Agent skill

Writing Great Skills

by stevesolun in stevesolun/ctx

Design or revise concise skills with clear triggers, proportional constraints, progressive disclosure, and realistic validation.

MITAuto-check passed

Install Writing Great Skills

skills CLI
$ npx skills add stevesolun/ctx --skill writing-great-skills -a claude-code

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

GitHub CLI
$ gh skill install stevesolun/ctx writing-great-skills --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/stevesolun/ctx.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/writing-great-skills .claude/skills/writing-great-skills && 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
writing-great-skills
GitHub stars
588
Token cost
~421 tokens
SKILL.md length
196 words
Files
3
Skills in repo
26
Repo updated
First seen
Licence
MIT

At a glance

Design or revise concise skills with clear triggers, proportional constraints, progressive disclosure, and realistic validation.

  • Works in 8 steps: Define the job, realistic trigger… → Choose the degree of freedom → Keep metadata concise and… → …
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Writing Great Skills is an agent skill from stevesolun/ctx. Design or revise concise skills with clear triggers, proportional constraints, progressive disclosure, and realistic validation.

Its SKILL.md is about 420 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `GLOSSARY.md` and `agents/openai.yaml`).

The repository describes itself as: CTX Fit finds the cheapest AI coding setup that reliably works on your repository, then applies the winner as a reviewable change. The licence is MIT.

Example prompts

  • “/writing-great-skills”

Workflow steps

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

  1. Define the job, realistic trigger prompts, non-trigger prompts, expected
  2. Choose the degree of freedom
  3. Keep metadata concise and discriminative. Put trigger conditions in the
  4. Assume the model already understands general software work. Preserve only
  5. Keep the entrypoint legible. Move branch-specific detail, catalogues,
  6. Prefer positive target behavior and surrounding-context judgment over
  7. Validate syntax and links, then test both triggering and output quality with
  8. Prune repetition, stale material, and instructions that do not change model

What it can do on your machine

Read from SKILL.md and the folder at commit 11b582a. 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

Writing Great Skills loads about 421 tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 196 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~421

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 stevesolun/ctx at commit 11b582a, republished under its MIT licence (© stevesolun). 196 words, ~421 tokens.

Download SKILL.mdSave it as .claude/skills/writing-great-skills/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
writing-great-skills
description
Design or revise concise skills with clear triggers, proportional constraints, progressive disclosure, and realistic validation.

Write an effective skill

  1. Define the job, realistic trigger prompts, non-trigger prompts, expected output, and material failure modes.
  2. Choose the degree of freedom:
    • Use judgment-based guidance when context admits several good approaches.
    • Use parameters or pseudocode when a preferred pattern still needs adaptation.
    • Use deterministic scripts or hard gates only when reliability, safety, or repeatability justifies the constraint.
  3. Keep metadata concise and discriminative. Put trigger conditions in the description; put execution guidance in the body.
  4. Assume the model already understands general software work. Preserve only domain knowledge, workflow choices, tool interfaces, and opinions that materially change behavior.
  5. Keep the entrypoint legible. Move branch-specific detail, catalogues, templates, and examples to direct references; avoid deep reference chains.
  6. Prefer positive target behavior and surrounding-context judgment over blanket prohibitions. State exact constraints where mistakes would be costly or hard to recover.
  7. Validate syntax and links, then test both triggering and output quality with fresh, realistic prompts. Compare against a no-skill baseline when the skill's value is uncertain.
  8. Prune repetition, stale material, and instructions that do not change model behavior.

Read GLOSSARY.md when shared vocabulary helps discuss invocation, information hierarchy, steering, or pruning.

© stevesolun, 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 in .agents/skills/writing-great-skills of stevesolun/ctx.

  • SKILL.md
  • GLOSSARY.md
  • agents/openai.yaml

Open the folder on GitHubat commit 11b582a

Compare with similar skills

Writing Great Skills 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.

Writing Great Skills compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Writing Great Skills this skillstevesolun/ctx588—~421Automated safety check: PassMIT
Wobbling Ty Constraint Orderastral-sh/ruff50k—~838Automated safety check: PassMIT
Constraint-Driven Developmentaddyosmani/agent-skills105k2 repos~5.2kAutomated safety check: PassMIT
Concise Planningdavila7/claude-code-templates33k8 repos~328Automated safety check: PassMIT
Writing Clearly And ConciselyXe/site7321 repos~555Automated safety check: PassZlib
Earnings Revisions and GuidanceHKUDS/Vibe-Trading35k—~2.5kAutomated safety check: PassMIT

Similar skills

  • Official

    A skill your agent uses when a user asks to wobble ty constraint ordering, check constraint-set or TDD ordering determinism, test reversed constraint/typevar IDs, or investigate nondeterministic ty…

    50k GitHub stars~838 tokensUpdated today
    Testing & QAAuto-check passed
  • Constraint-Driven Development

    addyosmani/agent-skills

    Records a project's quality bar in CONSTRAINTS.md and watches diffs for signs an agent quietly weakened it, such as suppressions, skipped tests or lowered thresholds.

    105k GitHub starsUsed in 2 repos~5.2k tokens
    DevelopmentAuto-check passed
  • Concise Planning

    davila7/claude-code-templates

    A skill your agent uses when a user asks for a plan for a coding task, to generate a clear, actionable, and atomic checklist.

    33k GitHub starsUsed in 8 repos~328 tokens
    Auto-check passed
  • Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text.

    732 GitHub starsUsed in 1 repo~555 tokens
    DevelopmentAuto-check passed
  • Tracks analyst estimate revisions, earnings surprises, management guidance and post-earnings drift for US and Hong Kong stocks, and turns them into long and short signals.

    35k GitHub stars~2.5k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Constraint Driven Development

    sickn33/agentic-awesome-skills

    Write the project quality bar as enforced CONSTRAINTS.md so agents stop quietly lowering it: coverage, performance, accessibility thresholds watched on every diff.

    47k GitHub starsUsed in 1 repo~5.3k tokens
    Frontend & DesignAuto-check passed

More from stevesolun/ctx

All 26 skills in this repo
  • Diagnosing Bugs

    stevesolun/ctx

    Diagnose hard bugs and performance regressions with reproducible evidence, focused hypotheses, and proportional instrumentation.

    588 GitHub stars~596 tokensUpdated 7 days ago
    Auto-check passed
  • Repo Stats Autoupdate

    stevesolun/ctx

    Keeps README badge + inline counts in sync with the real number of skills, agents, graph nodes/edges, communities, converted pipelines, and test inventory.

    588 GitHub stars~724 tokensUpdated 7 days ago
    Auto-check passed
  • Code Review

    stevesolun/ctx

    Review a Git diff against repository standards and its originating requirements.

    588 GitHub stars~466 tokensUpdated 7 days ago
    Auto-check passed
  • No Mistakes

    stevesolun/ctx

    Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI.

    588 GitHub stars~458 tokensUpdated 7 days ago
    Auto-check passed
  • Skill Router

    stevesolun/ctx

    Repo-aware recommendation manager for ctx. An agent skill from stevesolun/ctx.

    588 GitHub stars~2.4k tokensUpdated 7 days ago
    Auto-check passed
  • Codebase Design

    stevesolun/ctx

    Design or improve module interfaces using deep-module heuristics.

    588 GitHub stars~662 tokensUpdated 7 days ago
    Auto-check passed

Questions about Writing Great Skills

What does Writing Great Skills do?

Design or revise concise skills with clear triggers, proportional constraints, progressive disclosure, and realistic validation. Writing Great Skills is an agent skill from stevesolun/ctx. Design or revise concise skills with clear triggers, proportional constraints, progressive disclosure, and realistic validation.

How do I install Writing Great Skills in Claude Code?

Run `npx skills add stevesolun/ctx --skill writing-great-skills -a claude-code`. Or copy the skill folder (.agents/skills/writing-great-skills in stevesolun/ctx) into .claude/skills/writing-great-skills in your project. Claude Code loads it when a task matches its description.

How do I install Writing Great Skills in Codex?

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

Can I use Writing Great Skills 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 stevesolun/ctx --skill writing-great-skills -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writing-great-skills, .gemini/skills/writing-great-skills, .github/skills/writing-great-skills and .opencode/skills/writing-great-skills in your project.

What does Writing Great Skills need to run?

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

Does Writing Great Skills 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 Writing Great Skills 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 Writing Great Skills use?

Writing Great Skills 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 Writing Great Skills use?

About 421 tokens (SKILL.md is roughly 1.7k 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 Writing Great Skills?

Skills that share tags, products or a category with Writing Great Skills: Wobbling Ty Constraint Order (astral-sh/ruff, 50k stars), Constraint-Driven Development (addyosmani/agent-skills, 105k stars), Concise Planning (davila7/claude-code-templates, 33k stars) and Writing Clearly And Concisely (Xe/site, 732 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Writing Great Skills?

stevesolun (a GitHub user) maintains it in stevesolun/ctx, which has 588 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 4, 2026.

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