tastedistill
01Plugin Claude Code
TasteDistill plugin marketplace for Claude Code.
2 3mo ago A
tokens not measured
original MIT
tasted
02Plugin Claude Code
Portable taste distillation and engineering harness for Codex and Claude Code.
2 3mo ago A
tokens not measured
original MIT
codegraph
03MCP server Claude CodeCodexCursor +2
Local-first code intelligence for AI agents (MCP). Self-contained — bundles its own runtime. Runs locally from the @colbymchenry/codegraph npm package.
2 3mo ago A
tokens not measured
original MIT
debug
04Skill Claude CodeCodex
Diagnose failures, broken behavior, regressions, test failures, runtime errors, stale state, rendering bugs, and repeated failed fixes. Use when something does not work, used to work, crashes, fails tests, or needs root-cause proof. Not for product planning or release readiness.
2 3mo ago A 60 tokens
original MIT
design
05Skill Claude CodeCodex
Define product direction, interaction principles, UI structure, visual execution rules, and screenshot-based polish before or during frontend implementation. Use when the task involves UI, product design, interaction behavior, visual quality, or design-system consistency. Not for backend-only logic.
2 3mo ago A 53 tokens
original MIT
distill
06Skill Claude CodeCodex
Extract reusable lessons from completed work, failed attempts, user corrections, logs, diffs, tests, project outcomes, local agent memory, and conversation history, then update durable skills or rules. Use when asked to learn from experience, personalize an agent from prior work, improve skills, refine agent behavior…
2 3mo ago B 74 tokens
original MIT
learn
07Skill Claude CodeCodex
Research unfamiliar domains, source materials, repositories, documents, or problem spaces and turn them into structured understanding before planning or implementation. Use when the task asks for deep research, source synthesis, domain learning, evidence mapping, or study notes. Not for one-off link fetching or simple…
2 3mo ago A 60 tokens
original MIT
ship
08Skill Claude CodeCodex
Review implemented work, verify acceptance criteria, prepare delivery, inspect release readiness, handle PR or issue follow-through, and confirm shipped state. Use when work is ready for review, merge, release, publish, push, or handoff. Not for root-cause debugging.
2 3mo ago A 56 tokens
original MIT
think
09Skill Claude CodeCodex
Turn rough ideas, product questions, architecture choices, implementation options, and tradeoffs into decision-ready plans. Use when the user asks what to build, whether an approach is worth it, how to structure a solution, or what plan the agent should execute. Not for debugging an already broken behavior.
2 3mo ago A 61 tokens
original MIT
tasted
10Plugin Claude Code
Portable taste distillation and engineering harness for Codex and Claude Code.
2 3mo ago A
tokens not measured
copy · 100% MIT
tasted-debug
11Skill Claude CodeCodex
Diagnose failures, broken behavior, regressions, test failures, runtime errors, stale state, rendering bugs, and repeated failed fixes. Use when something does not work, used to work, crashes, fails tests, or needs root-cause proof. Not for product planning or release readiness.
2 3mo ago A 62 tokens
copy · 91% MIT
Skill Claude CodeCodex
Define product direction, interaction principles, UI structure, visual execution rules, and screenshot-based polish before or during frontend implementation. Use when the task involves UI, product design, interaction behavior, visual quality, or design-system consistency. Not for backend-only logic.
2 3mo ago A 55 tokens
copy · 95% MIT
Skill Claude CodeCodex
Extract reusable lessons from completed work, failed attempts, user corrections, logs, diffs, tests, project outcomes, local agent memory, and conversation history, then update durable skills or rules. Use when asked to learn from experience, personalize an agent from prior work, improve skills, refine agent behavior…
2 3mo ago B 76 tokens
copy · 97% MIT
tasted-learn
14Skill Claude CodeCodex
Research unfamiliar domains, source materials, repositories, documents, or problem spaces and turn them into structured understanding before planning or implementation. Use when the task asks for deep research, source synthesis, domain learning, evidence mapping, or study notes. Not for one-off link fetching or simple…
2 3mo ago A 63 tokens
copy · 95% MIT
tasted-ship
15Skill Claude CodeCodex
Review implemented work, verify acceptance criteria, prepare delivery, inspect release readiness, handle PR or issue follow-through, and confirm shipped state. Use when work is ready for review, merge, release, publish, push, or handoff. Not for root-cause debugging.
2 3mo ago A 59 tokens
copy · 97% MIT
tasted-think
16Skill Claude CodeCodex
Turn rough ideas, product questions, architecture choices, implementation options, and tradeoffs into decision-ready plans. Use when the user asks what to build, whether an approach is worth it, how to structure a solution, or what plan the agent should execute. Not for debugging an already broken behavior.
2 3mo ago A 64 tokens
copy · 98% MIT