Audits a code change against a 54-phase failure taxonomy and reports what it did not check, not just what it found. Domain overlays run first and force critical-path treatment.
★not rated 6 27d agoA
tokens not measured
originalMIT
Three agent skills that catch structural decisions as you make them, ask you to defend each one, and hand back a mastery map of your project: /ledger, /ledger-audit, /ledger-report.
★not rated 6▲
+2
changed todayA
tokens not measured
originalMIT
Business copilot: market research, competitor analysis, customer discovery, PMF assessment, GTM strategy, business model — chained through a per-venture workspace. Works in Persian and English.
★not rated 6▲
+2 29d agoA
tokens not measured
originalMIT
Silent-executor mode. Give it a task, it says "yaparım...", does the work, says "tamam." — no explanation, summary, code block, progress note or task list in between. Questions still get full answers. Commands: /oduncu kalk — mode on /oduncu yat — mode off /oduncu talk — trace on: the completion line carries the.
★not rated 6▲
+1 20d agoA
tokens not measured
originalMIT
Evidence-driven Claude Code skills for playable 3D production, image-to-3D reconstruction, quality gates, gameplay verification, and cross-model subagents.
★not rated 6
changed 5d agoA
tokens not measured
originalMIT
Use when writing, reviewing, or modifying any code. Applies complexity-driven design principles from A Philosophy of Software Design, 2nd Edition by John Ousterhout.
★not rated 6 2mo agoA
tokens not measured
originalMIT
Free company lookups straight from official public APIs across 28 jurisdictions plus global LEI resolution - no Apify token and no per-result cost. Resolve and verify a company by name or national identifier.
★not rated 6 1mo agoA
tokens not measured
originalMIT
Skills for VillageSQL (MySQL with extensions): build extensions end-to-end (including porting PostgreSQL extensions to MySQL) and install VillageSQL Server.
Hypothesis-driven problem solving for AI agents: probe, falsify, escalate — never blind-retry. Bundles the behavioral skill and the inquisitor-mcp server (web search, project analysis, code tracing, phase tracking).
★not rated 5 1mo agoA
tokens not measured
originalMIT
Concise, plain-language response mode for readers with a limited attention span and/or smaller vocabulary. Cuts filler, hedging, and politeness. Keeps every fact. Caps answer options at 3 with a read-more escape hatch. 150 words / 45 sec by default; /junebug lite doubles the budget.
★not rated 5 1mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: