New: 97,000+ 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

Improve Agent Readiness

by OpenHands in OpenHands/extensions

Use an agent readiness report to identify and implement improvements that make a repository more agent-friendly.

MITAuto-check passed

Install Improve Agent Readiness

skills CLI
$ npx skills add OpenHands/extensions --skill improve-agent-readiness -a claude-code

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

GitHub CLI
$ gh skill install OpenHands/extensions improve-agent-readiness --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/OpenHands/extensions.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/onboarding/skills/improve-agent-readiness .claude/skills/improve-agent-readiness && 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
improve-agent-readiness
GitHub stars
157
Token cost
~1.7k tokens
SKILL.md length
729 words
Files
3 (incl. references)
Skills in repo
78
Repo updated
First seen
Licence
MIT

At a glance

Use an agent readiness report to identify and implement improvements that make a repository more agent-friendly.

  • Works in 3 steps: Read the report → Propose high-impact fixes → Implement on request
  • SKILL.md covers Prerequisites, How to run, Pillar-specific guidance and Output format
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Improve Agent Readiness is an agent skill from OpenHands/extensions. Use an agent readiness report to identify and implement improvements that make a repository more agent-friendly. Proposes repo-appropriate fixes for each pillar, then implements them on request. Use after running a readiness report or when a user wants to improve their repo's AI-readiness.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `README.md` and `references/criteria.md`).

The repository describes itself as: Public registry for OpenHands extensions. The licence is MIT.

Example prompts

  • “/improve-agent-readiness”

Requirements

  • Docker

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Read the report
  2. Propose high-impact fixes
  3. Implement on request

What it can do on your machine

Read from SKILL.md and the folder at commit d008b81. 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.

    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

Improve Agent Readiness loads about 1.7k tokens when it runs, and up to ~1.7k if it reads all its reference files. Until then it costs about 79 tokens; SKILL.md has 729 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.7k

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 OpenHands/extensions at commit d008b81, republished under its MIT licence (© OpenHands). 729 words, ~1,651 tokens.

Download SKILL.mdSave it as .claude/skills/improve-agent-readiness/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
improve-agent-readiness
description
Use an agent readiness report to identify and implement improvements that make a repository more agent-friendly. Proposes repo-appropriate fixes for each pillar, then implements them on request. Use after running a readiness report or when a user wants to improve their repo's AI-readiness.
triggers
improve-agent-readiness, agent onboarding

Agent Onboarding

Take a readiness report and turn its gaps into concrete, repo-appropriate fixes.

Prerequisites

This skill expects an agent readiness report to already exist — either from running agent-readiness-report on this repo or provided by the user. If no report exists, run the readiness report skill first.

How to run

Step 1: Read the report

Identify every ✗ (missing) feature across all five pillars.

Step 2: Propose high-impact fixes

Don't try to fix everything. Pick the 5–10 changes that would help agents the most across all pillars, ranked by impact. Not every pillar needs to be represented — focus on what matters most for this repo. The goal is to meaningfully improve the score, not to hit 74/74.

Ranking heuristic — rank by how directly the change helps an agent complete a coding task in this repo:

  1. Things that unblock agents from working at all (AGENTS.md, build commands, bootstrap scripts, dev environment setup)
  2. Things that give agents faster feedback on their work (pre-commit hooks, test documentation, PR templates with checklists)
  3. Things that improve quality or process (CI caching, label automation, spell checking, merge queues)
  4. Things that improve governance or compliance (SECURITY.md, CODEOWNERS, actionlint, CodeQL)

A single change that lets an agent build and test the project outranks a 2-for-1 that addresses minor gaps.

Proposals should fit this specific repo:

  • Look at the languages, frameworks, and tools already in use
  • Look at the project structure (monorepo vs single package, etc.)
  • Look at what's already partially in place (don't reinvent what exists)
  • Propose additions that match the repo's existing conventions and style

For each proposal, include:

  • What to add or change
  • Where it goes (file path)
  • Which pillar(s) it improves
  • Why it's high impact — use the feature descriptions in references/criteria.md to explain what goes wrong for agents without this feature. Don't just say "improves Agent Instructions" — say what the agent can't do today and what it'll be able to do after the fix.
Step 3: Implement on request

When the user approves fixes (all or a subset), implement them, then update the readiness report to reflect the new state. Flip each addressed feature from ✗ to ✓ and update the pillar counts and summary. This ensures the next run of this skill won't re-propose fixes that have already been applied.

Follow these rules:

  • Don't generate boilerplate — content should be specific to this repo
  • Match existing style — if the repo uses tabs, use tabs; if docs are in RDoc, don't write Markdown
  • Don't over-generate — a concise, accurate AGENTS.md beats a long generic one
  • Commit atomically — one commit per logical fix, not one giant commit

Pillar-specific guidance

Show full SKILL.md (297 more words)Show less
Agent Instructions fixes

The highest-impact fix is almost always an agent instruction file at the root. A good one includes:

  • Build / test / lint commands (copy from CI config or Makefile, not invented)
  • Project structure overview (what's in each top-level directory)
  • Key conventions (naming, architecture patterns, things to avoid)
  • Where to find more documentation

If the repo is a monorepo, also consider per-component instruction files that cover component-specific conventions.

Other common fixes:

  • Add AI IDE configuration if the team uses Cursor, Copilot, or Claude Code
  • Create a contributing guide if one doesn't exist
  • Add .env.example if the project uses environment variables
Feedback Loops fixes

Focus on what gives agents the fastest signal:

  • Pre-commit hooks are the single fastest feedback loop — configure them with the linter and formatter the project already uses
  • Test run documentation in the agent instruction file — agents need to know exactly which command runs which tests
  • If the project has no linter or formatter configured, propose one that matches the language ecosystem (don't propose Prettier for a Go project)
Workflows & Automation fixes

Focus on structure that helps agents understand the process:

  • PR template with a checklist — agents follow checklists well
  • Issue templates for bugs and features — gives agents structured input
  • CI concurrency control — prevents agent-triggered CI from piling up
Policy & Governance fixes

Focus on boundaries the agent needs to know:

  • CODEOWNERS — agents should know who owns what before making changes
  • Security policy — agents need to know not to file public security issues
  • Agent-aware .gitignore entries — prevent agent config files from being committed accidentally
Build & Dev Environment fixes

Focus on reproducibility:

  • Dependency lockfile if one doesn't exist — agents can't work with non-deterministic installs
  • Tool version pinning — prevents "works on my machine" failures
  • Single-command setup — document or script the full bootstrap

Output format

Present proposals like this:

# Agent Onboarding Proposals: {repo name}

Ranked by impact.  Implementing all of these would improve:
Agent Instructions (+4), Feedback Loops (+2), Policy & Governance (+1)

1. **Create AGENTS.md** — Agent Instructions
   - Include build commands from Makefile, test commands from CI, project structure
   - Path: `./AGENTS.md`
   - Right now agents have no way to learn this repo's conventions, banned
     patterns, or how to build/test — they'll guess and get it wrong.

2. **Add pre-commit hooks** — Feedback Loops
   - Configure with ruff (already in pyproject.toml) and mypy
   - Path: `./.pre-commit-config.yaml`
   - Agents currently don't find out about lint/type errors until CI runs.
     Pre-commit hooks catch these in seconds instead of minutes.

3. **Add .env.example** — Agent Instructions, Build & Dev Environment
   - Document the 3 env vars referenced in docker-compose.yml
   - Path: `./.env.example`
   - Agents can't start the dev server without knowing which env vars to set.
     They'll either skip setup or hallucinate values.

...

Ready to implement? Reply with "all" or specify which proposals to apply.

© OpenHands, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in plugins/onboarding/skills/improve-agent-readiness of OpenHands/extensions.

  • SKILL.md
  • README.md
  • references/criteria.md

Open the folder on GitHubat commit d008b81

Compare with similar skills

Improve Agent Readiness 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.

Improve Agent Readiness compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Improve Agent Readiness this skillOpenHands/extensions157—~1.7kAutomated safety check: PassMIT
Implementsickn33/agentic-awesome-skills47k5 repos~306Automated safety check: PassMIT
Implementcodewhale-hq/Codewhale41k—~190Automated safety check: PassMIT
Implement Planpenpot/penpot61k—~1.7kAutomated safety check: PassMPL-2.0
Implement Improvementstobihagemann/turbo406—~3.1kAutomated safety check: WarnMIT
Story ReadinessDonchitos/Claude-Code-Game-Studios26k—~6.9kAutomated safety check: PassMIT

Similar skills

  • Implement

    sickn33/agentic-awesome-skills

    Implement a piece of work based on a PRD or set of issues. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 5 repos~306 tokens
    Product & Project ManagementAuto-check passed

  • Implement

    codewhale-hq/Codewhale

    Carry an authorized, defined request or approved plan through scoped edits and proportionate verification.

    41k GitHub stars~190 tokensUpdated today
    Auto-check passed

  • Implement Plan

    penpot/penpot

    Implementation flow — execute a ready plan from the session context

    61k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Implement Improvements

    tobihagemann/turbo

    Validate improvements from .turbo/improvements.md, recommend a working set tailored to what's in the backlog, and run one lane: direct fixes, investigation, or planned work.

    406 GitHub stars~3.1k tokensUpdated yesterday
    Business, Finance & HRAuto-check: warnings

  • Story Readiness

    Donchitos/Claude-Code-Game-Studios

    Is a story implementation-ready?. An agent skill from Donchitos/Claude-Code-Game-Studios.

    26k GitHub stars~6.9k tokensUpdated 8 days ago
    Product & Project ManagementAuto-check passed

  • Incremental Implementation

    addyosmani/agent-skills

    Delivers a change in thin vertical slices, each implemented, tested, verified and committed before the next, using vertical, contract-first or risk-first slicing.

    102k GitHub starsUsed in 1 repo~2.3k tokens
    Agent WorkflowsAuto-check passed

More from OpenHands/extensions

All 78 skills in this repo

  • Agent Readiness Report

    OpenHands/extensions

    Evaluate how well a codebase supports autonomous AI-assisted development.

    157 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

  • Discord

    OpenHands/extensions

    Build and automate Discord integrations (bots, webhooks, slash commands, and REST API workflows).

    157 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

  • GitHub

    OpenHands/extensions

    Interact with GitHub repositories, pull requests, issues, and workflows using the GITHUBTOKEN environment variable and GitHub CLI.

    157 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

  • GitHub Issue To PR

    OpenHands/extensions

    Create an automation that implements GitHub issues when a configurable trigger label is applied.

    157 GitHub stars~4.4k tokensUpdated yesterday
    Auto-check passed

  • GitHub Repo Monitor

    OpenHands/extensions

    This skill should be used when the user asks to "monitor a GitHub repository", "watch GitHub for issues or PRs", "respond to @OpenHands mentions on GitHub", "set up an OpenHands GitHub integration"…

    157 GitHub stars~3.1k tokensUpdated yesterday
    Auto-check passed

  • GitLab Issue To Mr

    OpenHands/extensions

    Create an automation that implements GitLab issues when a configurable trigger label is applied.

    157 GitHub stars~4.9k tokensUpdated yesterday
    Auto-check passed

Questions about Improve Agent Readiness

What does Improve Agent Readiness do?

Use an agent readiness report to identify and implement improvements that make a repository more agent-friendly. Improve Agent Readiness is an agent skill from OpenHands/extensions. Use an agent readiness report to identify and implement improvements that make a repository more agent-friendly.

How do I install Improve Agent Readiness in Claude Code?

Run `npx skills add OpenHands/extensions --skill improve-agent-readiness -a claude-code`. Or copy the skill folder (plugins/onboarding/skills/improve-agent-readiness in OpenHands/extensions) into .claude/skills/improve-agent-readiness in your project. Claude Code loads it when a task matches its description.

How do I install Improve Agent Readiness in Codex?

Run `npx skills add OpenHands/extensions --skill improve-agent-readiness -a codex`. Or copy the skill folder (plugins/onboarding/skills/improve-agent-readiness in OpenHands/extensions) into .agents/skills/improve-agent-readiness in your project. Codex loads it when a task matches its description.

Can I use Improve Agent Readiness 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 OpenHands/extensions --skill improve-agent-readiness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/improve-agent-readiness, .gemini/skills/improve-agent-readiness, .github/skills/improve-agent-readiness and .opencode/skills/improve-agent-readiness in your project.

What does Improve Agent Readiness need to run?

SKILL.md names no scripts, command-line tools or credentials: Improve Agent Readiness is instructions for the agent only. Our summary lists: Docker.

Does Improve Agent Readiness 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 Improve Agent Readiness 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 Improve Agent Readiness use?

Improve Agent Readiness is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Improve Agent Readiness use?

About 1.7k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8 tokens, read only when the agent opens those files.

What are the alternatives to Improve Agent Readiness?

Skills that share tags, products or a category with Improve Agent Readiness: Implement (sickn33/agentic-awesome-skills, 47k stars), Implement (codewhale-hq/Codewhale, 41k stars), Implement Plan (penpot/penpot, 61k stars) and Implement Improvements (tobihagemann/turbo, 406 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Improve Agent Readiness?

OpenHands (a GitHub organization) maintains it in OpenHands/extensions, which has 157 GitHub stars. The repository holds 78 skills in this directory. The repository was last updated on October 6, 2026.

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