AI Plugin Index
maka-cli
Skill by apache · updated · ★ 5.9k
Coordinates the Maka CLI as a worker to submit tasks, check progress, update saved models, and answer Session questions or approvals. It is for agents that delegate work to Maka. maka-cli is published by apache on GitHub.
Install maka-cli
Built from the published package, never by AIgit clone --depth 1 https://github.com/apache/maka /tmp/maka && mkdir -p ~/.claude/skills && cp -r /tmp/maka/skills/maka-cli ~/.claude/skills/maka-cliRun in your terminal. Claude Code loads skills from ~/.claude/skills automatically.
git clone --depth 1 https://github.com/apache/maka /tmp/maka && mkdir -p ~/.gemini/antigravity-cli/skills && cp -r /tmp/maka/skills/maka-cli ~/.gemini/antigravity-cli/skills/maka-cliAntigravity CLI loads skills from ~/.gemini/antigravity-cli/skills, or .agents/skills for one project.
Skills can run scripts on your machine. Some need an API key: check the README.
Last commit in the past day
Apache-2.0: permissive, fine for commercial use
Clear description, installs from GitHub, 5,870 stars, original repository
No risky patterns in the files we checked
About maka-cli
This agent skill tells an AI assistant how to delegate work to the Maka CLI. The parent agent submits a task with a no-wait run, saves the returned session ID, and later waits on that Session for results. It also covers checking status, requesting a recap, and adding follow-up prompts to a busy or idle Session.
The skill maps each Session status, such as running, needs_input, needs_approval, completed, failed, and idle, to a parent action. It explains how to answer questions, assess approval requests, and stop a Session. It is written for parent agents coordinating Maka work across several calls, and it keeps the parent responsible for the final judgment.
Written from the project's SKILL.md and checked against it.
What maka-cli can do
- Submit and waitSubmits a task with no-wait, then waits on the saved Session ID for the next result.
- Inspect progressReturns Session lifecycle and pending interactions, with an optional recap of recorded progress.
- Add follow-up workQueues a new prompt on an existing Session, or steers it with a focused instruction.
- Handle questions and approvalsAnswers Session questions and assesses sandbox approval requests before approving or denying.
- Stop a SessionExplicitly requests a stop for a Session, while observer interruption leaves execution running.
What you need
- Maka CLI installed
- A persistent Maka installation for detached work
Weekly newsletter
Like maka-cli? Get the best new skills every week
The best new tools, security warnings before you install something risky, and one practical tip. Free, three minute read.
Try asking
- Submit a project review to Maka and save the session ID
- Check the progress of my running Maka session
- Answer the pending question in my Maka session
Good to know
- Detached work needs a persistent installation and cannot own CLI MCP servers or use Graph Mode.
- Recaps call the model independently and can lag execution.
- This skill does not upgrade Maka.
Security check
ANo download-and-run commands, hidden instructions or signs of sending keys out were found.
Checked automatically: skills/maka-cli/SKILL.md. This looks for known risky patterns and is not a full audit. How grades work
Inside the skill
-
SKILL.md5 KB -
agents/openai.yaml1004 B -
references/session-control.md7 KB
Alternatives to maka-cli
All alternatives →
Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request bodies, tool/function schemas, outputs, and iterate until the reproduced behavior is close enough.
Retune a skill corpus for a new model, measurement-first: mine the run archive for a baseline, establish a noise floor, audit the corpus adversarially, then cut in measured passes until a pre-registered bar clears. Requires a benchmark harness that can A/B two builds of the corpus; refuses without one.
Use when building CLI tools, implementing argument parsing, or adding interactive prompts. Invoke for parsing flags and subcommands, displaying progress bars and spinners, generating bash/zsh/fish completion scripts, CLI design, shell completions, and cross-platform terminal applications using commander, click, typer, or cobra.
Audit or update English SDK documentation against the requested implementation scope.
Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates. Use when asked to improve a prompt, optimize a system prompt, rewrite an agent prompt, tune prompt wording, make a prompt more reliable, port prompts between OpenAI, Claude, or Gemini, or build prompt evals.
Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
maka-cli: common questions
Does this skill let an agent check progress on Maka tasks?
Yes. Status returns lifecycle and pending interactions, and a recap can summarize recorded progress during execution.
What happens if I press Ctrl+C while observing a Maka Session?
According to the source, Ctrl+C on a Session observer leaves Host execution running. Only the explicit stop command requests a stop.
Does a successful exit mean the task finished?
No. The source says exit 0 can mean admission or a pending interaction, not task completion.
How do I install maka-cli?
Run the command above to copy the skill into ~/.claude/skills/. Claude Code picks it up automatically.
Is maka-cli free?
The code is published under the Apache-2.0 licence. The service it connects to may have its own pricing.
Is maka-cli safe to use?
It scores 91 of 100. Grades: maintenance A, licence A, quality A. Security check: grade A, no risky patterns found in the files checked. Review the code before you install. How grades work.
What are alternatives to maka-cli?
Similar skills: agent-reproduce-align, ce-retune, cli-developer, docs-sync.