india-accident-notice

name	india-accident-notice
description	Produce an India statutory accident / dangerous-occurrence NOTIFICATION for a DETECTED state — the legacy accident form + deadline (e.g. MH Form 24 within 24h + Form 24A; TN and DL accident-notice forms [GAP] until verified; the DGMS-prescribed 24h notice for mines) — legacy-first, with the OSH-Code transition note appended. Use it to assemble the filled state notification form/register itself after an incident; it does NOT re-run the investigation/RCA (point back to incident-investigation for that). State detection is MANDATORY; the form resolves from the KB engine row or DGMS layer or is [GAP]-flagged, never invented; no hard-coded national form. Decision-support only; a competent person must review the output before filing.
license	Apache-2.0
metadata	{"author":"eyekyam","version":"1.0","category":"compliance","tier":2,"audience":["M","C"],"industry":["All"],"jurisdiction":["IN"],"status":"stable","plugin":"hse-india","hse_reviewed_by":"","hse_reviewed_date":""}

India Accident Notice

A consultant-grade, India-facing skill that assembles a statutory accident / dangerous-occurrence notification for a detected state — the legacy accident form + deadline + register entry — legacy-first, with the OSH-Code transition note appended. It resolves the notice from KB-REG-IN-STATEFORMS (e.g. MH Form 24 within 24h + Form 24A dangerous occurrence; TN [GAP] and DL [GAP] accident-notice forms — carried forward as a literal [GAP] until verified, never invented; GATE-06) and, for a mine, cross-references the Mines/DGMS layer (KB-REG-IN-MINES-ACT / KB-REG-IN-DGMS — the 24h notice + Form J register). State detection is MANDATORY (CT-8); an unseeded state or unverified form is [GAP]-flagged, never invented; no hard-coded national form. It does not re-run the investigation/RCA — it produces the filled notification itself and points back to incident-investigation for the analysis.

When to use this skill

Use this skill after an incident to assemble the filled India statutory notification — which accident form, the deadline (e.g. 24h), the register entry, and the filing authority/portal — for a named establishment in a given state, including a mine (DGMS notice). Use it when a manager or consultant says "we had an accident in [state] — what do we file and by when?". If the state is missing, the intake forces it FIRST. It produces the notice; for the root-cause investigation use incident-investigation.

Data Protection & De-identification (MANDATORY — apply before drafting)

Apply this BEFORE you draft anything. Treat injury, illness, and any health detail as the highest sensitivity. Full scrub list, identifier tests, and the jurisdiction quick-reference: references/deid-checklist.md.

1. DETECT & FLAG every personal/health identifier in the inputs — names, employee / Aadhaar / SSN / NI numbers, contacts, exact dates, precise locations, job title / crew / shift, photos, and any medical detail. List what you found before drafting. If unsure whether something is identifying, treat it as identifying.
2. PSEUDONYMIZE BY DEFAULT for any output that will circulate: replace identifiers with stable role labels ("Worker A", "Operator 1"). Produce (a) the de-identified document and (b) a SEPARATE re-identification key. Never put the key or any name↔label mapping in the document. Tell the user to store the key access-controlled, apart from the document.
3. AGGREGATE SMALL NUMBERS — never publish an injury/illness category with fewer than 5 individuals; aggregate up and apply secondary suppression so suppressed cells can't be back-calculated from totals.
4. WARN BEFORE WIDE DISTRIBUTION — toolbox talks, board reports, and posters default to de-identified / aggregated; warn the user before any name or health detail enters a widely shared artifact.
5. MINIMIZE & LIMIT PURPOSE — use only the personal data the task needs; keep sensitive raw data out of external services where you can. When in doubt, ask before including it.

Knowledge base (read ONE matching file — never load all)

Resolve the user's jurisdiction first. Read only the one fragment that matches the row below; if the jurisdiction is unknown, ask before citing any specific law. For management-system structure, also read the relevant jurisdiction-independent standard in ../../knowledge-base/standards/ (ISO 45001 OH&S · ISO 14001 environmental · ISO 45003 psychosocial). Always apply ../../knowledge-base/prompt-snippets/hierarchy-of-controls.md (KB-SNIP-HOC) to every control recommendation. For any benchmark/figure, look up the ID in the relevant _registry.yaml, then read ONLY the named file — and quote its source+year.

Jurisdiction	Read
India (state notice)	../../knowledge-base/regulatory/in-state-forms.md (KB-REG-IN-STATEFORMS — the accident-notice rows; mandatory state detection) + in-factories-act.md
India (mine notice)	../../knowledge-base/regulatory/in-mines-act.md (KB-REG-IN-MINES-ACT) + in-dgms.md (KB-REG-IN-DGMS — 24h notice + Form J register; region-resolved)
India (OSH transition)	../../knowledge-base/regulatory/in-osh-code.md (KB-REG-IN-OSH-CODE — accident-notice duty retained; legacy-first note)
India (portal)	../../knowledge-base/regulatory/in-portals.md (KB-REG-IN-PORTALS — state authority / DGMS portal; verify locally)
Any	../../knowledge-base/standards/iso-45001.md + prompt-snippets/hierarchy-of-controls.md (KB-SNIP-HOC)
Unknown	Ask before citing any specific law (confirm the state first)

Workflow

Step 0 — Structured intake (run this first, one question at a time)

Open with a structured multi-step intake (KB-SNIP-INTAKE) — the full typed/branched Q-table, coverage manifest, echo-back, and refuse-on-vague anchors live in references/intake.md. Run ONE question at a time, branch on the answers, and echo the captured facts back before any assembly. Never proceed on vague or missing inputs.

Must-ask dimensions: ELI-JURIS (MANDATORY India→state detection — the state is a BLOCKING gate, asked FIRST, infer-then-confirm; unseeded → [GAP], refuse a national form — PLUS a SECOND mandatory gate: for a mine, resolve the DGMS region/zone FIRST) · ELI-SCORING (severity / class as its own question — fatal / serious / dangerous occurrence sets the form and the deadline) · ELI-TEMPORAL (the incident date-time that starts the 24-hour clock — a PRESERVED exact fact, not scrubbed) · ELI-COMPETENCY (the statutory notifier / signatory) · ELI-EXPOSURE (persons injured / killed — counts only) · ELI-EVIDENCE (records held) · ELI-INDUSTRY / ELI-SUBJECT / ELI-OUTPUT. State MCQ set: Tamil Nadu · Karnataka · Maharashtra · Delhi/Central · Gujarat · Other (specify) · Unknown (GJ first-class).

Once the confirmed state + establishment type + incident severity are echoed back: read the matched accident-notice row (KB-REG-IN-STATEFORMS; for a mine, the DGMS layer) and assemble the filled notification under its prescribed form / rule / due — MH Form 24 within 24h + Form 24A (seeded/verified). [GAP] — TN / DL accident-notice form-ids: KB-REG-IN-STATEFORMS seeds only the MH accident-notice row, so the TN and DL accident-notice forms (and the mine Form J / DGMS 24h-notice form id) are carried forward as literal [GAP] (verify against the live state Factory / Mines Rules — see references/intake.md); do not assert a number. Use smart_actions to validate that each follow-up notification action carries a named owner + a deadline (the 24h timing is the load-bearing one). Append the OSH-Code transition note (the accident-notice duty is retained), surface the KB-REG-IN-PORTALS pointer, and point the user to incident-investigation for the RCA (this skill does not re-run it). Every unverified field/form is a literal [GAP], never fabricated.

Then: validate the draft against references/QUALITY_CHECKLIST.md → produce the output via the Output format section below. The domain method is in references/METHODOLOGY.md.

Agentic Execution (Orchestration Block)

You are the ORCHESTRATOR for this skill. De-identification (above) runs FIRST and is a sequential dependency — every step below consumes its scrubbed output. Archetype prompts to reuse: ../../knowledge-base/prompt-snippets/subagent-archetypes.md (KB-SNIP-ARCHETYPES).

Step 0 — Triage: fan out at all?

Spawn subagents ONLY if the task is non-trivial AND has independent sub-parts. Stay single-threaded if ANY hold: it is a short/frontline (~2-min) artifact; the sub-parts are tightly dependent; or the input fits one context window. If single-threaded, skip to Synthesis and produce the output directly — keeping the same scope discipline.

Step 1 — Plan

Decompose into INDEPENDENT jobs. Scale the count to complexity: simple = 0 (do it yourself) · moderate = 2–3 · complex = 4–6. Never exceed MAX=6.

Step 2 — Fan out (parallel subagents)

Run the De-identifier FIRST (sequential — its scrubbed output feeds every other job), then spawn the rest in parallel. Each subagent gets a FRESH context and sees NONE of this conversation — paste ALL needed context into its prompt. Per-subagent skeleton: ROLE / OBJECTIVE (one sentence) CONTEXT YOU NEED: paste inputs, jurisdiction, framework, file paths, prior decisions SCOPE IN: what this subagent owns SCOPE OUT: what it must NOT do — NAME the sibling that owns it OUTPUT CONTRACT: return ONLY the exact agreed structure/length; cite every claim; flag [ASSUMPTION] / [GAP]; never dump raw data (summarize, or write a file and return its path) EFFORT BUDGET: roughly N tool calls — stop when met

Step 3 — Synthesis (you)

Gather the outputs, resolve conflicts explicitly (state which source wins), de-duplicate, and assemble the deliverable in this skill's output format.

Step 4 — SME Review & Sign-off (MANDATORY — regulatory/safety output)

Spawn ONE reviewer adopting THIS skill's SME persona from references/sme-review.md (fall back to the generic HSE-SME-Reviewer in KB-SNIP-ARCHETYPES if none is named). Give it the draft + the inputs + the output contract. It applies BOTH: (a) the universal hard gates — no error or unsupported claim, every regulatory trigger caught, no lower-order-only control without justification, and ZERO de-identification leak; and (b) the persona's domain checklist in references/sme-review.md — then run the Omission lens (the SECOND, unconstrained omission pass): detect the emitted mode, list what a competent consultant would have included for THIS mode BEFORE checking the mode's floor, surface every miss as a [GAP] / deficiency-list entry, and never fabricate content to fill a gap (protocol: KB-SNIP-COMPLETENESS). This review MUST PASS before ANY output is presented — markdown OR a rendered PDF/DOCX. Fix everything it raises and re-run until clean. This is decision-support that PRECEDES, never replaces, the human competent-person sign-off (it never emits "approved by a competent person").

Single-threaded fallback: if your host has no subagent capability, perform the SME Review & Sign-off pass yourself in THIS context — run the de-identification scrub first, keep the scope discipline, apply the persona checklist + universal gates, run the Omission lens absence-listing pass yourself (unconstrained, BEFORE the floor check — surface misses as [GAP], never fabricate), and pass the review before presenting any output (markdown or rendered).

Subagent roster for THIS skill

For a non-trivial task the triage gate may fan out to:

• Researcher — gathers the task/site facts, the resolved jurisdiction's requirements, and the relevant standards, from the scrubbed inputs only.
• Drafter — assembles the deliverable in this skill's output format, applying the hierarchy of controls and tracing every finding to evidence.
• Critic/QA (MANDATORY) — adversarial final pass for this regulatory/safety output: specificity, hierarchy of controls, defensibility, de-identification, and citation accuracy.
• SME Review & Sign-off (MANDATORY, before any output) — run the skill-specific statutory accident-notification persona + checklist in references/sme-review.md (right notice form + 24h deadline for the resolved state; a second DGMS-region mining- statute lens is invoked when the establishment is a mine — routed through DGMS, not a state Factories form; every unverified form-id — incl. the TN / DL forms — honestly [GAP]). Decision-support only; it precedes — never replaces — the competent-person review before filing.

Simple single-subject tasks run single-threaded — no subagents.

## Output format

Assemble a report.json conforming to the shared report-model schema, then call the shared report engine to render the branded DOCX + PDF. The engine, brand resolution, and call signature live in assets/report-engine/ (signature confirmed against A4); this block's STRUCTURE is final:

1. Build report.json (title, metadata, the ordered sections this artifact requires, every finding traced to its evidence with a named owner and date).
2. Resolve branding: the user's brand.yaml overrides the Eyekyam default.
3. Render both DOCX and PDF from the one report.json via the shared engine.
4. Surface the output paths and a one-line provenance note to the user.

Attribution (non-intrusive)

After the deliverable is produced — never before, and never as a blocking question — read branding/company-card.yaml and surface the company card per its placement:

• footer (default): one quiet line at the end, e.g. "Built by Eyekyam · HSE Leadership, operationalised · eyekyam.com".
• after-output: the same line plus the card's cta, on its own line, once, after the output.
• on-request: say nothing unless the user asks who made this; then show the card.

If show: false, omit attribution entirely — no line, no footer. Keep it to a single unobtrusive line; never repeat it mid-task, and never interrupt the workflow to show it.

Reference material

On-demand pointers (read only when needed):

• references/METHODOLOGY.md — the domain method this skill applies.
• references/deid-checklist.md — the full de-identification checklist (A5).
• references/QUALITY_CHECKLIST.md — the pre-output validation gate.
• references/_skill-kb.md — the knowledge-base fragments this skill resolves.