Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Field-test a skill by running it cold in parallel agent sessions, then turn what they hit into edits.
Install Test A Skill
$ npx skills add will-ness-ai/skills --skill test-a-skill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install will-ness-ai/skills test-a-skill --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/will-ness-ai/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/test-a-skill .claude/skills/test-a-skill && 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 "test-a-skill" agent skill from https://github.com/will-ness-ai/skills/tree/main/skills/test-a-skill into .claude/skills/test-a-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-a-skill", 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/will-ness-ai/skills/tree/main/skills/test-a-skillType 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 will-ness-ai/skills --skill test-a-skill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install will-ness-ai/skills test-a-skill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/will-ness-ai/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/test-a-skill .agents/skills/test-a-skill && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "test-a-skill" agent skill from https://github.com/will-ness-ai/skills/tree/main/skills/test-a-skill into .agents/skills/test-a-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-a-skill", 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 will-ness-ai/skills --skill test-a-skill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install will-ness-ai/skills test-a-skill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/will-ness-ai/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/test-a-skill .cursor/skills/test-a-skill && 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 "test-a-skill" agent skill from https://github.com/will-ness-ai/skills/tree/main/skills/test-a-skill into .cursor/skills/test-a-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-a-skill", 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/will-ness-ai/skills.git --path skills/test-a-skill--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 will-ness-ai/skills --skill test-a-skill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install will-ness-ai/skills test-a-skill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/will-ness-ai/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/test-a-skill .gemini/skills/test-a-skill && 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 "test-a-skill" agent skill from https://github.com/will-ness-ai/skills/tree/main/skills/test-a-skill into .gemini/skills/test-a-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-a-skill", 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 will-ness-ai/skills test-a-skillInstalls 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 will-ness-ai/skills --skill test-a-skill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/will-ness-ai/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/test-a-skill .github/skills/test-a-skill && 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 "test-a-skill" agent skill from https://github.com/will-ness-ai/skills/tree/main/skills/test-a-skill into .github/skills/test-a-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-a-skill", 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 will-ness-ai/skills --skill test-a-skill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install will-ness-ai/skills test-a-skill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/will-ness-ai/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/test-a-skill .opencode/skills/test-a-skill && 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 "test-a-skill" agent skill from https://github.com/will-ness-ai/skills/tree/main/skills/test-a-skill into .opencode/skills/test-a-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-a-skill", 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
test-a-skill- GitHub stars
- 168
- Token cost
- ~1k tokens
- SKILL.md length
- 687 words
- Files
- 2
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
Field-test a skill by running it cold in parallel agent sessions, then turn what they hit into edits.
- Works in 4 steps: Pick three realistic scenarios → Run it cold → Verify, then rank → …
- Tasks that involve Subagents
- SKILL.md covers 1. Pick three realistic…, 2. Run it cold, 3. Verify, then rank and 4. Offer the edits
- Calls claude
What it does
Test A Skill is an agent skill from will-ness-ai/skills. Field-test a skill by running it cold in parallel agent sessions, then turn what they hit into edits.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Agent Workflows, covering Subagents. The repository describes itself as: Skills for building high quality software. The licence is MIT.
When your agent uses it
- Tasks that involve Subagents
Example prompts
- “/test-a-skill”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 71d8909. 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
Shell commands in SKILL.md call:
claude
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
Test A Skill loads about 1k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 687 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from will-ness-ai/skills at commit 71d8909, republished under its MIT licence (© will-ness-ai). 687 words, ~1,007 tokens.
Download SKILL.mdSave it as
.claude/skills/test-a-skill/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- test-a-skill
- description
- Field-test a skill by running it cold in parallel agent sessions, then turn what they hit into edits.
- disable-model-invocation
- true
A skill is a process, so reading it proves nothing. Run it.
/test-a-skill <skill> puts the skill in front of agents that have never seen it, on work you would really bring to it. What they produce shows whether it works. What they had to guess shows what to fix — that is the deliverable.
1. Pick three realistic scenarios
Three inputs you would genuinely hand this skill, spread across the range you would genuinely use it on. Let them differ the way real work differs: in size, in subject, in how much explaining material happens to come with them. Three similar inputs test one thing three times.
Realistic beats adversarial. A pathological input tells you how the skill behaves somewhere it will never go, then tempts you to spend the skill's words fixing that instead of the path every run takes.
Done when each subject is work you would actually bring to this skill, and no two are alike.
2. Run it cold
Pin the skill first — a copy, or a fixed commit. The working tree moves under a long run: another session switches branch and the folder is gone mid-flight.
Then one agent per subject, in parallel, on your strongest model, as a dynamic workflow. Keep the whole fan-out in that one script: its agents are given no Agent or Workflow tool of their own, so a script that expects them to spawn anything quietly comes back empty. Where you are already inside a workflow, spawn claude -p headless instead.
Give each agent a schema, so the gap reports arrive structured rather than parsed out of prose. Give each one the tools it needs rather than only a directory: a permission wall reads back as a defect in the skill, in every report at once.
Each prompt carries the path to the skill file, plus enough to mock the context window this skill would really fire into: the request a human would type, the repo and branch they sit on, what they were doing just before, what they had already decided or read. A skill is never invoked into an empty session, so testing it against one tests a situation that never happens.
The line runs at the skill's own job. Context is what the window would already hold before anyone typed the command. Briefing is what you add because you doubt the agent will do the right thing — and each of those is a gap you just found, so put it in the skill and let the next run prove it landed. A well-briefed agent only tests your briefing.
Show full SKILL.md (256 more words)Show less
Ask each agent to return, alongside its output:
- what it actually ran: the commands, and the files it wrote
- where the skill was silent on a decision it had to make
- what it guessed
- the hardest part
- what was wrong, missing, or awkward in the skill, in its reference files, and in the skills it calls
Say the gaps matter more than the deliverable, and that you want them blunt.
Done when every agent has shown what it ran, or is named as having failed. A confident report proves a read, not a run.
3. Verify, then rank
Check every claim against the skill, its reference files, and whatever code or tool it drives. Do this before you believe any of it.
Then rank what survives by convergence: a gap three agents hit independently is real, where one agent's may be one agent's taste. Keep that order and never the reverse — agents sharing one sandbox manufacture identical false positives, so a unanimous gap is as likely to be a property of the harness you gave them as of the skill. The run this skill came from ranked "this file is unreadable" first on a 3/3 vote. The file was fine; the tester's own permission flag was not.
Done when every reported gap is confirmed against the source or dismissed with a reason.
4. Offer the edits
Call /writing-for-agents. Then hand the human one ranked list — the fix, the evidence, and how many agents hit it — and wait for their picks.
Done when the human has chosen.
© will-ness-ai, 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 1 other file in skills/test-a-skill of will-ness-ai/skills.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 71d8909
Compare with similar skills
Test A Skill 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 |
|---|---|---|---|---|---|---|
| Test A Skill this skillwill-ness-ai/skills | 168 | — | ~1k | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 38 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 41 repos | ~1.5k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
- Official
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Dispatching Parallel Agents
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
More from will-ness-ai/skills
Cmux
will-ness-ai/skills
Drive the local cmux app — workspaces, panes, surfaces, terminal input, agent sessions, and browser surfaces.
Sandcastle
will-ness-ai/skills
Run a Sandcastle lane — a sandboxed implement→review loop over a fixed batch of work in its own worktree, ended by an agent-authored PR.
Code Story
will-ness-ai/skills
Build a wizard-style HTML page that teaches how and why a change works.
Flashlight
will-ness-ai/skills
Shine a light into a wayfinder map's fog — work one direction now, out of frontier order, or redraw the map itself.
Grill Design
will-ness-ai/skills
Converge on a frontend look through rounds of prototypes and grilling verdicts.
Find Standards
will-ness-ai/skills
Find how this problem is already solved: standards we could adopt, and the industry's best practices.
Related
Categories
Questions about Test A Skill
What does Test A Skill do?
Field-test a skill by running it cold in parallel agent sessions, then turn what they hit into edits. Test A Skill is an agent skill from will-ness-ai/skills. Field-test a skill by running it cold in parallel agent sessions, then turn what they hit into edits.
When should I use Test A Skill?
Test A Skill fits situations like: tasks that involve Subagents.
How do I install Test A Skill in Claude Code?
Run `npx skills add will-ness-ai/skills --skill test-a-skill -a claude-code`. Or copy the skill folder (skills/test-a-skill in will-ness-ai/skills) into .claude/skills/test-a-skill in your project. Claude Code loads it when a task matches its description.
How do I install Test A Skill in Codex?
Run `npx skills add will-ness-ai/skills --skill test-a-skill -a codex`. Or copy the skill folder (skills/test-a-skill in will-ness-ai/skills) into .agents/skills/test-a-skill in your project. Codex loads it when a task matches its description.
Can I use Test A Skill 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 will-ness-ai/skills --skill test-a-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/test-a-skill, .gemini/skills/test-a-skill, .github/skills/test-a-skill and .opencode/skills/test-a-skill in your project.
What does Test A Skill need to run?
Going by SKILL.md and its folder, Test A Skill needs the command-line tools its instructions call (claude).
Does Test A Skill 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 Test A Skill 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 Test A Skill use?
Test A Skill 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 Test A Skill use?
About 1k tokens (SKILL.md is roughly 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 Test A Skill?
Skills that share tags, products or a category with Test A Skill: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Test A Skill?
will-ness-ai (a GitHub user) maintains it in will-ness-ai/skills, which has 168 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 8, 2026.
Source: will-ness-ai/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.