skills/research/SKILL.md
Structured multi-source research methodology. Enables web search, memory, file reading, and deep search for comprehensive investigation. Keywords: research, investigate, explore, analyze, gather, study
npx skillsauth add avifenesh/cairn researchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Structured multi-source research. Follow these phases:
Decompose the topic into 3-7 research questions covering multiple angles before searching.
cairn.webSearch with 2-3 queries per question. Prefer authoritative sources.cairn.readFile, cairn.searchFiles, cairn.listFiles for local investigation.cairn.searchMemory for simple lookups. cairn.deepSearch for multi-hop queries.cairn.readFeed for recent signals. cairn.journalSearch for past decisions.Use cairn.webFetch to read full content from the top 5-10 URLs. Do not rely on search snippets.
Combine findings with citations. Use source credibility ranking:
Always structure findings with: Summary, Key Findings (cited), Details, Sources table, Confidence assessment, Open Questions.
data-ai
Detect agent-cairn PRs that have stalled (no activity >=90 min) and classify the failure mode to route to appropriate recovery agent.
tools
Post-install skill adaptation: read a newly installed SKILL.md, fix environment-specific references (paths, accounts, tool names), assign the skill to relevant agent types, and propose an AGENTS.md update. Triggered automatically after cairn.installSkill completes.
data-ai
Monthly self-improvement brief for Cairn. Queries error_patterns, action_exemplars, experiment_windows, and session_journal to synthesize what Cairn learned, where it failed, and 3 concrete proposals for Avi to approve. Run on the 1st of each month. Keywords: growth brief, monthly review, self-improvement, what did cairn learn, how is cairn doing, monthly report
testing
Decision support with memory-backed context. Retrieves past decisions, journal history, and relevant facts before answering questions that involve a choice or tradeoff. Keywords: should I, which is better, tradeoff, compare, decide, choose, option, alternative, pros and cons, recommend