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

Intent CLI

by J-Tech-Japan in J-Tech-Japan/intent-system

Drive intent-driven development on GitHub with intent-cli. An agent skill from J-Tech-Japan/intent-system.

Apache-2.0Auto-check passed

Install Intent CLI

skills CLI
$ npx skills add J-Tech-Japan/intent-system --skill intent-cli -a claude-code

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

GitHub CLI
$ gh skill install J-Tech-Japan/intent-system intent-cli --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/J-Tech-Japan/intent-system.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/intent-cli .claude/skills/intent-cli && 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
intent-cli
GitHub stars
107
Token cost
~855 tokens
SKILL.md length
436 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
Apache-2.0

At a glance

Drive intent-driven development on GitHub with intent-cli. An agent skill from J-Tech-Japan/intent-system.

  • Works in 4 steps: Run the guide command first. Do not plan… → Follow its steps literally, including… → Prefer the canonical command it names… → …
  • The user wants to shape an intent
  • SKILL.md covers Before anything else, Which guide command to run, How to use what it prints and Keeping this skill current
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Intent CLI is an agent skill from J-Tech-Japan/intent-system. Drive intent-driven development on GitHub with intent-cli. Use when the user wants to shape an intent, cut the next slice, publish an issue, implement or review a packet, close out a PR, or set up the four-thread orchestration loop — or asks what intent-cli can do.

Its SKILL.md is about 860 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with GitHub. The licence is Apache-2.0.

When your agent uses it

  • The user wants to shape an intent
  • Cut the next slice
  • Publish an issue
  • Review a packet

Example prompts

  • “/intent-cli”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Run the guide command first. Do not plan the work from this file.
  2. Follow its steps literally, including any preflight or verification it
  3. Prefer the canonical command it names over hand-editing files or calling
  4. Report what the command actually returned — exit code, and the fields the

What it can do on your machine

Read from SKILL.md and the folder at commit 44a622e. 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 no API keys, tokens, secrets or passwords.

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

Context cost

Intent CLI loads about 855 tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 436 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~855

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 J-Tech-Japan/intent-system at commit 44a622e, republished under its Apache-2.0 licence (© J-Tech-Japan). 436 words, ~855 tokens.

Download SKILL.mdSave it as .claude/skills/intent-cli/SKILL.md (or your agent's skills folder).
name
intent-cli
description
Drive intent-driven development on GitHub with intent-cli. Use when the user wants to shape an intent, cut the next slice, publish an issue, implement or review a packet, close out a PR, or set up the four-thread orchestration loop — or asks what intent-cli can do.

intent-cli

This skill is a dispatcher, not a manual. It tells you which intent-cli command to ask for the guidance you need. It deliberately restates none of the workflow: the installed CLI's guide output is the single source of truth, and it moves with the tool while a copied-out description would not.

Rule: installed guide output wins. If anything you remember — including anything in this file — disagrees with what intent-cli guide ... prints, the guide output is correct. Run the command; do not answer from memory.

Before anything else

Confirm the tool is available and see what it offers:

bash
intent-cli --version
intent-cli guide model

guide model describes the collaboration model the rest of the workflow assumes. Read it before acting on any other guidance.

Which guide command to run

Ask the guide, then follow exactly what it prints.

The user wants to…Run
get oriented / set up for the first timeintent-cli guide onboarding
see every available command surfaceintent-cli guide commands list
find the right workflow for a goalintent-cli guide workflow suggest --goal "<what they said>"
shape or deepen an intentintent-cli guide collaborate
interview the user to draw out intentintent-cli grill
decide what to work on nextintent-cli guide next
take a slice from issue to PRintent-cli guide worker issue-to-pr
review a pull requestintent-cli guide review --pr <n> --repo <r> --domain <d>
close out a merged PRintent-cli guide closeout
run the four-thread orchestration loopintent-cli guide orchestrator-thread
understand the rules that bind a surfaceintent-cli guide rules list

When none of these obviously fits, run intent-cli guide workflow suggest --goal "<the user's own words>" and let it route.

Most guide commands accept --format markdown|json. Prefer markdown when you are going to read and act on the output; json when you need to extract a specific field.

Show full SKILL.md (139 more words)Show less

How to use what it prints

  1. Run the guide command first. Do not plan the work from this file.
  2. Follow its steps literally, including any preflight or verification it names. Guides state their own gates; skipping one is how a loop breaks.
  3. Prefer the canonical command it names over hand-editing files or calling gh directly. Where a guide names an intent-cli command for a state change, that command is the supported path.
  4. Report what the command actually returned — exit code, and the fields the guide told you to check. Do not summarize a result you did not observe.

Keeping this skill current

This file ships inside the intent-cli package. Update it with the tool:

bash
intent-cli skill list              # what is installed, and whether it has drifted
intent-cli skill diff              # what differs between installed and shipped
intent-cli skill install --target all

skill install refuses to overwrite a copy you have edited unless you pass --force, so local changes are never lost silently.

© J-Tech-Japan, 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/intent-cli of J-Tech-Japan/intent-system.

Open the folder on GitHubat commit 44a622e

Compare with similar skills

Intent CLI 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.

Intent CLI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Intent CLI this skillJ-Tech-Japan/intent-system107—~855Automated safety check: PassApache-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT
GitHub Deep Researchbytedance/deer-flow84k4 repos~1.3kAutomated safety check: PassMIT
Diagnosing Superpowers Sessionsobra/superpowers297k3 repos~1.7kAutomated safety check: PassMIT
Update V8 Versionopeninterpreter/openinterpreter69k2 repos~845Automated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    84k GitHub starsUsed in 4 repos~1.3k tokens
    Research & ScienceAuto-check passed

  • Diagnosing Superpowers Sessions

    obra/superpowers

    Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

    297k GitHub starsUsed in 3 repos~1.7k tokens
    Agent WorkflowsAuto-check passed

  • Update V8 Version

    openinterpreter/openinterpreter

    Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.

    69k GitHub starsUsed in 2 repos~845 tokens
    DevOps & CloudAuto-check passed

  • Last30days

    mvanhorn/last30days-skill

    Research what people actually say about any topic in the last 30 days.

    64k GitHub stars~7.9k tokensUpdated yesterday
    Research & ScienceAuto-check: notes

Works with

Questions about Intent CLI

What does Intent CLI do?

Drive intent-driven development on GitHub with intent-cli. An agent skill from J-Tech-Japan/intent-system. Intent CLI is an agent skill from J-Tech-Japan/intent-system. Drive intent-driven development on GitHub with intent-cli.

When should I use Intent CLI?

Intent CLI fits situations like: the user wants to shape an intent; cut the next slice; publish an issue; review a packet.

How do I install Intent CLI in Claude Code?

Run `npx skills add J-Tech-Japan/intent-system --skill intent-cli -a claude-code`. Or copy the skill folder (skills/intent-cli in J-Tech-Japan/intent-system) into .claude/skills/intent-cli in your project. Claude Code loads it when a task matches its description.

How do I install Intent CLI in Codex?

Run `npx skills add J-Tech-Japan/intent-system --skill intent-cli -a codex`. Or copy the skill folder (skills/intent-cli in J-Tech-Japan/intent-system) into .agents/skills/intent-cli in your project. Codex loads it when a task matches its description.

Can I use Intent CLI 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 J-Tech-Japan/intent-system --skill intent-cli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/intent-cli, .gemini/skills/intent-cli, .github/skills/intent-cli and .opencode/skills/intent-cli in your project.

What does Intent CLI need to run?

SKILL.md names no scripts, command-line tools or credentials: Intent CLI is instructions for the agent only.

Does Intent CLI 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 Intent CLI 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 Intent CLI use?

Intent CLI is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Intent CLI use?

About 855 tokens (SKILL.md is roughly 3.4k 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 Intent CLI?

Skills that share tags, products or a category with Intent CLI: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Greploop (onyx-dot-app/onyx, 32k stars), GitHub Deep Research (bytedance/deer-flow, 84k stars) and Diagnosing Superpowers Sessions (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Intent CLI?

J-Tech-Japan (a GitHub organization) maintains it in J-Tech-Japan/intent-system, which has 107 GitHub stars. The repository was last updated on October 11, 2026.

Source: J-Tech-Japan/intent-system on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.