hoavdc/CodexKit / skills/codexkit-data-story-builder
codexkit-data-story-builder
VerifiedTurn business data, KPI movement, or experiment results into a clear narrative using the what-so what-now what structure, audience calibration, and action-oriented insight. Use when leaders need a data-backed brief, dashboard storyline, or metric interpretation. Do not use for raw statistical modeling with no communication deliverable.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.4 KB |
| agents/openai.yaml | config | 179 B |
| examples/common-mistakes.md | markdown | 799 B |
| examples/good-output.md | markdown | 1.2 KB |
| verification/checklist.md | markdown | 1.4 KB |
verification/checklist.md
View on GitHub# 4C Verification Checklist - Data Story Builder
Use this checklist before sending a data narrative to stakeholders.
## Correctness - Is it right?
- [ ] All numbers, comparisons, and percentages match the source data.
- [ ] Causal language is justified by the evidence.
- [ ] Baselines, targets, time periods, and units are clear.
- [ ] Caveats and confidence levels are included where data is weak.
## Completeness - Is it done?
- [ ] The story answers: what changed, so what, now what.
- [ ] The narrative includes context, evidence, implication, and action.
- [ ] Material counter-signals or outliers are acknowledged.
- [ ] Recommended next steps are tied to owners or decisions where possible.
## Context-fit - Does it match?
- [ ] The level of detail matches the audience.
- [ ] The story is framed around the stakeholder's decision, not the analyst's curiosity.
- [ ] Technical terms are translated when the audience is non-technical.
- [ ] The tone is appropriately cautious when evidence is directional.
## Consequence - Is it safe to use?
- [ ] What bad decision could result from overstating certainty?
- [ ] Could a metric be optimized at the expense of a guardrail?
- [ ] Could seasonality, data quality, or definition changes explain the movement?
- [ ] Should this be positioned as a finding, hypothesis, or recommendation?
Final check: label the main claim as fact, interpretation, or hypothesis.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 468k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |