Decision records & design docs

The top-rated launch-quality Decision records & design docs skill for AI agents is litho-document-skill (grade B), followed by adr-writing-stinger and flow-wizard. Skillspace rates 367 Decision records & design docs skills; 46 are launch-quality.

Captures why and how a system is built as durable documents — ADRs, RFCs, design and architecture write-ups, and knowledge wikis that record decisions and system models.

Launch-quality skills first, then by grade, then by our Skill Score, which adds judge reviews, test results, GitHub stars and adoption.

  1. litho-document-skill B
  2. adr-writing-stinger B
  3. flow-wizard B
  4. adr-writer B
  5. adr-skill B
  6. ai-agents-docs-of-record B
  7. adr-ops B
  8. adr-generator B
  9. decider B
  10. first-tree B
  11. governance C
  12. codebase-wiki C
  13. mcaf-adr-writing C
  14. use-arkouda C
  15. constitution C
  16. code-to-catalog C
  17. documentation-criteria C
  18. write-an-adr C
  19. bikeshed-conversion C
  20. develop-adr C
  21. decision C
  22. engineering-journal C
  23. design-doc-orchestrator C
  24. decision-lifecycle C
  25. mpm-adr C

Frequently asked questions

What is the best Decision records & design docs skill for AI agents?

The top-rated launch-quality Decision records & design docs skill for AI agents is litho-document-skill (grade B), followed by adr-writing-stinger and flow-wizard. Skillspace rates 367 Decision records & design docs skills; 46 are launch-quality.

How does Skillspace rate Decision records & design docs skills?

Skillspace grades every Decision records & design docs skill from A to F with a published scoring engine that reads the skill's SKILL.md: architecture and maturity make the score, and a security scan can cap it. In crowded categories, a judge model also compares the strongest contenders side by side, and some skills are tested head-to-head on real tasks against other skills in the same category (including a deliberately weak one) and a no-skill baseline. Launch-quality skills are graded A to C with a clean safety verdict, and not excluded by a quality filter: the filters catch skills our model's safety screen flags for prompt injection, guardrail bypass, harmful content or credential exposure; test fixtures and attack benchmarks; skills written only for the repository they live in; templates and stubs; and near-duplicate variants and copies of other skills. Ratings were last updated on 24 September 2026; the full method is on the methodology page.

Are Decision records & design docs skills safe to install?

Of the 367 Decision records & design docs skills Skillspace rates, 357 passed its safety scan and 10 are flagged: 3 for review, 5 as risky and 2 as unsafe. Each skill's page shows its safety verdict. A pass is not a guarantee: the scan reads only the skill's SKILL.md, not the scripts or other files it ships, and looks for patterns such as piping a remote script into a shell, reading credentials or hiding actions from the user. Skills are third-party code that Skillspace indexes but does not host or endorse, so read a skill's source on GitHub before you install it.

Skillspace indexes and rates skills; it does not host or endorse them. Run third-party skills at your own risk.