Bocw compliance

Bocw Compliance

A consultant-grade, India-facing skill that assesses BOCW (Building & Other Construction Workers Act 1996 + Rules) statutory compliance for a named construction establishment — registration, the 1% welfare cess, the Form XXV annual return (by ~15 Feb), the Safety Officer / Safety Committee thresholds, and accident notification — grounded in KB-REG-IN-BOCW. State detection is MANDATORY (CT-8): the operative returns/portal are state Welfare Board specific, so the Workflow resolves the state FIRST. State-specific values resolve from the KB row or are [GAP]-flagged, never invented; no hard-coded national form. The OSH-Code transition (BOCW subsumed) is noted (legacy-first).

When to use this skill

Use this skill to produce a BOCW compliance gap-list for a construction site in a given state — which establishment/worker registrations apply, the cess obligation, which Welfare Board return is filed and when (Form XXV), the Safety-Officer/Committee thresholds, and the accident-notice duty. Use it when a manager or consultant asks "are we BOCW-compliant in [state]?". If the state is missing, the intake forces it FIRST. It assesses BOCW compliance; it does not assemble the Factories-Act return (that is factories-act-returns).

<!-- hse:block:deid:start -->

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.

<!-- hse:block:deid:end --> <!-- hse:block:kb-selection:start -->

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.

<!-- hse:block:kb-selection:end --> <!-- The jurisdiction ROWS below live BELOW the :end marker: per-skill, presence-only (rule-2 presence check, never byte-diffed). Author the rows for the jurisdictions this skill serves; rule-9 checks every path/ID resolves against the KB registries. -->

Jurisdiction	Read
India (BOCW)	../../knowledge-base/regulatory/in-bocw.md (KB-REG-IN-BOCW — registration/cess/Form XXV/safety-officer thresholds) + in-state-forms.md (KB-REG-IN-STATEFORMS — mandatory state detection)
India (OSH transition)	../../knowledge-base/regulatory/in-osh-code.md (KB-REG-IN-OSH-CODE — BOCW subsumed; legacy-first note)
India (portal)	../../knowledge-base/regulatory/in-portals.md (KB-REG-IN-PORTALS — state Welfare Board 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 gap-list. Never proceed on vague or missing inputs.

Must-ask dimensions: ELI-JURIS (MANDATORY India→state detection — the state is a BLOCKING gate, asked FIRST; the BOCW return/portal is administered by the state Welfare Board, so it is state-specific; unseeded → state-specific values [GAP]) · ELI-EXPOSURE (the three threshold drivers as separate numbered facts — peak headcount (≥10 → registration; notified threshold → Safety Officer/Committee), cost of construction (→ 1% cess), and the direct-vs-contract split) · ELI-BASELINE (what's already in place — the gap-list is computed against it) · ELI-COMPETENCY (principal employer vs contractor — who registers, who pays cess) · ELI-OBLIGATIONS (which duties to check) · ELI-TEMPORAL (filing-cycle position — Form XXV due ~15 Feb) · ELI-INDUSTRY / ELI-OUTPUT / ELI-SCOPE / ELI-SUBJECT. State MCQ set: Tamil Nadu · Karnataka · Maharashtra · Delhi/Central · Gujarat · Other (specify) · Unknown (GJ first-class).

Once the confirmed state + establishment profile + obligation are echoed back: read KB-REG-IN-BOCW for the duty set and KB-REG-IN-STATEFORMS for the Form XXV anchor; produce the compliance verdict / gap-list (each gap with the cited rule, a HoC-ranked corrective control via controls, a named owner and a date). Cite the Form XXV annual return as the verified anchor; mark every state-specific value (Safety-Officer headcount, accident-notice form/timing, cess due date) [GAP] where the KB does not supply a verified value. Append the OSH-Code transition note and the KB-REG-IN-PORTALS (state Welfare Board) pointer.

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.

<!-- hse:block:orchestration:start -->

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).

<!-- hse:block:orchestration:end -->

Subagent roster for THIS skill

<!-- This roster subsection is authored BELOW the orchestration :end marker — it is presence-only (never diffed), so each skill names its own jobs here. -->

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 BOCW / construction-labour-welfare persona + checklist in references/sme-review.md (right state Welfare Board, right duty-holder, correct cess base). Decision-support only; it precedes — never replaces — the competent-person review.

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

<!-- hse:block:report-output:start -->## 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.

<!-- hse:block:report-output:end --> <!-- hse:block:attribution:start -->

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.

<!-- hse:block:attribution:end -->

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.