Index of every page on this site: llms.txt
All skills
makenotion avatar

/research-documentation

@016c74f official
Run it yourself

Researches questions across Notion sources and synthesizes cited briefs, comparisons, or reports. Use when answering requires discovering and reconciling workspace information, optionally with external research, and returning or saving the findings.

  • 27 files
  • 61.6 KB
  • Updated 2 weeks ago
  • GitHub
Use this Skill: https://skilld.dev/gh/makenotion/claude-code-notion-plugin/research-documentation

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencecustomer-feedback.md

≈590 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Synthesize customer feedback

Use for feedback from interviews, support, sales, surveys, or research notes. Establish the question, period, audience, and source population before drawing conclusions. Retrieve the relevant feedback, following pagination when necessary; state coverage limits when the set is incomplete or selectively sampled.

Count evidence at the right level

Keep source links and stable feedback or customer identifiers where available. Deduplicate copied notes and cross-posted tickets by their origin. Repeated mentions from one customer can show persistence, but are not independent customer votes. Similar wording from distinct customers is not automatically a duplicate. When customer identity is unknown, do not invent a match or a unique-customer count.

Distinguish feedback records, mentions, and distinct customers in any quantitative claim. Define the denominator, period, and eligibility rules. A customer may appear in multiple themes, so theme counts need not sum to the customer population. Do not infer market prevalence from a selected set of interviews or support tickets.

Preserve differences that affect the conclusion

Cluster by the underlying need or problem, retaining representative evidence and important counterexamples. Separate requested solutions from the problems they address. Preserve segment, plan, role, or use-case differences when sourced and material; do not infer them from names. Avoid combining opposing needs into a single universal recommendation.

Keep direct quotes faithful and attributable. Distinguish observations, your interpretation, and proposed next steps. A rare but consequential failure may deserve attention without being called widespread. Do not turn theme frequency alone into a priority score or claim roadmap commitments.

Deliver a traceable synthesis

Use the requested depth: themes with evidence, relevant segment differences, exceptions, implications, and open questions. Include counts only when defensible; qualitative synthesis is useful without percentages. Link back to supporting feedback, respecting the intended audience's access and handling of customer data. Save or update only when requested, following the main skill's destination and verification workflow. Creating a synthesis does not authorize CRM edits, task creation, or customer messages.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 016c74f. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 2 weeks ago

README badge

README badge for makenotion/claude-code-notion-plugin/research-documentation