Skip to content
SkillCheatSheet Sign in

writing-skills

An AI agent skill from obra/superpowers, scored 71 out of 100 by code.

71/ 100B

Code score by group

  • Spec20/20
  • Description5/20
  • Procedure12/15
  • Done criteria13/15
  • Resources6/10
  • Scripts5/8
  • Safety7/7
  • Upkeep3/5

It loses the most points in Description (15), the group that checks whether the description says what the skill does and when to use it.

What the author says it does

Use when creating new skills, editing existing skills, or verifying skills work before deployment

This is the description in the skill's own SKILL.md, written by its author, not by SkillCheatSheet.

Repository
obra/superpowers
Folder
skills/writing-skills
License
MIT
GitHub stars
316,479
SKILL.md lines
400
Other files
9

Add writing-skills to your agent

npx skills add obra/superpowers --skill writing-skills

The command uses the open skills CLI. A skill is instructions and scripts your agent will follow, so read it first: open the folder on GitHub at the commit that was scored.

Labelled for

More skills from obra/superpowers

  1. dispatching-parallel-agents

    Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    78B
  2. using-git-worktrees

    Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git…

    70B
  3. finishing-a-development-branch

    Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

    69C
  4. test-driven-development

    Use when implementing any feature or bugfix, before writing implementation code

    69C
  5. verification-before-completion

    Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any suc…

    66C
  6. diagnosing-superpowers

    Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too l…

    65C
  7. systematic-debugging

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    64C
  8. using-superpowers

    Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

    62C

All skills in obra/superpowers

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.