Structures a principal-hazard management plan (PHMP) for a named mining principal hazard — ground/strata failure, inrush, fire/explosion, ventilation, mobile-plant interaction and others: hazard analysis, a hierarchy-ranked control suite, critical-control linkage to ICMM CCM, and monitoring. Use it to develop a PHMP for a mine's principal hazard or structure the PHMP workshop. Assistive: it structures the multidisciplinary workshop and never an autonomous artifact — the mine team owns the engineering judgement.
Structures a principal-hazard management plan (PHMP) for a named mining principal hazard — ground/strata failure, inrush, fire/explosion, ventilation, mobile-plant interaction and others: hazard analysis, a hierarchy-ranked control suite, critical-control linkage to ICMM CCM, and monitoring. Use it to develop a PHMP for a mine's principal hazard or structure the PHMP workshop. Assistive: it structures the multidisciplinary workshop and never an autonomous artifact — the mine team owns the engineering judgement.
An assistive (Tier-4) skill that structures a principal-hazard management plan (PHMP) for a named mining principal hazard — ground/strata failure, inrush, fire/explosion, ventilation failure, mobile-plant interaction, fall from height, hazardous energy or respirable dust: hazard analysis (HIRA structure + risk_matrix), a hierarchy-ranked control suite (controls, critical controls flagged), critical-control linkage to ICMM CCM (icmm-critical-control-management), and monitoring (smart_actions). It grounds in KB-STD-ICMM-CCM / . It — the mine team owns the engineering judgement.
## Output format
KB-DATA-MINING-HAZARDS
structures the multidisciplinary workshop, never an autonomous artifact
When to use this skill
Use this skill to develop a PHMP for a mine's principal hazard or structure the PHMP workshop — for a named principal hazard. It is assistive: it frames and records the team's analysis, never an autonomous plan. It builds on icmm-critical-control-management for the critical-control linkage. If the request is vague, the Workflow intake forces the named principal hazard first.
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.
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.
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.
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.
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.
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.
Open with a structured multi-step intake — MCQ where the answer space is enumerable, free-text where it is open; one question at a time, branch on the answers, echo the captured facts before any structuring; refuse on a vague subject and never invent (KB-SNIP-INTAKE).
Step 0 — Structured intake (run this first, one question at a time)
The full typed, branched Q-table — the commodity × mine-type branch driver, the principal-
hazard selection, the existing-controls + monitoring baseline, the rating-scheme confirm,
the contributing-disciplines roles, the echo-back and the refuse-on-vague anchors — lives in
references/intake.md (self-contained; it shares ~80% of its surface with
icmm-critical-control-management per D-04 but is kept as a separate file). Must-ask
dimensions: the commodity / mine type (sets the hazard mechanisms + control families),
the named principal hazard + mine scenario, and the existing controls + monitoring
data. Then (PHMP structure): run the HIRA structure for the named hazard and risk-rate
on the org matrix (risk_matrix); build the control suite hierarchy-ranked (controls /
KB-SNIP-HOC) — a PPE/admin-only treatment of a principal hazard is flagged, not accepted;
link the critical controls to the ICMM CCM (icmm-critical-control-management /
KB-STD-ICMM-CCM), performance + verification carried over; define monitoring with owner
due date (smart_actions). Where the team has not supplied an engineering value, record
[GAP] — never fabricate. Validate against references/QUALITY_CHECKLIST.md, then produce
the PHMP. This is workshop structuring for the team, not an autonomous plan.
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.
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.
Step 4 — SME review & sign-off (MANDATORY, before any output): run the skill-specific
SME persona sign-off in references/sme-review.md (the principal-hazard / major-hazard
management specialist, with the assistive autonomy test) — model QA, decision-support, FLAGs
non-blocking; workshop-structuring only, the mine team owns the engineering judgement and a
competent person signs off.
Simple single-subject tasks run single-threaded — no subagents.
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:
Build report.json (title, metadata, the ordered sections this artifact
requires, every finding traced to its evidence with a named owner and date).
Resolve branding: the user's brand.yaml overrides the Eyekyam default.
Render both DOCX and PDF from the one report.json via the shared engine.
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.
