research-reporter

Solid

Turns a feedback-synthesizer output into a stakeholder-ready report — exec summary, methodology, benchmark comparison, and prioritized recommendations — formatted for the audience reading it (markdown or Notion for internal readers, Word for formal/external stakeholders). Trigger when someone has synthesis output ready and wants it turned into something shareable, says "write this up," "make me a report," or "turn these findings into something I can send to leadership." Entry point 3 of the research loop (see research-loop).

Data & Documents 20 stars 0 forks Updated today MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%
44
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Research Reporter Turns a synthesis file into something a stakeholder actually reads and acts on. Does not re-analyze anything — feedback-synthesizer already did the scoring, testing, and theming. This skill's job is presentation and prioritization for a specific audience, not new analysis. ----- ## Step 0: Who's reading this? Ask (or infer from context if it's obvious) before drafting: 1. **Audience:** internal team/PM (fast, working doc) vs. leadership or external stakeholder (formal, polished). Run `scripts/report_checks.py`'s `select_format(audience)` once you know which — `"internal"`, `"leadership"`, or `"external"` — rather than picking the format by feel. 2. **Format:** confirmed by the lookup above, or ask if the audience itself is genuinely unclear 3. **What decision is this report supporting?** Pull this from the original learning goal in `00-intake.md` if it exists — the report should visibly answer that question, not just summarize everything that was measured If there's no synthesis file to point to and someone asks for a report from scratch, stop and say synthesis needs to happen first — don't fabricate scores or themes to fill a report shape. ----- ## Step 1: Structure Every report gets these sections, scaled by audience (internal = terse, formal = fuller prose): ### Executive summary 2–4 sentences. Leads with the answer to the stated learning goal, not a recap of the method. State the headline score with its CI in plain lan...

Details

Author
ommakes
Repository
ommakes/Skills
Created
6 months ago
Last Updated
today
Language
HTML
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

research-report

Create or revise a markdown research or experiment report that makes the work UNDERSTANDABLE (why it matters, what the core idea is, what it achieved), backed by traceable evidence, integrated plots, optional literature support, plot manifest tracking, and version history, inside a single Harness without external Codex or Gemini calls. Use when you need to generate `report.md`, explain a result or method so a colleague can understand it, inventory or validate plots, create `plots/plot_manifest.json`, manage `report_versions.json`, connect report sections to supporting references, or turn an experiment or output directory into a reusable report workflow.

3 Updated 4 days ago
Axect
AI & Automation Solid

synthesize-research

Synthesize user research from interviews, surveys, and feedback into structured, evidence-backed insights. Use when you have a pile of notes to make sense of and say things like "synthesize these interviews", "find themes in this feedback", "what are users telling us", "turn this research into insights", or "analyze these support tickets". Extracts themes ranked by frequency and impact, then translates them into roadmap recommendations.

6 Updated 3 weeks ago
Sidsaladi9
Web & Frontend Solid

feedback-synthesizer

Turns raw survey results (scores + open-text comments) or any pile of qualitative feedback (reviews, support tickets, open-ended comments) into a scored, statistically-tested, thematically-coded synthesis with severity-ranked findings. Trigger when someone pastes raw survey data, a CSV of responses, or a pile of qualitative feedback and wants it turned into findings. Entry point 2 of the research loop (see research-loop); also runs standalone without a survey-architect-built survey.

20 Updated today
ommakes