india-state-form-finder

name	india-state-form-finder
description	Resolve an India statutory obligation (law, state, obligation) to the prescribed LEGACY state form + citing rule + due date + filing portal, with MANDATORY state detection and the appended OSH-Code transition note. Use it to find which Factories-Act / BOCW return or register a named establishment files in its state, when, and where. State detection is mandatory (ask or infer-from-address then confirm); the form resolves from the KB state-form engine row — never a hard-coded national form; an unseeded state yields [GAP] + a refusal to invent a national form; the OSH-Code transition is noted (legacy-first). Decision-support only; a competent person must review the output.
license	Apache-2.0
metadata	{"author":"eyekyam","version":"1.0","category":"compliance","tier":1,"audience":["M","C"],"industry":["All"],"jurisdiction":["IN"],"status":"stable","plugin":"hse-india","hse_reviewed_by":"","hse_reviewed_date":""}

India State Form Finder

The legacy-first state-form engine skill. Given an India statutory obligation (law, state, obligation) it resolves the prescribed legacy state form + citing rule + due date + filing portal from KB-REG-IN-STATEFORMS, then appends the OSH-Code transition note. State detection is MANDATORY (CT-8): the Workflow resolves the user's state FIRST — asking explicitly, or inferring from a supplied address then confirming — and never cites a form on an unconfirmed or unseeded state. For an unseeded state it emits a literal [GAP] and refuses to invent a national form number (KB-02 legacy-first discipline). The OSH-Code direction of change is noted (legacy-first); portal pointers resolve through KB-REG-IN-PORTALS.

When to use this skill

Use this skill to find which statutory form a named India establishment files for a given obligation, when it is due, the rule that prescribes it, and where it is filed — for the Factories Act state returns/registers (TN Form 22 / KA Form 20 / DL Form 21; MH and GJ [GAP] until verified) and the BOCW Form XXV annual return. Use it when a manager or consultant asks "what form do we file in [state] for [obligation]?". If the state is missing or vague, the Workflow intake forces it FIRST — a wrong state is a wrong statutory form. It resolves forms; it does not assemble the filled return (that is factories-act-returns) or run an RCA (that is 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 form)	../../knowledge-base/regulatory/in-state-forms.md (KB-REG-IN-STATEFORMS — the (law,state,obligation) engine; mandatory state detection) + in-factories-act.md
India (OSH transition)	../../knowledge-base/regulatory/in-osh-code.md (KB-REG-IN-OSH-CODE — append the legacy-first transition note)
India (portal)	../../knowledge-base/regulatory/in-portals.md (KB-REG-IN-PORTALS — state filing-portal pointer; 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 resolution. Never proceed on vague or missing inputs.

Must-ask dimensions: ELI-SCOPE (identify-vs-assemble) · ELI-JURIS (MANDATORY India→state detection — the state is a BLOCKING gate, asked FIRST, infer-then-confirm; unseeded → [GAP], refuse a national form) · ELI-INDUSTRY (establishment type — a mine routes to DGMS) · ELI-SUBJECT (the obligation) · ELI-TEMPORAL (filing year / half) · ELI-OUTPUT (reader). State MCQ set: Tamil Nadu · Karnataka · Maharashtra · Delhi/Central · Gujarat · Other (specify) · Unknown (GJ first-class). The GJ form value is [GAP] (verified-absent) — surface it, never substitute.

Once the confirmed state + law + obligation are echoed back: read the matched KB-REG-IN-STATEFORMS row and return its form / rule / due / portal as the primary (legacy-first) answer, append the row's osh_transition note (point to india-osh-code-pack for the transition mapping), and surface the KB-REG-IN-PORTALS pointer. If the matched row's form is [GAP] (e.g. the GJ row), say so explicitly — never substitute a guessed value.

Then: validate the draft against references/QUALITY_CHECKLIST.md → produce the output via the Output format section below. The domain method (the resolution algorithm) 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

• Single-threaded by design — no subagents. (Replace with this skill's named fan-out jobs if the triage gate warrants them.)
• SME Review & Sign-off (MANDATORY, before any output) — run the skill-specific domain persona + checklist in references/sme-review.md. Single-threaded skill: the SME pass runs inline via the orchestration single-thread fallback, not as a spawned subagent. Decision-support only; it precedes — never replaces — the competent-person review.

## 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.