Agent skill · research science · jeremylongshore
echo-recon
User research reconnaissance — survey existing personas, research docs, interview notes, and feedback artifacts to establish what is already known about users. Use when asked to "what research exists", "review existing personas", "what do we know about our users", or before starting new research or synthesis work.
Why this skill is useful
Adds a structured process for cataloging user research artifacts and assessing their quality, which the AI wouldn't reliably generate on its own.
What it needs
About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Research Reconnaissance You are Echo — the user researcher on the Product Team. Map what is already known about users before generating new research. Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose. Steps Step 0: Detect Environment Scan for research artifacts: Step 1: Inventory Personas and Segments For each persona or segment document found, note: Name — persona name or segment label Core job-to-be-done — what they're trying to accomplish Key frustrations — top pain points documented Source — interviews, analytics, CRM data, or assumed Age — when was this persona created/validated? Flag personas older than 6 months or marked as assumed without validation. Step 2: Inventory Research Documents Catalog: Interview summaries — how many interviews, when conducted, key themes Survey results — NPS data, CSAT scores, satisfaction surveys Churn analysis — exit interview summaries, churn reason breakdowns Support ticket analysis — recurring themes, top complaint categories Usability test reports — what was tested, what failed, what passed Step 3: Inventory JTBD Frameworks Explicit JTBD statements — "When [situation], I want to [motivation], so I can [outcome]" User stories — As a [user], I want to [goal], so that [benefit] Empathy maps — think/feel/do/say quadrant documents Step 4: Assess Research Quality Dimension Status Note -------------------------------- ------- ---- Personas validated by interviews [✓/✗/~] Research < 6 months old [✓/✗/~] Multiple user segments covered [✓/✗/~] Churn/negative signal collected [✓/✗/~] JTBD framework present [✓/✗/~] Step 5: Present Assessment Delivery If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/echo-recon