Design a voluntary / confidential aviation safety reporting system: the intake form, the de-identification and handling workflow, the feedback loop, and the reporter-protection assurances — per the ICAO Annex 19 Safety Promotion pillar. Use this skill to build or review a confidential safety reporting scheme for a named operator, airport, or AMO. Grounds in KB-STD-ICAO-ANNEX19, runs the de-identification scrub FIRST (reporter identity protection is load-bearing — names, role/route/base/flight, and narrative re-identifiers are tokenised to role labels, the re-identification key held separately), and makes the reporter-protection promise a mechanical pre-condition. Decision-support only; a competent person must review the output.
Design a voluntary / confidential aviation safety reporting system: the intake form, the de-identification and handling workflow, the feedback loop, and the reporter-protection assurances — per the ICAO Annex 19 Safety Promotion pillar. Use this skill to build or review a confidential safety reporting scheme for a named operator, airport, or AMO. Grounds in KB-STD-ICAO-ANNEX19, runs the de-identification scrub FIRST (reporter identity protection is load-bearing — names, role/route/base/flight, and narrative re-identifiers are tokenised to role labels, the re-identification key held separately), and makes the reporter-protection promise a mechanical pre-condition. Decision-support only; a competent person must review the output.
The voluntary / confidential safety reporting skill (ICAO Annex 19 Pillar 4 — Safety Promotion). For a named operator, airport, or AMO it designs the reporting system: the intake form, the de-identification and handling workflow, the feedback loop, and the reporter-protection assurances. De-identification is load-bearing here — reporter names, the reporter's role/route/base/flight, exact dates, and any narrative detail that could re-identify a reporter are tokenised to role labels the skill reasons about the content, and any re-identification key is held in a separate custodian artifact, never in the circulated design. The just-culture promise — "you can report without being identified" — becomes a mechanical pre-condition, not a hope.
## Output format
before
When to use this skill
Use this skill when the user needs a confidential / voluntary safety reporting system designed or reviewed for a named operator/airport/AMO. Trigger phrases: "design our confidential reporting scheme", "build a voluntary safety reporting system", "how do we protect reporter identity", "set up our hazard reporting intake and feedback loop". If the request is vague, the Workflow intake forces the named operator and the reporting scope first. It designs the reporting system; the just-culture policy is aviation-just-culture-policy, and the whole SMS is aviation-sms-builder.
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.
Ask the operator's certificating authority before aligning to a State programme
Workflow
Open with a structured multi-step intake — MCQ where the answer space is enumerable, free-text where it is open. Ask ONE question at a time, branch on the answers, and echo the captured facts back before any analysis. Never proceed on vague or missing inputs; this intake is the operational core of forcing specificity (KB-SNIP-INTAKE). (Intake is a Workflow convention, not a sixth block.)
De-identification is LOAD-BEARING and runs FIRST — reporter-identity protection is the point of the artifact:
The full typed/branched intake Q-table — the named operator, the scheme-type branch
(confidential/voluntary/anonymous — the de-identification trigger), the protection-basis
jurisdiction branch (India → KB-REG-IN-DGCA, Unknown → Annex 19 Appendix 3 + legal-review
flag, never assert immunity the law doesn't grant), the MOR interface, the named custodian +
re-id-key handling, the feedback loop, the SLA/retention, and the optional de-identified sample
report — lives in references/intake.md (the intake-coverage manifest + de-id-aware
echo-back, role labels only + refuse-on-vague anchors). Run it one question at a time, branch on
the answers, and echo the confirmed operator + scheme type + custodian arrangement back
(role labels only, never a reporter name) before any drafting. Then design (a) the intake form, (b) the de-identification + handling workflow (de-id at the earliest point; the re-identification key held by the named custodian, apart from the circulated design), (c) the feedback loop, and (d) the reporter-protection assurances. No reporter is ever named in the circulated design; no re-identification key is embedded.
Then: validate the draft against references/QUALITY_CHECKLIST.md → produce the output via the Output format section below. The domain method (the reporting-system design) 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.
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
Moderate fan-out (the De-identifier runs FIRST as a sequential dependency — and here it is
the load-bearing job, not a formality):
De-identifier — runs FIRST; scrub EVERY reporter identifier (name, role/route/base/flight,
exact dates, narrative re-identifiers) into role labels before any sibling sees the content.
Returns the re-identification key SEPARATELY to the orchestrator (for the named custodian), never
to a sibling and never into the design.
Researcher — from the SCRUBBED inputs only, gather the operator/scheme facts and the Annex 19
Pillar 4 confidential-reporting criteria (KB-STD-ICAO-ANNEX19). SCOPE-OUT: does not draft.
Drafter — design the intake form, the de-id/handling workflow, the feedback loop, and the
reporter-protection assurances; no reporter named, no key embedded. SCOPE-OUT: does not re-identify.
Critic/QA (MANDATORY) — the Aviation-SMS persona (KB-SNIP-ARCHETYPES): the design protects
reporter identity (role labels, no narrative re-identification, key held separately), the feedback
loop is real, and ZERO reporter-identity leak (a leak is a de-id hard-fail, not a FLAG). Runs the
per-skill SME sign-off checklist in references/sme-review.md (decision-support; precedes —
never replaces — the human competent-person review).
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.
