Research artifacts
Living Docs — a AI agent skill that runs your project's documentation as a living system: constitution, ADRs, BDRs, PRDs, issues, research notes & Mermaid architecture diagrams under five no-drift governance invariants. OKF-formatted, stack-agnostic. Works with Claude Code, Cursor, Copilot, OpenCode & Pi.
npx -y skills add ejklock/living-docs-skill --skill research-artifactsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Organize, format, and index research as OKF-conformant knowledge bundles — dated, sourced, append-only snapshots of the external evidence behind a decision (technology evaluations, library comparisons, industry-practice surveys). Use when recording research output, structuring a docs/research/ session, enforcing source discipline (primary sources, vendor-COI flags, inference-vs-fact labels, confidence levels), or wiring the research → decision → issue traceable chain. Pairs with deep-research (which gathers/verifies the evidence) and living-docs (which owns the ADR/BDR/issue artifacts research feeds into).
SKILL.md
3.1 KB, as published. Nobody here has run it
Research Artifacts
Research records the external evidence behind a decision: technology evaluations, library comparisons, industry-practice surveys. Research is dated, sourced, and append-only — a snapshot of what the evidence said at a point in time, not a living opinion.
This skill defines how research is organized, formatted, and indexed. The deep-research skill defines how it is gathered and cross-verified; living-docs owns the decisions and issues it feeds. The three compose. Research artifacts are OKF concepts — see the okf-knowledge-format skill for the frontmatter/reserved-file rules applied here.
Using this skill (progressive disclosure)
This SKILL.md is a slim stub — a trigger plus a task->topic router. The living-docs CLI holds the full research rules, source discipline, structure and traceable chain, and discloses them progressively. Before authoring anything, load the topic for your task:
living-docs skill research-artifacts --list— discover every topic.living-docs skill research-artifacts --topic <topic>— load that topic.
Piped output is minified JSON (machine default); --plain for human text, --json to force JSON. Topics: rules, structure, research-report, research-index, research-general-references, about.
This stub is a pure router (ADR 0017): it triggers and points at topics — it holds no rules inline. The source discipline and the research → decision → issue chain are topics, loaded before authoring via --topic rules / --topic structure.
When to invoke
- Recording the output of a research session into
docs/research/—living-docs skill research-artifacts --topic research-report. - Structuring or indexing a research note (
docs/research/NNNN-<slug>.md+ the index listing + the general roll-up) —living-docs skill research-artifacts --topic research-index/--topic research-general-referencesfor the templates,--topic structurefor the layout rules. - Enforcing source discipline on a draft (primary sources, vendor-COI flags, inference-vs-fact labels, confidence levels, fetch-failure notes) —
living-docs skill research-artifacts --topic rules. - Wiring the research → decision → issue traceable chain (an accepted recommendation must reach an ADR/BDR and then issues, in
living-docs) —living-docs skill research-artifacts --topic structure.