Download for macOS
Skill

find-prior-art

@tanainc Updated 2026-10-17

Search the team's Tana meetings and docs for earlier discussion of a topic: past feedback, bug reports, decisions, objections, customer requests, experiments that were tried. Reads the best hits, including the exact transcript passages and screenshots where the topic came up, and reports what was said, when and by whom, with links. Use when the user asks 'has anyone discussed this before?', 'did we try this already?', 'any feedback on X?', 'what have customers said about Y?', 'have we seen this bug before?', 'what's the history of Z?', or is mid-work and wonders whether the team has been here before. For one quick fact (a decision, a date, an owner), use ask-tana instead.

gemini-cli-extension

Install

With your agent

Install OMGSkills skill "tanainc/tana-plugin:skills/find-prior-art" into this agent's normal skills directory: use the OMGSkills MCP get_skill tool, install only the pinned_install commit and path, verify SKILL.md against pinned_install.skill_md_sha, and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.

Manual command

git clone https://github.com/tanainc/tana-plugin /tmp/tana-plugin && ln -s /tmp/tana-plugin/skills/find-prior-art ~/.claude/skills/find-prior-art

From README

Find prior art Someone halfway through a piece of work wants to know whether the team has been here before. The answer usually sits in a meeting: a customer complaining on a call, a bug someone screen-shared in standup, a design review that already rejected the idea. This skill searches meetings and docs, reads the passages where the topic came up, and reports the history with links. Steps Frame the search. Write 2–4 keyword variants (product names, feature names, error strings, customer names, the team's slang) and one plain-language description of the topic. Search wide, in parallel. Keywords across docs, transcripts and meetings, batched in one call: (searchItems) Meaning, for what nobody named the same way: semanticSearchItems({ query: "customers confused about where to enter a discount", limit: 20 }). If the workspace files things like bugs or feedback as typed docs, narrow with the text target's type ("type": ["Bug", "Feedback"]); getTypes lists the names.