token-saving-techniques
A list of techniques for reducing token usage while working on complex tasks.
Skill by viktor-ferenczi
Chalk Labs
Need help deploying token-saving-techniques?
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/viktor-ferenczi-token-saving-techniques
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: productivity
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/token-saving-techniques
What's inside
- Skill name
token-saving-techniques- Description
- A list of techniques for reducing token usage while working on complex tasks. Use this skill when the task at hand involves working with a significant number of documents or resources.
- License
- MIT
- Instructions
- 11 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Consider using these skills: - [caveman](https://www.skills.sh/juliusbrussee/caveman/caveman) Instructions to use concise language, while not losing important details. Use only `lite` or `full` levels. Do not use this skill while producing documentation files. - [silent-cli](https://skills.sh/viktor-ferenczi/skills/silent-cli) Environment variables and parameters for running command line programs reliably in non-interactive environments (unattended). Includes silent modes, color/disable TTY, and reduced output options for 155 CLI tools. - [structured-documentation](https://skills.sh/viktor-ferenczi/skills/structured-documentation) A systematic plan for generating structured documentation to optimize further work on the same code or documents. Serves as a TOC for progressive disclosure, reducing the search effort to find facts. - [recursive-language-model](https://skills.sh/viktor-ferenczi/skills/recursive-language-model) Recursive Language Model workflow for processing documents that exceed context window limits. Uses a persistent Python REPL and subordinate agents to chunk, search, and analyze large context files. If you don't have them, ask for permission to fetch them from their respective GitHub pages: - https://github.com/viktor-ferenczi/skills - https://github.com/JuliusBrussee/caveman
From viktor-ferenczi/skills, MIT.
More from viktor-ferenczi/skills
- 0.582score
pr-description-concise-markdown
viktor-ferenczi
Writes a concise, high-level PR description in Markdown for the changes in the current branch.
SkillAFreshness: A★ 1Claude Code +9 - 0.539score
pr-review-comment-fix
viktor-ferenczi
Fixes an issue pointed out by a comment in a PR review.
SkillBFreshness: B★ 1Claude Code +9 - 0.502score
bizzfactory-document-downloader
viktor-ferenczi
Download all of a client's documents from the Bizz Factory portal (portal.bizzfactory.se) into a local folder tree that mirrors the page, without converting…
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
recursive-language-model
viktor-ferenczi
Recursive Language Model workflow for processing documents that exceed context window limits.
SkillCFreshness: C★ 1Claude Code +9 - 0.498score
sdl3-wiki
viktor-ferenczi
Complete offline copy of the SDL3 (Simple DirectMedia Layer 3) wiki in CommonMark format.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
gcp-batch-inference
viktor-ferenczi
Run Gemini batch inference on Google Cloud Vertex AI.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
consistency-check
viktor-ferenczi
Finds and fixes internal inconsistencies in a software project — code vs configuration vs documentation drift, plus linter findings.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
stabilization-loop
viktor-ferenczi
Iterates on a locally runnable project (typically a server with a test suite) until it builds, runs, and passes all tests cleanly, fixing failures between runs.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
structured-documentation
viktor-ferenczi
Generate a verified, modular handbook from a large source-code or document tree, then keep it cheap to refresh as the inputs change.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
python-guidelines
viktor-ferenczi
Guiding principles for writing clear, concise, human readable and maintainable Python code.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
godot-documentation
viktor-ferenczi
Installs and serves an offline copy of the official Godot Engine documentation (getting started guides, tutorials, API class reference, engine details).
SkillCFreshness: C★ 1Claude Code +9 - 0.492score
swdev-best-practices
viktor-ferenczi
Best practices to follow and principles to adhere to during software development.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 5, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/viktor-ferenczi/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from viktor-ferenczi
- 0.582score
pr-description-concise-markdown
viktor-ferenczi
Writes a concise, high-level PR description in Markdown for the changes in the current branch.
SkillAFreshness: A★ 1Claude Code +9 - 0.539score
pr-review-comment-fix
viktor-ferenczi
Fixes an issue pointed out by a comment in a PR review.
SkillBFreshness: B★ 1Claude Code +9 - 0.502score
bizzfactory-document-downloader
viktor-ferenczi
Download all of a client's documents from the Bizz Factory portal (portal.bizzfactory.se) into a local folder tree that mirrors the page, without converting…
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
recursive-language-model
viktor-ferenczi
Recursive Language Model workflow for processing documents that exceed context window limits.
SkillCFreshness: C★ 1Claude Code +9 - 0.498score
sdl3-wiki
viktor-ferenczi
Complete offline copy of the SDL3 (Simple DirectMedia Layer 3) wiki in CommonMark format.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
consistency-check
viktor-ferenczi
Finds and fixes internal inconsistencies in a software project — code vs configuration vs documentation drift, plus linter findings.
SkillCFreshness: C★ 1Claude 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 token-saving-techniques 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
token-saving-techniques skill. Agent Mart. https://agentmart.dev/skills/viktor-ferenczi-token-saving-techniques (last updated 2026-10-24)