` or `"backfill"` and the body references a Paperclip source bundle for a project or root issue. Turn raw Paperclip activity into a wiki-insightful project page, decisions log, and history note. This skill exists specifically to replace the stiff, datestamp-heavy templated output that the deterministic distiller produces.

953191 votes

Academic Pipeline

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory, coverage-bounded integrity checks, two-stage peer review, and auditable quality-assurance artifacts. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end p...

502941 votes

Literature Review

Assistance with writing literature reviews by searching for academic sources via Semantic Scholar, OpenAlex, Crossref and PubMed APIs. Use when the user needs to find papers on a topic, get details for specific DOIs, or draft sections of a literature review with proper citations.

6511 votes
View all in research →