Agent skill

Coding

by teddytennant in teddytennant/wizard

Baseline coding workflow. An agent skill from teddytennant/wizard.

Apache-2.0Auto-check passedDevelopment

Install Coding

skills CLI
$ npx skills add teddytennant/wizard --skill coding -a claude-code

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

GitHub CLI
$ gh skill install teddytennant/wizard coding --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/teddytennant/wizard.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/coding .claude/skills/coding && 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
coding
GitHub stars
103
Token cost
~1.4k tokens
SKILL.md length
764 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
Apache-2.0

At a glance

Baseline coding workflow. An agent skill from teddytennant/wizard.

  • Works in 7 steps: Orient first. list_files / search_files… → Honor project instructions. AGENTS.md /… → Plan briefly, then act. One or two… → …
  • Tasks that involve Code review
  • SKILL.md covers Workflow, Spec-driven / report tasks, Polyglots and build-verify and Long-lived services (HTTP,…, plus 5 more sections
  • Calls python3, cargo and npm

What it does

Coding is an agent skill from teddytennant/wizard. Baseline coding workflow. Explore before editing, make minimal precise diffs, verify with the project's own build and tests, clean deliverable directories, and review the diff before finishing.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Code review. The repository describes itself as: The fastest agent in your terminal: one Rust binary, any model. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Code review

Example prompts

  • “/coding”

Requirements

  • Python 3

Workflow steps

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

  1. Orient first. list_files / search_files / read_file before edits;
  2. Honor project instructions. AGENTS.md / project WIZARD.md build and
  3. Plan briefly, then act. One or two sentences of intent, then change.
  4. Smallest change. Prefer edit_file with an exact unique old_string.
  5. Verify. Run the project's commands via execute (from project
  6. Clean deliverable tree. Remove compile/build byproducts next to required
  7. Review before done. git_diff; confirm compile, tests, nothing unintended.

What it can do on your machine

Read from SKILL.md and the folder at commit 9d123be. 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:

    • python3
    • cargo
    • npm
    • make
    • pip
    • sh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm and pip, 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

Coding loads about 1.4k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 764 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 teddytennant/wizard at commit 9d123be, republished under its Apache-2.0 licence (© teddytennant). 764 words, ~1,391 tokens.

Download SKILL.mdSave it as .claude/skills/coding/SKILL.md (or your agent's skills folder).
name
coding
description
Baseline coding workflow. Explore before editing, make minimal precise diffs, verify with the project's own build and tests, clean deliverable directories, and review the diff before finishing.

Coding guidelines

Workflow

  1. Orient first. list_files / search_files / read_file before edits; git_status for starting state.
  2. Honor project instructions. AGENTS.md / project WIZARD.md build and style rules override defaults. The user message is the contract — extract required paths, formats, IDs, and cleanup constraints before coding.
  3. Plan briefly, then act. One or two sentences of intent, then change. Do not narrate every tool call.
  4. Smallest change. Prefer edit_file with an exact unique old_string. Do not reformat, rename, or clean up unrelated code.
  5. Verify. Run the project's commands via execute (from project instructions, else infer: cargo test, npm test, pytest, make test).
  6. Clean deliverable tree. Remove compile/build byproducts next to required sources when the task expects a specific final file set (or build under /tmp).
  7. Review before done. git_diff; confirm compile, tests, nothing unintended.

Spec-driven / report tasks

When the user gives an explicit contract (signatures, flags, exit codes, JSON/JSONL, CWE IDs, polyglots, exact paths):

  1. Checklist (or todo) every required output path on turn 1.
  2. Implement the general case — not only examples.
  3. Vulnerability / CWE reports, in order:
    1. Locate the defect fast (run tests early; search validation helpers).
    2. Minimal fix so invalid input raises the expected error.
    3. Write the report immediately in the demonstration schema.
    4. IDs only from the task's listed vocabulary (lowercased cwe-N). For listed CRLF/header-splitting bugs include cwe-93 (and cwe-20 if listed). Never only an unlisted synonym like cwe-113.
    5. Schema literally: cwe_id is a list of strings; prefer demo path style.
    6. Re-run tests; json.loads + assert list IDs and required tokens.
  4. Self-test against the contract before finishing.
  5. Never touch files the contract forbids.
  6. Confirm every required path exists (ls/cat) before the final message.

Polyglots and build-verify

  • Compile/run to verify, but write binaries under /tmp or delete them from the deliverable directory before finishing.
  • Final checks often require only the named source/output file(s).

Long-lived services (HTTP, QEMU, daemons)

  • Must survive after the agent ends: nohup ... > log 2>&1 & (or a small start script). Prove liveness with curl/ss/pgrep.
  • Do not use execute(run_in_background=true) for verifier-facing services.
  • Keep setup simple once e2e is green.

Install packages with native extensions

Critical path (timeouts fail — avoid inventory greps after green):

  1. Small compatibility-fix batch (Numpy 2 aliases, fractions.gcd→math.gcd, soft-import optional viz, int() on size math).
  2. Immediately python3 setup.py build_ext --inplace && python3 setup.py install (or equivalent that puts .so in site-packages).
  3. Verify from cd /tmp so local source cannot mask a bad install; run the required snippet.
  4. If pip install . yields pure-Python with no .so, fall back to setup.py.
  5. Run the allowed test suite next (exclude only task-marked broken tests).
  6. Fix the first real failure (often third-party key renames → dual-key .get), reinstall, re-run the same suite.
  7. Reinstall after every later source fix. Once snippet + allowed tests pass, stop.
Show full SKILL.md (295 more words)Show less

Image / board / puzzle analysis

  • Look at it. read_file on a png/jpeg/gif/webp/bmp/ppm returns the image itself, so read the file and read what you see. A QEMU screendump is a .ppm and reads the same way.
  • Don't reconstruct an image from pixel values in a script. Sampling squares and inferring labels gets the wrong answer on anything with anti-aliasing or a drop shadow, and it costs a dozen turns to get there.
  • A script still earns its place after you have seen the image, for work the eye is bad at: an engine search from a FEN you read off the board, a diff between two renders, counting hundreds of items.
  • Keep script output small either way. No pixel grids or IoU matrices in chat.

Editing rules

  • read_file immediately before every edit_file; match whitespace exactly.
  • On missing/ambiguous old_string, re-read and retry with more context — never guess.
  • Never fabricate unread file contents. Match local style. No placeholder stubs or TODO in finished work.

Shell usage

  • execute is sh -c in the project root. Non-interactive flags; no commands that wait for input. It waits 30s by default, then moves the command to a background task instead of killing it — carry on and read the notification, or task_output(id, wait_secs=N) when you need the result now. Pass timeout_secs (up to 600) when you would rather wait inline.
  • Prefer summaries over megabyte dumps; large intermediates go under /tmp.
  • No destructive commands (rm -rf, hard reset, force push, drop DB) unless explicitly asked — except routine cleanup of your own build byproducts.
  • Do not commit or push unless asked.

When things go wrong

  • Read the first error fully before reacting.
  • Same approach fails twice → change strategy (more context, different tool, ask).
  • Report failures honestly with what you tried. Never claim tests passed unrun.

© teddytennant, 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/coding of teddytennant/wizard.

Open the folder on GitHubat commit 9d123be

Compare with similar skills

Coding 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.

Coding compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Coding this skillteddytennant/wizard103—~1.4kAutomated safety check: PassApache-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Backend Code Reviewlangflow-ai/langflow155k—~3.5kAutomated safety check: NotesMIT
Mole Bug Patternstw93/Mole70k—~2kAutomated safety check: PassGPL-3.0
Backend Code Reviewlanggenius/dify158k—~676Automated safety check: PassCustom licence

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
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Backend Code Review

    langflow-ai/langflow

    Review backend code for quality, security, maintainability, and best practices based on established checklist rules.

    155k GitHub stars~3.5k tokensUpdated today
    DevelopmentAuto-check: notes
  • A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    70k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    DevelopmentAuto-check passed
  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed

More from teddytennant/wizard

  • Plain Writing

    teddytennant/wizard

    Write prose that reads like a person wrote it, not a model. An agent skill from teddytennant/wizard.

    103 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Conventional Commit

    teddytennant/wizard

    Write a conventional commit subject and body from the current diff.

    103 GitHub stars~501 tokensUpdated today
    Auto-check passed
  • Evolve

    teddytennant/wizard

    How to extend Wizard via /evolve. An agent skill from teddytennant/wizard.

    103 GitHub stars~835 tokensUpdated today
    Auto-check passed
  • PR Description

    teddytennant/wizard

    Write a pull-request title and body from the current branch against its base.

    103 GitHub stars~484 tokensUpdated today
    Auto-check passed
  • Undercover

    teddytennant/wizard

    Keep git history clean in public repos. An agent skill from teddytennant/wizard.

    103 GitHub stars~335 tokensUpdated today
    Auto-check passed

Categories

Questions about Coding

What does Coding do?

Baseline coding workflow. An agent skill from teddytennant/wizard. Coding is an agent skill from teddytennant/wizard. Baseline coding workflow.

When should I use Coding?

Coding fits situations like: tasks that involve Code review.

How do I install Coding in Claude Code?

Run `npx skills add teddytennant/wizard --skill coding -a claude-code`. Or copy the skill folder (skills/coding in teddytennant/wizard) into .claude/skills/coding in your project. Claude Code loads it when a task matches its description.

How do I install Coding in Codex?

Run `npx skills add teddytennant/wizard --skill coding -a codex`. Or copy the skill folder (skills/coding in teddytennant/wizard) into .agents/skills/coding in your project. Codex loads it when a task matches its description.

Can I use Coding 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 teddytennant/wizard --skill coding -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/coding, .gemini/skills/coding, .github/skills/coding and .opencode/skills/coding in your project.

What does Coding need to run?

Going by SKILL.md and its folder, Coding needs the command-line tools its instructions call (python3, cargo, npm, make, pip and sh). Our summary lists: Python 3.

Does Coding access the network?

SKILL.md contains no URLs. Its commands use npm and pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Coding 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 Coding use?

Coding 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 Coding use?

About 1.4k tokens (SKILL.md is roughly 5.6k 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 Coding?

Skills that share tags, products or a category with Coding: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Backend Code Review (langflow-ai/langflow, 155k stars) and Mole Bug Patterns (tw93/Mole, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Coding?

teddytennant (a GitHub user) maintains it in teddytennant/wizard, which has 103 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 8, 2026.

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