Data Share Review

This is a Hermes-native data-share-review workflow skill.

Why This Exists

data-share-review exists because data leaving the team had no owner: Hermes redacts identifiers in gateway chat and secrets in tool output, omh-security-safety-review reviews an agent's own exposure, and omh-legal-compliance-review reads the obligations, while nothing minimized a file's fields, kept its pseudonym mapping local, and refused to call it redacted before a scan of what actually leaves.

First Steps

• Ask where the file goes and what the destination needs it for before touching a field.
• Inventory the fields from the header and the schema before planning any masking.

Do Not Use When

• Whether the data may lawfully leave at all -- the lawful basis, a DPA, consent, or a cross-border transfer -- is a contract and compliance question; use omh-legal-compliance-review, then return here for the fields.
• The exposure is an agent's tool permissions, a secret in code, or a prompt-injection path rather than a file about to leave; use omh-security-safety-review.
• The ask is analysing the dataset itself -- trends, a cleanup, a chart; use omh-data-analysis.
• Filing the issue once its attachment is clean -- the title, labels, and reproduction steps; use omh-github-issue-intake.
• Building the training set or deciding whether to train once the corpus is clean; use omh-model-finetuning.
• Working the support queue -- triaging or answering tickets rather than exporting them; use omh-support-operations.

Examples

Good example:

• Prompt: the analytics vendor wants last month's ticket export, take the customer details out first
• Expected behavior: Ask what the vendor needs, inventory the columns from the header and per-column shape counts, drop the ones it does not need, pseudonymize the customer id with the mapping kept in a local folder, count emails, phone numbers, names, and secrets in the output with a scan that prints counts only, and write the share record.
• Why: A masking step that was never followed by a scan of the shipped file has not shown that anything came out.

Bad example:

• Prompt: I ran find and replace on the emails, so the file is clean, right
• Expected behavior: Hold the verdict at not_observed: count every class in the exact file that leaves, free-text fields included, before calling it redacted.
• Why: A find and replace covers the shapes it was given; names and account numbers in a notes column stay.

Completion Checklist

• Every field has a class and an action, and each kept field names the destination's need for it.
• The pseudonym mapping, if any, sits at a local path outside the shipped file.
• The residual scan ran on the exact file that leaves and counted every class, free text included.
• The verdict is redacted only with that scan observed; otherwise it reads not_observed.
• The share record holds destination, date, fields, row count, and digest, and no value from the file.

Recovery Notes

• If the scan cannot run in this session, hand the user the per-class scan and keep the verdict not_observed until the counts come back.
• If a class still has hits after masking, fix the field or the free text and scan again; never ship on an explained hit that was not accepted by name.

Workflow Lane

• Current lane: Research and company ops (product-docs, source-finder, web-research, research, model-optimization, inference-serving, model-finetuning, research-brief, +21 more) - research, signals, ops, and briefings.
• If intent belongs to another lane, hand back to oh-my-hermes or name the adjacent workflow.
• Shared product, routing, compatibility, and evidence rules: skill_view(name='omh-routing', file_path='references/skill-common-rail.md').

When to Use

Use when a dataset, log bundle, ticket or CRM export, or transcript excerpt is about to leave the team -- to a vendor or contractor, a public issue, a model provider, or a training corpus -- and its personal data, identifiers, and secrets must come out first. The output is a field inventory with each field's class, a minimization plan, a residual scan of the file that leaves with counts per class, and a metadata-only record of what left; OMH uploads nothing and keeps no raw data.

Strong routing signals: `data-share-review`, `data share review`, `pii redaction`, `redact pii`, `pseudonymize`, `de-identify`, `anonymize the dataset`, `residual pii`, `redact the pii`, `redact personal data`, `strip pii`, `strip the pii`, `remove pii`, `remove the pii`, `scrub pii`, `scrub the pii`, `mask pii`, `mask personal data`, `remove personal data`, `scan for pii`, `pseudonymise`, `pseudonymizing`, `pseudonymization`, `pseudonymisation`, `de-identifying`, `deidentify`, `quasi-identifier`, `quasi-identifiers`, `direct identifiers`, `anonymize this dataset`, `anonymize the data`, `anonymize the logs`, `redact the logs`, `redact these logs`

Catalog Metadata

Category: review Phase: data-share-review Hermes role: reviewer Quality tier: observed-residual-scan Reasoning demand: standard

Quality bar:

• Inventory fields from the header and the schema, read with read_file and its line limit; when a field's class is unclear, prefer a script that prints per-column shape counts, and read a row only when that still leaves it unclear, because every row read enters the session.
• Load references/data-share-method.md for the field classes, the minimization order, the pseudonymization method, the per-class scan patterns, and the quasi-identifier group check instead of recalling them.
• Count each class with search_files in its count output mode, or with a detector script run through execute_code when execute_code is in your tool list or tool_search finds it; its stdout returns, and so do stderr and any traceback, so it prints counts only and catches its own errors without echoing a value. With neither, hand the user the scan to run and keep the verdict not_observed until the counts come back.
• Hermes' privacy.redact_pii hashes user and chat identifiers in the gateway's session prompt on the platforms that allow it, and security.redact_secrets masks secret-shaped strings in tool output; neither changes a file that leaves, so neither is this scan.
• Keep inventoried, minimized, masked, scanned, and shipped as separate states for the file.

Handoff policy:

Keep the field inventory, minimization plan, residual scan result, and share record in Hermes. Field classes come from the header, the schema, and per-column shape counts; scan counts come only from an observed scan of the exact file that leaves; OMH uploads nothing, stores no raw value, and keeps no pseudonym mapping.

Required inputs:

• the file or export about to leave, and the destination it goes to
• why the destination needs it, which decides the fields it may keep
• the header or schema, and per-column shape counts when a field's content is unclear
• where the pseudonym mapping may be kept locally, when a field must stay joinable

Expected outputs:

• field_inventory/v1
• minimization_plan/v1
• residual_scan/v1
• share_record/v1

Artifact expectations:

• field_inventory/v1 lists every column, key, and free-text field with its class -- direct identifier, quasi-identifier, secret, free text, or not personal -- and the evidence for the class
• minimization_plan/v1 gives each field one action -- drop, generalize, mask, or pseudonymize -- with the destination's need for the fields it keeps, and names the local path that holds any pseudonym mapping outside the shipped file
• residual_scan/v1 records, for the exact file that leaves, the scan method and an observed count per class with zero hits or each remaining hit accepted by name, and its verdict: redacted, not redacted with the counts while a hit remains unaccepted, or not_observed when no scan ran
• share_record/v1 is metadata only -- destination, date, fields shipped, row count, and the sha256 digest of the shipped file -- and holds no value from it

Safety rules:

• Call the output redacted only after an observed residual scan of the exact file that leaves, counted per class; without one the state is not_observed, whatever the masking step reported.
• Minimize before masking: drop every field the destination does not need, because a masked field that ships still links rows back to people.
• Keep the pseudonym mapping local, outside the shipped file and its folder; a mapping that travels with the data reverses it.
• Treat free text as unscanned until the residual scan counts it: notes, comments, and transcript excerpts hide names, emails, and account numbers that a column plan never touches.
• A scan prints counts, never matched values; a hit printed to the session reaches the model provider the same way the raw file would.
• OMH uploads nothing, keeps no raw value, and records only the metadata-only share record; whether the data may lawfully leave at all is not decided here.

Runtime Evidence

Preferred harness for this skill: critic.

omh runtime record --skill data-share-review --harness critic --status started

Record observed delegation results; otherwise return not_available or not_observed. Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.

• Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes. Preserve workflow intent and stop conditions; verify before claiming completion. Reply in the user's own words and the host's own voice: its SOUL.md persona owns reply language, tone, speech level, and sentence endings, progress updates included (where it sets no language, use the one the user wrote in), and OMH shapes structure and content only; OMH's record terms (surface, lane, wrapper, handoff, evidence boundary, not_observed) stay in records and tool calls, never in the sentence the user reads unless they ask about one; and when a stop condition or a decision the user owns ends the turn, offer the next action as a question rather than declaring what will not be done.

Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.

Shared product, compatibility, topology, memory, harness, and execution rules: skill_view(name='omh-routing', file_path='references/skill-common-rail.md'). Load it when applicable; otherwise name an unavailable capability.