digital-brain

An agent skill by muratcankoylan, from muratcankoylan/Agent-Skills-for-Context-Engineering. Tags: automation, brainstorming, office, product-strategy, social-listening.

What it does

This skill should be used for personal operating-system workflows: content creation, voice consistency, relationship lookup, meeting preparation, weekly review, goal tracking, personal brand management, and network management.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill digital-brain

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering
cp -r Agent-Skills-for-Context-Engineering/examples/digital-brain-skill ~/.claude/skills/digital-brain

Safety box score

Grade C, moderate risk: 28 of 100 risk points, rated 2026-10-21. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

Digital Brain is a local personal-OS skill for content drafting, relationship tracking, and weekly review. Its main risks are local file mutation and a destructive installer; it does not contain remote execution, network exfiltration, or secret-handling logic.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	2 (moderate)	It ships runnable shell/Python tooling (`scripts/install.sh`, `agents/scripts/weekly_review.py`, `content_ideas.py`, `stale_contacts.py`, `idea_to_draft.py`) that the agent can execute locally.
Network access	0 (none)	There are documentation links and install examples, but no runtime code that fetches remote content or sends data to external hosts.
Filesystem reach	2 (moderate)	The installer writes outside the project into `~/.claude/skills/` and can replace an existing target directory; the skill also reads/writes multiple project data files.
Secrets & credentials	0 (none)	It handles personal notes and contacts, but nothing in the shipped files touches passwords, API keys, keychains, `.env` files, browser sessions, or CLI logins.
Privilege & persistence	1 (low)	Installation affects the user’s Claude skills directory (`~/.claude/skills/`) but there is no `sudo`, service registration, or system-wide privilege change.
Instruction hijack surface	1 (low)	The templates contain hidden HTML comments such as `<!-- First tweet - must stop the scroll -->` and `<!-- Must work before "see more" click -->`, which can steer output in ways a rendered reader might miss.
Irreversible actions	1 (low)	It is designed to generate posts, replies, meeting briefs, and interaction logs on the user’s behalf, but it does not automatically publish, send, or delete anything.
Transparency	0 (none)	All shipped scripts and prompts are plain text; there are no binaries, minified blobs, or runtime-downloaded installers.

Before installing

Read `scripts/install.sh`; it can `rm -rf` an existing target directory.
Prefer installing to `./.claude/skills/digital-brain` first, not `~/.claude/skills/`.
Inspect `agents/scripts/*.py` to confirm you’re comfortable with local reads/writes to `content/`, `network/`, and `operations/`.
Fill in `identity/voice.md` and `identity/brand.md` before using it to draft public content.

Rated 2026-10-21 by an automated review of 38 files from the skill's repository.

Source

Repository: muratcankoylan/Agent-Skills-for-Context-Engineering (all skills from this repository)
Path: examples/digital-brain-skill/SKILL.md
Branch: main
Updated: 2026-09-19

brainstorm-experiments-existing — Design experiments to test assumptions for an existing product — prototypes, A/B tests, spikes, and other low-effort validation methods.
free-tools — When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness.
goal-prompt — Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex.
advanced-evaluation — This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration.
long-horizon-prompting — This skill should be used when writing, enhancing.
multi-agent-patterns — This skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit handoffs.