furkansarikaya/proofline
No evidence, no claim. A deterministic engineering team for coding agents: a task is not done until scripts have checked the evidence, whatever the model says. For Claude Code and Codex.
stack: JavaScript
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit furkansarikaya/proofline/skills ./rig-proofline/skills MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit furkansarikaya/proofline/skills/api-design .claude/skills/api-design $ npx degit furkansarikaya/proofline/skills/concurrency-proof .claude/skills/concurrency-proof $ npx degit furkansarikaya/proofline/skills/contract-proof .claude/skills/contract-proof $ npx degit furkansarikaya/proofline/skills/data-design .claude/skills/data-design $ npx degit furkansarikaya/proofline/skills/debug-proof .claude/skills/debug-proof $ npx degit furkansarikaya/proofline/skills/design-sync .claude/skills/design-sync $ npx degit furkansarikaya/proofline/skills/docs-writer .claude/skills/docs-writer $ npx degit furkansarikaya/proofline/skills/evidence-map .claude/skills/evidence-map $ npx degit furkansarikaya/proofline/skills/explain-html .claude/skills/explain-html $ npx degit furkansarikaya/proofline/skills/exploit-proof .claude/skills/exploit-proof $ npx degit furkansarikaya/proofline/skills/intent-grill .claude/skills/intent-grill $ npx degit furkansarikaya/proofline/skills/llm-wiki .claude/skills/llm-wiki $ npx degit furkansarikaya/proofline/skills/performance-proof .claude/skills/performance-proof $ npx degit furkansarikaya/proofline/skills/plan-contract .claude/skills/plan-contract $ npx degit furkansarikaya/proofline/skills/product-assess .claude/skills/product-assess $ npx degit furkansarikaya/proofline/skills/product-discovery .claude/skills/product-discovery $ npx degit furkansarikaya/proofline/skills/product-spec .claude/skills/product-spec $ npx degit furkansarikaya/proofline/skills/proof-review .claude/skills/proof-review $ npx degit furkansarikaya/proofline/skills/proofline-lead .claude/skills/proofline-lead $ npx degit furkansarikaya/proofline/skills/proofline .claude/skills/proofline $ npx degit furkansarikaya/proofline/skills/qa-plan .claude/skills/qa-plan $ npx degit furkansarikaya/proofline/skills/system-design .claude/skills/system-design $ npx degit furkansarikaya/proofline/skills/task-author .claude/skills/task-author $ npx degit furkansarikaya/proofline/skills/tdd-proof .claude/skills/tdd-proof $ npx degit furkansarikaya/proofline/skills/test-trust .claude/skills/test-trust $ npx degit furkansarikaya/proofline/skills/ui-design .claude/skills/ui-design $ npx degit furkansarikaya/proofline/skills/verify-proof .claude/skills/verify-proof $ npx degit furkansarikaya/proofline/skills/visual-proof .claude/skills/visual-proof
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (28)
api-designconcurrency-proofcontract-proofdata-designdebug-proofdesign-syncdocs-writerevidence-mapexplain-htmlexploit-proofintent-grillllm-wikiperformance-proofplan-contractproduct-assessproduct-discoveryproduct-specproof-reviewproofline-leadprooflineqa-plansystem-designtask-authortdd-prooftest-trustui-designverify-proofvisual-proof
Similar rigs
MartinOlivero/saas-builder
Build a complete, secure SaaS end to end with your CLI agent: 22 lifecycle skills, prevention-first security, RLS audit, real payments — and field notes from production apps that passed every test. Pairs with Superpowers.
Skill Collector 1.9k tok · · Q0
AbuMahir980/peer-ai
Keeps AI coding tools (Claude Code, Codex, Cursor, Copilot, Gemini CLI) to a senior team's standard: planning, testing, security and compliance, with proof of every check. One package: a CLI and an MCP server.
Skill Collector 2.4k tok · · Q0
proyecto26/system-design-skills
A divide-and-conquer wiki of system-design skills for Claude Code — reason about scalable systems, don't memorize architectures.
Skill Collector 1.9k tok · · Q0
1a2b3cw/claude-team-config
AI 全栈开发团队配置 v2.0 - 基于 Claude Code 的 5 Agent + 13 Skill 协作开发模板
Orchestrator 33.6k tok · · Q51