dia-agent
Drive the operator's real logged-in Dia: cc-dia-act for the agent's own window (Accessibility read on any site; click and type only on operator-listed hosts)…
Skill by renchris
Chalk Labs
Need help deploying dia-agent?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/renchris-dia-agent
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/dia-agent
Tools it pre-approves 2
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash,Read
What's inside
- Skill name
dia-agent- Description
- Drive the operator's real logged-in Dia: cc-dia-act for the agent's own window (Accessibility read on any site; click and type only on operator-listed hosts), AppleScript for tabs and windows, CDP via dia://inspect, a clean-profile launcher.
- License
- unknown
- Allowed tools
- Bash,, Read
- Instructions
- 415 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
- Instructions call the network
- Instructions read files in your home folder (~/.ssh, ~/.aws…)
Files (2)
- SKILL.md
- cc-dia-act-ax.swift
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from renchris/claude-infrastructure
- 0.584score
frontend-design-vue
renchris
Redesign a Vue 3 app into a modern SaaS-style interface: vertical sidebar navigation, design-token CSS architecture, Signal-aesthetic defaults.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
cc-upgrade
renchris
Upgrade Claude Code for a new model, a CC release or harness feature, or both: registration probe, CHANGELOG HOLD/ADVANCE, headless gate, activation…
SkillAFreshness: A★ 1Claude Code - 0.579score
frontier-hole
renchris
Log an unknown-unknown (a "frontier hole") to FRONTIER_HOLES.md for the frontier model without spending frontier tokens.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
agent-browser
renchris
agent-browser CLI for browser automation: navigate, click, fill forms, take screenshots, test web apps and extract page data.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
codex-security
renchris
Run OpenAI's Codex Security methodology natively (vendored plugin; no Codex or OpenAI account): repo and diff security scans, threat models, finding…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
coding-standards
renchris
House style for TypeScript, React/Next.js and Python (FastAPI, Pydantic v2, mypy strict, ruff): strictness, exports, Server Components, naming.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
frontier-campaign
renchris
Curate and run a long-horizon frontier campaign: one generator-class problem (a fix that dissolves 3+ worklist items) with Fable as architect and judge over…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
frontier-run
renchris
Spend the frontier (Fable) window on unknown-unknown discovery: baseline-blind derivation panels over the FRONTIER_HOLES ledger or a seam sweep.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
autonomous-authenticated-web-access
renchris
Choose and run read-only access to a logged-in web app: API token, then clean-profile CDP, then warm Dia CDP; plus trusted-input, shadow-DOM and consent-modal…
SkillAFreshness: A★ 1Claude Code +9 - 0.575score
agent-teams
renchris
Orchestrating code-writing teammates (Agent with name:): runtime detection, 150-line brief rules, pre-spawn checklist, model and effort pinning, lifecycle…
SkillAFreshness: A★ 1Claude Code +9 - 0.575score
browsermcp
renchris
History of the retired BrowserMCP server plus the browser-automation decision tree; the agent-browser CLI is the live path.
SkillAFreshness: A★ 1Claude Code +9 - 0.571score
cc-upgrade-gate
renchris
Renamed: now /cc-upgrade (gate phase).
SkillAFreshness: A★ 1Claude Code
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 19, 2026 (12 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from renchris
- 0.584score
frontend-design-vue
renchris
Redesign a Vue 3 app into a modern SaaS-style interface: vertical sidebar navigation, design-token CSS architecture, Signal-aesthetic defaults.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
cc-upgrade
renchris
Upgrade Claude Code for a new model, a CC release or harness feature, or both: registration probe, CHANGELOG HOLD/ADVANCE, headless gate, activation…
SkillAFreshness: A★ 1Claude Code - 0.579score
coding-standards
renchris
House style for TypeScript, React/Next.js and Python (FastAPI, Pydantic v2, mypy strict, ruff): strictness, exports, Server Components, naming.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
agent-browser
renchris
agent-browser CLI for browser automation: navigate, click, fill forms, take screenshots, test web apps and extract page data.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
codex-security
renchris
Run OpenAI's Codex Security methodology natively (vendored plugin; no Codex or OpenAI account): repo and diff security scans, threat models, finding…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
frontier-campaign
renchris
Curate and run a long-horizon frontier campaign: one generator-class problem (a fix that dissolves 3+ worklist items) with Fable as architect and judge over…
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get dia-agent running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
dia-agent skill. Agent Mart. https://agentmart.dev/skills/renchris-dia-agent (last updated 2026-10-24)