πŸ“
WritingShell

Done Or Not

by kharmanskyi

Done Or Not is a Writing skill for Claude Code, published by kharmanskyi in open-steps.

211 stars55 forkson kharmanskyi/open-stepsAdded 2026/09/05+56% in starsRepository updated 2026/09/03
agent-skillagent-skillsai-agentsclaude-codeclaude-code-pluginclaude-code-skillsclaude-skillprompt-optimizationvibe-coding
Install in seconds
Install Done Or Not
Copy Done Or Not into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/kharmanskyi/open-steps/tree/main/skills/os-done-or-not ~/.claude/skills/os-done-or-not

Requires Node.js. Downloads this skill only β€” not the rest of the repository β€” into your Claude Code skills folder.

Without Node.js

git clone https://github.com/kharmanskyi/open-steps.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/os-done-or-not/SKILL.md in kharmanskyi/open-steps
Installs to
~/.claude/skills/os-done-or-not
Collection
One of 7 skills cataloged from this repository
Category
Writing β€” 1361 skills

What Done Or Not does

Done Or Not creates a plain-language session report when work wraps up or someone asks what happened. It summarizes proof, remaining needs, new debt, and whether it is safe to close.

Done Or Not is cataloged under Writing on DirSkills. Done Or Not comes from a repository tagged agent-skill, agent-skills, ai-agents, claude-code and claude-code-plugin.

Documentation

README

os-done-or-not

One question, one screen: did the agent finish, and what actually happened

  • in words a reader who does not code will understand. Nothing happened (pure questions, no files touched) β†’ one line saying so, no report.

Language

The language the user speaks in this session, detected from the conversation

  • translate every template label. Code, files, commands stay English.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Done Or Not

  • What else does kharmanskyi publish alongside Done Or Not?

    Done Or Not is one of 7 skills that DirSkills catalogs from kharmanskyi/open-steps, the repository it ships in. Its siblings there include Ask Simple, Check Work and Say Simple. Each one is a separate skill with its own page in this directory, installs the same way Done Or Not does, and is maintained by kharmanskyi in that same repository. The rest of the collection is listed on the kharmanskyi/open-steps page.

  • How does Done Or Not compare to other Writing skills?

    Done Or Not ranks #955 by stars among the 1361 Writing skills in this catalog. The most-starred ones next to it are Article Writing, Social Media Content Calendar and Knowledge Comic Creator. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Done Or Not against them. Open each page to compare what they document and how they install.

More from kharmanskyi/open-steps

Done Or Not is one of 7 skills cataloged on DirSkills from kharmanskyi/open-steps.

See all 7 skills β†’
❓
2026/09/05

Ask Simple

Ask Simple rewrites technical questions in plain words and asks only when the answer changes what gets built. It also screens structural choices with six checks and ends with a recommendation.
AI Engineering
21155
πŸ”
2026/09/05

Check Work

Check Work verifies another session’s reported progress against machine state and names any gaps. Use it when accepting finished work, checking other sessions, or deciding whether it is ready to merge.
Quality
21155
πŸ“
2026/09/05

Say Simple

Say Simple rewrites text in simpler words without changing the facts. Use it when a user asks for a shorter explanation, plain words, or a restatement of text.
Writing
21155
πŸͺœ
2026/09/05

Step By Step

Step By Step turns tasks that need the user's hands into clear, one-action instructions they can follow without guessing. Use it when you need someone to run commands, click, approve, or provide a secret, and verify each step after they act.
Automation
21155
πŸ”
2026/09/05

What Could Go Wrong

What Could Go Wrong runs a premortem before hard-to-undo decisions, asking what might fail, what’s missing, and why the plan could break. It is used for contracts, launches, migrations, and other one-way changes.
AI Engineering
21155
➑️
2026/09/05

What's Next

What's Next picks the next piece of work when you ask what to do now, what is left, or what is blocked. It reads recent state, open pull requests, and the backlog, then recommends one plain next task or a finished merge.
AI Engineering
21155