This is a forcing function for deliberate engineering decisions when your first instinct might be expensive to get wrong. It fires autonomously on mechanical triggers like a fix failing twice, adding a dependency, schema design, or changing a public API. The core mechanism refuses premature collapse: instead of greedy-decoding to the obvious solution, you hold multiple branches open (the urge, the contrarian, synthesis, out-of-box moves, precedent, first principles), ground each in real evidence from the codebase or docs, walk forward through consequences, then deliberately choose and try to refute the winner before acting. It logs decisions and rejected branches to docs/decision_logs/. Expensive on purpose, so not for routine calls. A decision worth more than one forward pass.

GitHub stars
298
last updated
Jun 11, 2026

Install

$ npx -y skills add syahiidkamil/software-engineer-ai-agent-atlas --skill free-will --agent claude-code

Installs into .claude/skills of the current project.

Files

Free Will — Deliberate Choice, Against the Urge

Most turns I answer from the urge: the default next-token pull, the single most-probable continuation given pretraining. In engineering terms, that's the first plausible design that comes to mind — the obvious library, the familiar pattern, the fix that worked last time. Usually that's fine and fast. But the first plausible design is often the one you regret in month three, and some forks are worth more than one forward pass. This skill is the procedure for choosing instead of being run.

It is expensive on purpose — it spends real test-time compute to branch, ground, simulate, and choose. So it is not the default; constant deliberation is its own pathology (analysis paralysis).

When it fires — autonomously

I invoke this skill myself, the moment a fork fits — I never wait for the partner to ask for it. In fully autonomous work (one-shotting an app, long unattended runs) nobody is watching to say "slow down here"; the trigger discipline is mine. Noticing forks is itself a judgment the fast path can fumble, so the primary triggers are mechanical — countable events, not vibes:

Sponsors

Details

Repository
github.com/syahiidkamil/software-engineer-ai-agent-atlas
Categories
Backend & APIs, Git & Pull Requests, Documentation, Code Review & Quality, AI & Agent Building, Debugging, Productivity & Planning, Design & UI/UX
First seen
Jun 11, 2026

More from syahiidkamil/software-engineer-ai-agent-atlas

All 17
1telagod avataranalyzing-spreadsheetstelagod/code-abyssProcesses Excel spreadsheet files (.xlsx, .xlsm, .csv). Creates workbooks, builds formulas, preserves formatting, analyzes tabular data, and validates financial0skills.sh installs
2telagod avatarautomating-devopstelagod/code-abyssDevOps knowledge reference covering Git workflows, testing strategies, DevSecOps, release pipeline orchestration (release.yml, multi-arch images, cosign integra0skills.sh installs
3telagod avataroperating-kicad-edatelagod/code-abyssKiCad EDA orchestration via kicad-mcp MCP server. Routes 17 tools for schematic creation, PCB layout, autorouting, DRC, and Gerber export. Enforces serialized P0skills.sh installs
4TencentCloudBase avatarmcp-attribution-worktreeTencentCloudBase/CloudBase-AI-ToolkitTriage, repair, and close MCP attribution issues from the local report API with evidence-driven decisions and isolated Worktrunk worktrees. Use this skill when 0skills.sh installs
5tidyverse avatarsql-translationtidyverse/dbplyrGuide for adding SQL function translations to dbplyr backends. Use when implementing new database-specific R-to-SQL translations for functions like string manip0skills.sh installs
6Trevoke avatarqaTrevoke/org-gtd.elThis is adversarial testing that actually writes and runs code instead of theorizing about edge cases.0skills.sh installs