Using Agent Skills
addyosmani/agent-skills
Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.
Build, audit, and improve lightweight harnesses for AI coding agents: AGENTS.md/CLAUDE.md, feature state, verification workflows, scope boundaries, lifecycle handoff, memory persistence, context…
Install Harness Creator
$ npx skills add juliepy/AI-Engineer-from-scrach --skill harness-creator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install juliepy/AI-Engineer-from-scrach harness-creator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/juliepy/AI-Engineer-from-scrach.git skills-src && mkdir -p .claude/skills && cp -r skills-src/06-harnes/learn-harness-engineering/skills/harness-creator .claude/skills/harness-creator && rm -rf skills-srcUse ~/.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/
Install the "harness-creator" agent skill from https://github.com/juliepy/AI-Engineer-from-scrach/tree/main/06-harnes/learn-harness-engineering/skills/harness-creator into .claude/skills/harness-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-creator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/juliepy/AI-Engineer-from-scrach/tree/main/06-harnes/learn-harness-engineering/skills/harness-creatorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add juliepy/AI-Engineer-from-scrach --skill harness-creator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install juliepy/AI-Engineer-from-scrach harness-creator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/juliepy/AI-Engineer-from-scrach.git skills-src && mkdir -p .agents/skills && cp -r skills-src/06-harnes/learn-harness-engineering/skills/harness-creator .agents/skills/harness-creator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "harness-creator" agent skill from https://github.com/juliepy/AI-Engineer-from-scrach/tree/main/06-harnes/learn-harness-engineering/skills/harness-creator into .agents/skills/harness-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-creator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add juliepy/AI-Engineer-from-scrach --skill harness-creator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install juliepy/AI-Engineer-from-scrach harness-creator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/juliepy/AI-Engineer-from-scrach.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/06-harnes/learn-harness-engineering/skills/harness-creator .cursor/skills/harness-creator && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "harness-creator" agent skill from https://github.com/juliepy/AI-Engineer-from-scrach/tree/main/06-harnes/learn-harness-engineering/skills/harness-creator into .cursor/skills/harness-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-creator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/juliepy/AI-Engineer-from-scrach.git --path 06-harnes/learn-harness-engineering/skills/harness-creator--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add juliepy/AI-Engineer-from-scrach --skill harness-creator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install juliepy/AI-Engineer-from-scrach harness-creator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/juliepy/AI-Engineer-from-scrach.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/06-harnes/learn-harness-engineering/skills/harness-creator .gemini/skills/harness-creator && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "harness-creator" agent skill from https://github.com/juliepy/AI-Engineer-from-scrach/tree/main/06-harnes/learn-harness-engineering/skills/harness-creator into .gemini/skills/harness-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-creator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install juliepy/AI-Engineer-from-scrach harness-creatorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add juliepy/AI-Engineer-from-scrach --skill harness-creator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/juliepy/AI-Engineer-from-scrach.git skills-src && mkdir -p .github/skills && cp -r skills-src/06-harnes/learn-harness-engineering/skills/harness-creator .github/skills/harness-creator && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "harness-creator" agent skill from https://github.com/juliepy/AI-Engineer-from-scrach/tree/main/06-harnes/learn-harness-engineering/skills/harness-creator into .github/skills/harness-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-creator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add juliepy/AI-Engineer-from-scrach --skill harness-creator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install juliepy/AI-Engineer-from-scrach harness-creator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/juliepy/AI-Engineer-from-scrach.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/06-harnes/learn-harness-engineering/skills/harness-creator .opencode/skills/harness-creator && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "harness-creator" agent skill from https://github.com/juliepy/AI-Engineer-from-scrach/tree/main/06-harnes/learn-harness-engineering/skills/harness-creator into .opencode/skills/harness-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-creator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
harness-creator- GitHub stars
- 436
- Token cost
- ~1.2k tokens
- SKILL.md length
- 465 words
- Files
- 25 (incl. scripts, references)
- Skills in repo
- 15
- Repo updated
- First seen
- Licence
- MIT
At a glance
Build, audit, and improve lightweight harnesses for AI coding agents: AGENTS.md/CLAUDE.md, feature state, verification workflows, scope boundaries, lifecycle handoff, memory persistence, context…
- Works in 3 steps: Inspect what already exists: instruction… → Ask only for missing context that cannot… → Prefer a minimal harness first. Add…
- Tasks that involve Agent instruction files
- SKILL.md covers Core Model, First Move, Common Tasks and When to Read References, plus 2 more sections
- Runs JavaScript scripts from its folder; calls node, pnpm and yarn
What it does
Harness Creator is an agent skill from juliepy/AI-Engineer-from-scrach. Build, audit, and improve lightweight harnesses for AI coding agents: AGENTS.md/CLAUDE.md, feature state, verification workflows, scope boundaries, lifecycle handoff, memory persistence, context control, tool safety, and multi-agent coordination.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 29 other files, including scripts and reference files (for example `README.md`, `agents/openai.yaml` and `evals/evals.json`).
It sits in Agent Workflows, covering Agent instruction files. The licence is MIT.
When your agent uses it
- Tasks that involve Agent instruction files
Example prompts
- “/harness-creator”
Requirements
- Node.js
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Inspect what already exists: instruction files, feature/state files, verification commands, docs, package manifests.
- Ask only for missing context that cannot be inferred safely: target agent, desired file name, tolerance for structure, and whether…
- Prefer a minimal harness first. Add memory, tool safety, multi-agent, or benchmark details only when the user's problem calls for them.
What it can do on your machine
Read from SKILL.md and the folder at commit d9e02cb. 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
Ships 3 files in scripts/ (JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
nodepnpmyarnbun
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pnpm and yarn, which can reach the network depending on how they are called.
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
Harness Creator loads about 1.2k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 465 words of instructions outside code blocks.
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); the scripts in this folder are not scanned.
SKILL.md
The full file from juliepy/AI-Engineer-from-scrach at commit d9e02cb, republished under its MIT licence (© juliepy). 465 words, ~1,151 tokens.
Download SKILL.mdSave it as
.claude/skills/harness-creator/SKILL.md (or your agent's skills folder). This skill also uses 24 other files; get the full folder from GitHub.- name
- harness-creator
- description
- Build, audit, and improve lightweight harnesses for AI coding agents: AGENTS.md/CLAUDE.md, feature state, verification workflows, scope boundaries, lifecycle handoff, memory persistence, context control, tool safety, and multi-agent coordination.
- license
- MIT
Harness Creator
Use this skill to make a repository easier for coding agents to start, stay in scope, verify work, and resume across sessions. Keep the harness small enough that agents actually follow it.
Not for model selection, prompt tuning in isolation, chat UI design, or general app architecture.
Core Model
Every useful coding-agent harness has five subsystems:
| Subsystem | Minimal artifact | Purpose |
|---|---|---|
| Instructions | AGENTS.md or CLAUDE.md | Startup path, working rules, definition of done |
| State | feature_list.json, progress.md | Current feature, status, evidence, next step |
| Verification | init.sh or documented commands | Tests/checks the agent must run before claiming done |
| Scope | Feature dependencies and done criteria | Prevents overreach and half-finished work |
| Lifecycle | session-handoff.md, end-of-session routine | Makes the next session restartable |
First Move
- Inspect what already exists: instruction files, feature/state files, verification commands, docs, package manifests.
- Ask only for missing context that cannot be inferred safely: target agent, desired file name, tolerance for structure, and whether overwriting is allowed.
- Prefer a minimal harness first. Add memory, tool safety, multi-agent, or benchmark details only when the user's problem calls for them.
Common Tasks
Create a harness
Use the bundled script when working on a local repository:
node skills/harness-creator/scripts/create-harness.mjs --target /path/to/projectOptions:
--agent-file CLAUDE.mdfor Claude-oriented projects.--package-manager npm|pnpm|yarn|bunwhen detection is wrong.--commands "cmd one,cmd two"for custom verification.--forceonly after confirming overwrites are acceptable.
Then explain what was created and how the user should replace placeholder feature entries.
Audit an existing harness
Run:
node skills/harness-creator/scripts/validate-harness.mjs --target /path/to/projectReport the five subsystem scores, the lowest-scoring area, and the first 2-3 changes that would improve reliability. Treat the lowest score as a candidate bottleneck; confirm with failures, logs, or task outcomes before claiming causality.
Show full SKILL.md (193 more words)Show less
Produce a report
Use when the user wants a shareable assessment:
node skills/harness-creator/scripts/render-assessment-html.mjs --target /path/to/project
node skills/harness-creator/scripts/run-benchmark.mjs --target /path/to/project --html /path/to/report.htmlBe clear that this is a structural benchmark. Real effectiveness still needs before/after agent sessions on representative tasks.
When to Read References
Load only the reference needed for the user's problem:
- Memory across sessions: Memory Persistence
- Reusable workflows as skills: Skill Runtime
- Permissions, tools, concurrency: Tool Registry & Safety
- Context budget and progressive disclosure: Context Engineering
- Delegation and parallel agents: Multi-Agent Coordination
- Hooks, startup, long-running work: Lifecycle & Bootstrap
- Non-obvious failure modes: Gotchas
Design Rules
- Keep the root instruction file short: routing and invariants, not a full manual.
- Put project facts in project docs, not in the skill.
- Make verification commands explicit and runnable.
- Require evidence before marking a feature done.
- Use one active feature unless the harness has explicit multi-agent ownership boundaries.
- Prefer append/update state files over relying on chat history.
- Never hide destructive behavior in scripts; overwrites require explicit user approval.
Deliverable Checklist
For a usable minimal harness, leave the target project with:
-
AGENTS.mdorCLAUDE.md -
feature_list.json -
progress.md -
init.sh - Optional
session-handoff.mdfor multi-session work - Documented verification evidence or next action
If you cannot create files, provide exact file contents and commands instead.
© juliepy, 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 24 other files (scripts, references) in 06-harnes/learn-harness-engineering/skills/harness-creator of juliepy/AI-Engineer-from-scrach.
- SKILL.md
- README.md
- SKILL.md.en
- agents/openai.yaml
- evals/evals.json
- metadata.json
- references/context-engineering-pattern.md
- references/gotchas.md
- references/lifecycle-bootstrap-pattern.md
- references/memory-persistence-pattern.md
- references/multi-agent-pattern.md
- references/skill-runtime-pattern.md
- references/tool-registry-pattern.md
- scripts/create-harness.mjs
- scripts/lib/harness-utils.mjs
- scripts/render-assessment-html.mjs
- … and 9 more
Open the folder on GitHubat commit d9e02cb
Compare with similar skills
Harness 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Harness Creator this skilljuliepy/AI-Engineer-from-scrach | 436 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Using Agent Skillsaddyosmani/agent-skills | 103k | 4 repos | ~2.4k | Automated safety check: Pass | MIT | |
| Claude ReflectBayramAnnakov/claude-reflect | 1.7k | 2 repos | ~627 | Automated safety check: Pass | MIT | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Writing For Agentsbestofjs/bestofjs | 3.1k | 18 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
Claude Reflect
BayramAnnakov/claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.
Neat-Freak Knowledge Closeout
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
Writing For Agents
bestofjs/bestofjs
Writing documents for agents. An agent skill from bestofjs/bestofjs.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
- Official
SkillOpt Sleep Cycle
microsoft/SkillOpt
Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.
More from juliepy/AI-Engineer-from-scrach
All 15 skills in this repoPR Worktree
juliepy/AI-Engineer-from-scrach
Create and tear down the throwaway git worktrees used to test community PRs for waku-agent, without leaking API keys or leaving branches behind.
Review PR
juliepy/AI-Engineer-from-scrach
Review an incoming community PR for waku-agent and present it Sean's way — bilingual (English + 中文), three fixed sections: what they did & why it matters, verdict (merge / change / close), and how…
Implement
juliepy/AI-Engineer-from-scrach
Read a plan file, execute every task in dependency order with per-task validation, then write an implementation report to reports/<feature-slug-implementation-report.md.
Plan
juliepy/AI-Engineer-from-scrach
Analyze a ticket or feature description, read the codebase, identify risks, and write a context-rich implementation plan to plans/<feature-slug-plan.md.
Validate
juliepy/AI-Engineer-from-scrach
Run the full quality gate (ruff + mypy + pytest + tsc + vitest) and report PASS/FAIL for each command.
Implement
juliepy/AI-Engineer-from-scrach
读取计划文件，按依赖顺序执行每个任务并做任务级验证，最后写实现报告到 reports/<feature-implementation-report.md。
Related
Categories
Questions about Harness Creator
What does Harness Creator do?
Build, audit, and improve lightweight harnesses for AI coding agents: AGENTS.md/CLAUDE.md, feature state, verification workflows, scope boundaries, lifecycle handoff, memory persistence, context…. Harness Creator is an agent skill from juliepy/AI-Engineer-from-scrach.md, feature state, verification workflows, scope boundaries, lifecycle handoff, memory persistence, context control, tool safety, and multi-agent coordination.
When should I use Harness Creator?
Harness Creator fits situations like: tasks that involve Agent instruction files.
How do I install Harness Creator in Claude Code?
Run `npx skills add juliepy/AI-Engineer-from-scrach --skill harness-creator -a claude-code`. Or copy the skill folder (06-harnes/learn-harness-engineering/skills/harness-creator in juliepy/AI-Engineer-from-scrach) into .claude/skills/harness-creator in your project. Claude Code loads it when a task matches its description.
How do I install Harness Creator in Codex?
Run `npx skills add juliepy/AI-Engineer-from-scrach --skill harness-creator -a codex`. Or copy the skill folder (06-harnes/learn-harness-engineering/skills/harness-creator in juliepy/AI-Engineer-from-scrach) into .agents/skills/harness-creator in your project. Codex loads it when a task matches its description.
Can I use Harness 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 juliepy/AI-Engineer-from-scrach --skill harness-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/harness-creator, .gemini/skills/harness-creator, .github/skills/harness-creator and .opencode/skills/harness-creator in your project.
What does Harness Creator need to run?
Going by SKILL.md and its folder, Harness Creator needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node, pnpm, yarn and bun). Our summary lists: Node.js.
Does Harness 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 Harness 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Harness Creator use?
Harness Creator is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Harness Creator use?
About 1.2k tokens (SKILL.md is roughly 4.6k 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 9.8k tokens, read only when the agent opens those files.
What are the alternatives to Harness Creator?
Skills that share tags, products or a category with Harness Creator: Using Agent Skills (addyosmani/agent-skills, 103k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.7k stars), Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars) and Writing For Agents (bestofjs/bestofjs, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Harness Creator?
juliepy (a GitHub user) maintains it in juliepy/AI-Engineer-from-scrach, which has 436 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on September 6, 2026.
Source: juliepy/AI-Engineer-from-scrach on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.