Desk Complete — Development skill for Claude Code
Bring one underlying to a complete artifact set against checkable criteria.
How to install Desk Complete
Installs to ~/.claude/commands/iman-agent-driven-options-desk-and-skills-desk-complete.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/Iman/agent-driven-options-desk-and-skills/HEAD/.claude/commands/desk-complete.md -o ~/.claude/commands/iman-agent-driven-options-desk-and-skills-desk-complete.md Restart Claude Code, or start a new session, for it to be picked up.
What Desk Complete does
description: Bring one underlying to a complete artifact set against checkable criteria. Built for goal-based loops. argument-hint: SYMBOL [EXPIRY] arguments: [symbol, expiry]
Bring the desk on $symbol to a complete state, for expiry $expiry if one was given and the nearest listed expiry beyond a week otherwise. This has a deterministic finish, which is what makes it usable with `/goal`:
/goal run /desk-complete SPY until every criterion is met, stop after 5 tries
The crite
Alternatives in Development
- Agent Game Forge — The local-first, bring-your-own-agent 2D game IDE 207 ★
- Verify — Verify frontend changes against acceptance criteria using browser agents 107 ★
- Adversarial Dev — GAN-inspired three-agent harness that pits a generator against an adversarial evaluator to build applications 97 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Desk Watch
Refresh one underlying and report only what materially changed since the last run. Built for scheduled loops.
Desk Risk
Simulate an underlying forward and compare realised volatility against implied for every structure on file
Simmer
Iterative artifact refinement using judge subagents that score against user-defined criteria across multiple r
Hackathon Judge
Evaluate a hackathon project against the official "Built with Opus 4.6" judging criteria. Scores demo, impact,
Analyzing Systemic Governance Loops 20260822
Diagnosing functional failure by interrogating underlying structural mechanics rather than observed behavior o
Waypoint Videolink App
A single static page built to open (and close) a screen-recorded demo of Waypoint — a browser-based agent that
Related Agents
Goal Planner
Decomposes a user goal into 3-10 machine-checkable acceptance criteria with real single-line shell verify comm
Scoper
Pins a task's scope: goal, boundaries, non-goals, and machine-checkable success criteria.
Story Verifier
Independently verifies a built infographic against explicit acceptance criteria, direct artifact evidence, ide