ai-token-efficiency-research
Use this skill when the user asks about recent AI research on token efficiency, prompt compression, inference cache compression, prompt caching, agent memory…
Skill by jaemyeong-hwnag
Chalk Labs
Need help deploying ai-token-efficiency-research?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jaemyeong-hwnag-ai-token-efficiency-research
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, ml, research, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/ai-token-efficiency-research
What's inside
- Skill name
ai-token-efficiency-research- Description
- Use this skill when the user asks about recent AI research on token efficiency, prompt compression, inference cache compression, prompt caching, agent memory, or cost reduction in model and agent systems. Trigger on Korean cues such as "token 줄이기", "AI agent 비용", "토큰 최적화", "비용 줄이기", "정확도 유지", and English cues such as "prompt compression", "KV cache", "recent AI papers", "agent token optimization", and "cost reduction". Also trigger when the user wants a research summary that can become a skill or reference document.
- License
- MIT
- Instructions
- 104 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
More from jaemyeong-hwnag/common-ai-skill
- 0.474score
paper-research
jaemyeong-hwnag
Use proactively whenever academic literature could improve answer quality, even when the user does not mention papers or research.
SkillCFreshness: CClaude Code +9 - 0.471score
principle-audit
jaemyeong-hwnag
Audit the codebase for violations of the project's core principles — detect unintended system-imposed constraints that contradict the project's stated goals.
SkillCFreshness: CClaude Code +9 - 0.471score
code-documentation
jaemyeong-hwnag
Document public code surfaces and API behavior using the project's native documentation conventions while avoiding redundant comments and private…
SkillCFreshness: CClaude Code +9 - 0.471score
harness-engineering
jaemyeong-hwnag
Design the runtime environment around AI agents — constraints, guardrails, verification, sandboxing, feedback loops, and recovery mechanisms that make agents…
SkillCFreshness: CClaude Code +9 - 0.471score
auto-select
jaemyeong-hwnag
Detect project context and automatically select, apply, and propose skills.
SkillCFreshness: CClaude Code +9 - 0.471score
delivery-workflow
jaemyeong-hwnag
Enforce the full delivery cycle for every implementation task.
SkillCFreshness: CClaude Code +9 - 0.471score
ai-token-optimize
jaemyeong-hwnag
Optimize AI-consumed code and data for token efficiency — reduce token usage while preserving semantic fidelity.
SkillCFreshness: CClaude Code +9 - 0.469score
interface-first-development
jaemyeong-hwnag
Define contracts before implementations.
SkillCFreshness: CClaude Code +9 - 0.469score
hexagonal-development
jaemyeong-hwnag
Detect and enforce layered architecture boundaries.
SkillCFreshness: CClaude Code +9 - 0.469score
rag-development
jaemyeong-hwnag
Implement Retrieval-Augmented Generation pipelines — ingestion, chunking, embedding, retrieval, and generation.
SkillCFreshness: CClaude Code +9 - 0.469score
agent-orchestration
jaemyeong-hwnag
Coordinate multiple agents — routing, delegation, parallelism, state sharing, and result aggregation.
SkillCFreshness: CClaude Code +9 - 0.469score
coverage
jaemyeong-hwnag
Analyze test coverage and drive it to 80%+ by writing missing tests.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 2
- Last commit (this folder)
- May 21, 2026 (5 months ago)
- Last release
- May 21, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jaemyeong-hwnag
- 0.474score
paper-research
jaemyeong-hwnag
Use proactively whenever academic literature could improve answer quality, even when the user does not mention papers or research.
SkillCFreshness: CClaude Code +9 - 0.471score
delivery-workflow
jaemyeong-hwnag
Enforce the full delivery cycle for every implementation task.
SkillCFreshness: CClaude Code +9 - 0.471score
auto-select
jaemyeong-hwnag
Detect project context and automatically select, apply, and propose skills.
SkillCFreshness: CClaude Code +9 - 0.471score
code-documentation
jaemyeong-hwnag
Document public code surfaces and API behavior using the project's native documentation conventions while avoiding redundant comments and private…
SkillCFreshness: CClaude Code +9 - 0.471score
ai-token-optimize
jaemyeong-hwnag
Optimize AI-consumed code and data for token efficiency — reduce token usage while preserving semantic fidelity.
SkillCFreshness: CClaude Code +9 - 0.471score
harness-engineering
jaemyeong-hwnag
Design the runtime environment around AI agents — constraints, guardrails, verification, sandboxing, feedback loops, and recovery mechanisms that make agents…
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get ai-token-efficiency-research running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
ai-token-efficiency-research skill. Agent Mart. https://agentmart.dev/skills/jaemyeong-hwnag-ai-token-efficiency-research (last updated 2026-10-24)