# Policy Story Explainer

> Rewrites long policy, compliance, HR, legal, or governance documents into accurate story-led explanations. Use this skill when the user wants a policy made relatable and scenario-based without watering down obligations. Do not use when/for HTML page packaging (use policy-html-explainer) or inventing policy that is not in the source.

- Skill: `jagreehal/policy-story-explainer` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add jagreehal/policy-story-explainer`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jagreehal/policy-story-explainer/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- Author: jagreehal (https://skillmd.com/u/jagreehal)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/jagreehal/policy-story-explainer

---


# Policy Story Explainer

## Critical rules

- Preserve meaning, obligations, thresholds, exceptions, definitions, and consequences.
- Do not invent rules; do not soften `must`/`shall`; do not widen exceptions.
- Keep numbers, dates, approval levels, defined terms, and template placeholders verbatim.
- Separate policy quote, explanation, and scenario visually/structurally.
- Flag ambiguity: "The policy is not explicit on this point."
- Before rewriting, read [references/output-format.md](references/output-format.md), [references/writing-style.md](references/writing-style.md), and [references/examples.md](references/examples.md).

## Workflow

1. Read the three reference files above (mandatory).
2. Read the policy; extract rules, duties, permissions, exceptions, risks, consequences.
3. Group into themes; for each write scenario, plain-English meaning, verbatim rule, what to do, why it exists, what goes wrong if ignored.
4. Preserve source references (section/clause/page) where available.
5. For long/high-stakes policies, lead with an executive summary then the full story-led version (examples §6 shape).
6. Flag legal/safeguarding/medical/financial/regulatory items for human review.
7. Run Validation.

## Resources

- [references/output-format.md](references/output-format.md) — templates and section structure. Read before writing output.
- [references/writing-style.md](references/writing-style.md) — tone, audience tuning, anti-slop. Read before drafting prose.
- [references/examples.md](references/examples.md) — WRONG vs CORRECT fidelity traps and full miniature. Read before/during drafting.

## Validation

- [ ] Mandatory language intact (`must`/`shall` not softened)
- [ ] Thresholds, placeholders, source refs unchanged
- [ ] Exceptions present and not widened
- [ ] Ambiguity flagged; no invented advice
- [ ] Long docs: executive summary drops no obligation
- [ ] Genuinely easier to read than the source

## Constraints

- Ask if audience, tone, or "make it friendlier" could change meaning.
- Sibling for HTML packaging: `policy-html-explainer`.