initial-report
Skill0 starsChanged 3 months agoMITView on GitHub
Present the first Evermuse report after the initial source scan - Use right after ingestion completes, when the user picks "Get my initial report", runs find_skills:initial-report, or asks 'show me my initial report', 'what did you learn from my sources', 'give me the first report', or 'what patterns did you find'. Trigger terms: initial report, first report, what did you learn, show me the report, post-scan report, patterns across my sources.
In this repository44 other files it gives its agents.
- analyze-feature-requestsSkill
- assumptionsSkill
- beachhead-segmentSkill
- brainstorm-ideasSkill
- brainstorm-okrsSkill
- business-modelSkill
- competitive-battlecardSkill
- competitor-analysisSkill
- create-prdSkill
- customer-journey-mapSkill
- customer-researchSkill
- daily-briefSkill
- deep-diveSkill
- development-planSkill
- gap-analysisSkill
- gtm-strategySkill
- ideal-customer-profileSkill
- interview-scriptSkill
- list-capabilitiesSkill
- market-sizingSkill
- north-star-metricSkill
- opportunity-solution-treeSkill
- outcome-roadmapSkill
- positioning-and-messagingSkill
- pricing-strategySkill
- prioritize-featuresSkill
- product-strategySkill
- product-visionSkill
- release-notesSkill
- review-prSkill
- schedule-new-ingestion-tasksSkill
- segmentationSkill
- sentiment-analysisSkill
- setup-evermuseSkill
- shipping-artifactsSkill
- strategy-frameworksSkill
- strategy-red-teamSkill
- summarize-conversationSkill
- test-scenariosSkill
- user-personasSkill
- user-storiesSkill
- using-evermuseSkill
- value-propositionSkill
- write-feature-specSkill
The file
Files
Initial Report (first report after the first scan)
The first thing Evermuse shows a user once it has scanned and processed their sources: a report of the patterns it has learned across everything it ingested. This skill is almost always reached right after setup — from the post-ingestion view's "Get my initial report" option, or via find_skills:initial-report. The job here is small and precise: land the framing in chat, then hand the moment over to the interactive report UI.
How to run the initial report
Run a few 'search' queries to get a good sense of what's in the ingested sources. Other tools can be helpful but search should be your primary method. Use find_skills and read_skills as needed. Since this report might run right after ingestion, there might not be sufficient clustering or even signals yet. If there aren't - please inform the user that the ingestion is still ongoing and it's advisable to wait.
If there are a few hundred signals at least, then it's OK to proceed. Write a report of the patterns and insights found across the sources, with a focus on new, surprising, and actionable insights. The user is probably aware of the number 1 and 2 top patterns, so state them casually as the clear pattern but focus more on the 3rd, 4th, and 5th patterns, or any clear quick wins emerging from the data. If there are no patterns yet, please inform the user that the ingestion is still ongoing and it's advisable to wait.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.