Design Buddy
claudecodexA repo-agnostic design partner: adversarially debated designs, evidence-grounded implementation plans, and a strict plan-review gate — from bug fixes to rearchitectures.
3 skills · 5 agents
A context-engineering toolkit: context-constitution reverse-engineers a repo's non-obvious tribal knowledge into an evidence-cited context-constitution.md plus a behavioral contract in CLAUDE.md; context-scrubber audits the repo's context files and reports every line that fails the litmus test — stale citations, restated facts, duplication, contradictions, just-in-time, brittle instructions, bloat — plus a file-level context-budget signal, with an optional gated trim. Adds the high-signal context, removes the low-signal; invents nothing, every rule and verdict is grounded.
Plugin context-forge from marketplace davcs86-agent-plugins in davcs86/agent-plugins. Commands read from the repo's manifest — 26 days ago.
context-constitutionCapture the undocumented rules of a codebase — conventions nobody wrote down, the one file that breaks the pattern, and the scars behind them — into an evidence-cited context-constitution.md, plus a behavioral contract prepended to CLAUDE.md. Use when the user wants to write, generate, bootstrap, or
context-scrubberAudit a repo's agent-context files (CLAUDE.md, AGENTS.md, .cursor/rules/*, and opt-in docs) and report every line that costs tokens on each load without changing how the agent behaves — citations that no longer resolve, facts the agent reads for free, the same rule repeated in two files, claims the
context-auditorRead-only auditor for the context-scrubber skill. Given a list of a repo's auto-loaded context/instruction files (root + nested CLAUDE.md, AGENTS.md, the generated context-constitution.md, .cursor/rules/*) and the repo root, it classifies each substantive line AGAINST the actual repo — stale citatio
convention-scoutRead-only scout for the context-forge skill. Given an analysis root (a repo or one module of a monorepo), it hunts the NON-OBVIOUS — emergent patterns followed across many files with no doc stating them, asymmetries (the one place that deviates), implicit cross-module contracts, and code that looks
A repo-agnostic design partner: adversarially debated designs, evidence-grounded implementation plans, and a strict plan-review gate — from bug fixes to rearchitectures.
3 skills · 5 agents
Three staff-level survey lenses that scout a codebase and emit evidence-cited findings: debt-radar triages technical debt (smells, dead code, swallowed errors) with severity, LOE and do-vs-not trade-offs and verifies past findings; feature-gap maps the user-facing surface (UI, MCP tools, CLI, public API) for gaps, inconsistencies, discoverability and product metrics; signal-map recommends surgical log/metric/trace placement for debugging and feature performance. Read-only; invents nothing — every finding cites a path:line.
3 skills · 4 agents
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.