New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Autocontext Knowledge Creator

by greyhaven-ai in greyhaven-ai/autocontext

Runs the `autoctx` CLI to improve an approach to a task over several generations, score or refine a single output and inspect what a run produced.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Autocontext Knowledge Creator

skills CLI
$ npx skills add greyhaven-ai/autocontext --skill autocontext-creator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install greyhaven-ai/autocontext autocontext-creator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/greyhaven-ai/autocontext.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/autocontext-creator .claude/skills/autocontext-creator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
autocontext-creator
GitHub stars
1.3k
Token cost
~964 tokens
SKILL.md length
407 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Runs the `autoctx` CLI to improve an approach to a task over several generations, score or refine a single output and inspect what a run produced.

  • Improving an approach to a recurring task over several generations
  • SKILL.md covers Overview, When to Use, Always Pass --json When Parsing and Running a Scenario, plus 8 more sections
  • Needs AUTOCONTEXT_AGENT_API_KEY
  • Scoring one output against a rubric without running a full loop

What it does

Autocontext runs an improvement loop over a task and writes what it learns to disk. This skill covers producing that knowledge, while reading what already exists is left to `autocontext-consumer`. The only requirement is that the agent can run `autoctx` and read its output, so it is not tied to one host, and the agent passes `--json` whenever it will parse a result because the human-readable form is not a stable interface.

The commands covered are `autoctx run` on a named scenario with a number of iterations, each a generation that produces and scores a candidate, `autoctx solve` for a plain-language task, `autoctx judge` to score an output against a rubric and `autoctx improve` to iterate on one. A run can be given an id and then inspected with `list`, `status`, `show` and `replay`, or followed live with `watch`, and `scenario create` scaffolds a named scenario from a template. The excerpt ends before the provider section.

When your agent uses it

  • Improving an approach to a recurring task over several generations
  • Scoring one output against a rubric without running a full loop
  • Inspecting what a finished Autocontext run produced

Example prompts

  • “Run the grid_ctf scenario for three iterations and show me the status.”
  • “Use autoctx solve to improve our support-triage response policy.”
  • “Judge this draft reply against the rubric in rubric.md and report the score.”

Requirements

  • The `autoctx` command-line tool

What it can do on your machine

Read from SKILL.md and the folder at commit f72c154. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • AUTOCONTEXT_AGENT_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Autocontext Knowledge Creator loads about 964 tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 407 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~964

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from greyhaven-ai/autocontext at commit f72c154, republished under its Apache-2.0 licence (© greyhaven-ai). 407 words, ~964 tokens.

Download SKILL.mdSave it as .claude/skills/autocontext-creator/SKILL.md (or your agent's skills folder).
name
autocontext-creator
description
Use when an agent needs to CREATE knowledge with Autocontext - run a scenario or plain-language task through the improvement loop, judge or improve a single output, and inspect what the run produced. Host-agnostic; requires only the autoctx CLI.
version
1.0.0
author
Autocontext
license
Apache-2.0

Autocontext: Creating Knowledge

Overview

Autocontext runs an improvement loop over a task and writes what it learned to disk. This skill covers producing that knowledge. To read knowledge that already exists, use autocontext-consumer instead.

Nothing here assumes a particular agent host. The only requirement is that you can run autoctx and read its output.

When to Use

  • You have a task and want Autocontext to improve an approach to it over several generations.
  • You have one output and one rubric, and want it scored or improved without a full loop.
  • You want to see what a finished run produced.

Do not use this skill to look up existing knowledge. That is autocontext-consumer.

Always Pass --json When Parsing

Every command below accepts --json. Use it whenever you intend to read the result programmatically; the human-readable form is not a stable interface.

Running a Scenario

bash
autoctx run grid_ctf --iterations 3 --json

--iterations is the number of generations. Each one produces a candidate, scores it, and folds what it learned into the knowledge for that scenario.

Give the run an id you choose when you need to refer back to it:

bash
RUN_ID="my_run_$(date +%s)"
autoctx run grid_ctf --iterations 3 --run-id "$RUN_ID" --json
autoctx status "$RUN_ID" --json

Starting From a Plain-Language Task

When there is no scenario, describe the task:

bash
autoctx solve "Improve the support-triage response policy." --iterations 3 --json

Scoring or Improving a Single Output

For one-shot work, without a loop:

bash
autoctx judge --task-prompt "..." --output "..." --rubric "..." --json
autoctx improve --task-prompt "..." --rubric "..." --rounds 3 --json

judge scores an output you already have. improve iterates on it.

Seeing What a Run Produced

bash
autoctx list --json
autoctx status "$RUN_ID" --json
autoctx show "$RUN_ID"
autoctx replay "$RUN_ID" --generation 1

show renders the run's artifacts. replay prints the JSON for one generation, which is the level to inspect when a score looks wrong.

Show full SKILL.md (161 more words)Show less

Watching a Run in Flight

bash
autoctx watch "$RUN_ID"

Creating a New Scenario

bash
autoctx scenario create --list
autoctx scenario create --template content-generation --name support-content

Scaffolds from the template library. Use this when the task recurs and deserves a named scenario rather than a one-off solve.

Choosing a Provider

Autocontext defaults to a hosted Anthropic model. To point it somewhere else, including a local server, set the provider before running:

bash
export AUTOCONTEXT_AGENT_PROVIDER=openai-compatible
export AUTOCONTEXT_AGENT_BASE_URL=http://localhost:11434/v1
export AUTOCONTEXT_AGENT_API_KEY=no-key
export AUTOCONTEXT_LOCAL_MODEL=llama3.1
autoctx run grid_ctf --iterations 3 --json

Keep secrets and base URLs in the environment or the user's profile, never in a skill file.

Before a Long Run

autoctx run preflights every endpoint it will use and refuses to start on a dead endpoint, a rejected credential, or a model the server does not serve. That check is why a misconfigured run fails in seconds rather than after spending tokens. --skip-preflight exists but wastes that protection.

Privacy

Runs write to the local knowledge root and stay there. Nothing is uploaded. Treat run artifacts as you would any local file containing the task text and model output - they contain whatever you put in the prompt.

© greyhaven-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/autocontext-creator of greyhaven-ai/autocontext.

Open the folder on GitHubat commit f72c154

Compare with similar skills

Autocontext Knowledge Creator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Autocontext Knowledge Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Autocontext Knowledge Creator this skillgreyhaven-ai/autocontext1.3k—~964Automated safety check: PassApache-2.0
Agents Best PracticesDenisSergeevitch/agents-best-practices2.4k—~7.4kAutomated safety check: PassMIT
Clawpathy AutoresearchClawBio/ClawBio1.2k—~1.4kAutomated safety check: PassMIT
Looperksimback/looper710—~2.7kAutomated safety check: NotesMIT
Loop Architectfabricioctelles/skills106—~2.1kAutomated safety check: NotesMIT
Autoresearchbyungjunjang/jangpm-meta-skills120—~6kAutomated safety check: WarnNone

Similar skills

  • Agents Best Practices

    DenisSergeevitch/agents-best-practices

    A skill your agent uses when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain.

    2.4k GitHub stars~7.4k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed

  • Clawpathy Autoresearch

    ClawBio/ClawBio

    Eval-driven skill tuning. An agent skill from ClawBio/ClawBio.

    1.2k GitHub stars~1.4k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Looper

    ksimback/looper

    Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council.

    710 GitHub stars~2.7k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check: notes

  • Loop Architect

    fabricioctelles/skills

    Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them.

    106 GitHub stars~2.1k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check: notes

  • Autoresearch

    byungjunjang/jangpm-meta-skills

    Autonomously optimize a Claude Code skill or agent system by running it repeatedly, scoring outputs against evals, mutating owned artifacts (prompt, references, scripts, agent definitions), and…

    120 GitHub stars~6k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check: warnings

  • Spec Optimize

    leo-kuang-ai/spec-first

    Run metric-driven iterative optimization loops. An agent skill from leo-kuang-ai/spec-first.

    107 GitHub stars~13k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

More from greyhaven-ai/autocontext

  • Autocontext for Hermes

    greyhaven-ai/autocontext

    Lets a Hermes agent run Autocontext scenarios, inspect Hermes curator state, export reusable knowledge and prepare local MLX or CUDA training data through the autoctx CLI.

    1.3k GitHub stars~2.5k tokensUpdated 2 days ago
    Auto-check passed

  • Autocontext

    greyhaven-ai/autocontext

    Runs LLM-based rubric judging on agent output and loops revise-and-rejudge rounds until a quality threshold is met.

    1.3k GitHub stars~892 tokensUpdated 2 days ago
    Auto-check passed

  • Autocontext Knowledge Reader

    greyhaven-ai/autocontext

    Reads and moves the playbooks and lessons that Autocontext has already learned, using the autoctx CLI and plain files on disk.

    1.3k GitHub stars~934 tokensUpdated 2 days ago
    Auto-check passed

  • Grid CTF Strategy Playbook

    greyhaven-ai/autocontext

    Operational notes for generating, evaluating and debugging strategies in the autocontext grid_ctf scenario, with tier rules and parameter ranges that worked or failed.

    1.3k GitHub stars~1.3k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Autocontext Knowledge Creator

What does Autocontext Knowledge Creator do?

Runs the `autoctx` CLI to improve an approach to a task over several generations, score or refine a single output and inspect what a run produced. Autocontext runs an improvement loop over a task and writes what it learns to disk. This skill covers producing that knowledge, while reading what already exists is left to `autocontext-consumer`.

When should I use Autocontext Knowledge Creator?

Autocontext Knowledge Creator fits situations like: improving an approach to a recurring task over several generations; scoring one output against a rubric without running a full loop; inspecting what a finished Autocontext run produced.

How do I install Autocontext Knowledge Creator in Claude Code?

Run `npx skills add greyhaven-ai/autocontext --skill autocontext-creator -a claude-code`. Or copy the skill folder (skills/autocontext-creator in greyhaven-ai/autocontext) into .claude/skills/autocontext-creator in your project. Claude Code loads it when a task matches its description.

How do I install Autocontext Knowledge Creator in Codex?

Run `npx skills add greyhaven-ai/autocontext --skill autocontext-creator -a codex`. Or copy the skill folder (skills/autocontext-creator in greyhaven-ai/autocontext) into .agents/skills/autocontext-creator in your project. Codex loads it when a task matches its description.

Can I use Autocontext Knowledge Creator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add greyhaven-ai/autocontext --skill autocontext-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/autocontext-creator, .gemini/skills/autocontext-creator, .github/skills/autocontext-creator and .opencode/skills/autocontext-creator in your project.

What does Autocontext Knowledge Creator need to run?

Going by SKILL.md and its folder, Autocontext Knowledge Creator needs credentials named AUTOCONTEXT_AGENT_API_KEY. Our summary lists: The `autoctx` command-line tool.

Does Autocontext Knowledge Creator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Autocontext Knowledge Creator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Autocontext Knowledge Creator use?

Autocontext Knowledge Creator is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Autocontext Knowledge Creator use?

About 964 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Autocontext Knowledge Creator?

Skills that share tags, products or a category with Autocontext Knowledge Creator: Agents Best Practices (DenisSergeevitch/agents-best-practices, 2.4k stars), Clawpathy Autoresearch (ClawBio/ClawBio, 1.2k stars), Looper (ksimback/looper, 710 stars) and Loop Architect (fabricioctelles/skills, 106 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Autocontext Knowledge Creator?

greyhaven-ai (a GitHub organization) maintains it in greyhaven-ai/autocontext, which has 1,304 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.

Source: greyhaven-ai/autocontext on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.