Message Parser RE-India

Parse raw WhatsApp exports (TXT or JSON) into normalized message objects with `timestamp`, `sender`, and `content`. Use when users ask to parse chat export,...

Security Scan

The skill's requirements and instructions are consistent with its stated purpose: it parses WhatsApp exports into timestamp/sender/content arrays and requests no extra credentials, binaries, or installs.

Purpose & Capability

Name and description match the runtime instructions. The skill is instruction-only, requires no binaries, env vars, or installs, and the provided JSON schema matches the described output format. Nothing requested appears unrelated to parsing WhatsApp exports.

Instruction Scope

SKILL.md stays narrowly focused on parsing, normalization, validation, and error reporting. It explicitly forbids extracting leads, writing to storage, summarizing, or sending outbound communications. It relies on Supervisor to supply file contents and references a recommended chain (which includes a 'lead-extractor') — users should be aware that chaining this skill with downstream skills may expose parsed content to other capabilities even though this skill itself promises not to extract or store data.

Install Mechanism

No install spec or code files that would be written to disk; instruction-only skills are lowest risk in install mechanism terms.

Credentials

No environment variables, credentials, or config paths are requested. The skill does require access to input text/file contents (provided by Supervisor), which is appropriate for its purpose but is a vector for exposing sensitive chat data if the runtime environment or Supervisor is untrusted.

Persistence & Privilege

always:false and no behavior described that modifies other skills or system-wide settings. The skill explicitly prohibits writing to databases/files and bypassing Supervisor routing.

Assessment

This skill appears coherent and limited to parsing WhatsApp exports into structured message objects. Before installing or using it, consider: (1) the skill will process potentially sensitive chat data (PII); ensure you trust the runtime and Supervisor that supplies file contents; (2) the SKILL.md recommends chaining to downstream skills (e.g., lead-extractor, storage) — review and trust those downstream skills before chaining, because they could store or transmit parsed data even if this parser does not; (3) the skill has no provenance (unknown source/homepage), so prefer using it only in a controlled environment or after inspecting behavior in a sandbox; (4) confirm it handles the specific export formats and encodings you have and test on non-sensitive samples first.

Message Parser

Convert raw chat exports into a strict array of parsed message objects.

Quick Triggers

• Parse this WhatsApp export file.
• Convert this group dump into structured messages.
• Clean this TXT chat into timestamp/sender/content rows.

Recommended Chain

message-parser -> lead-extractor -> india-location-normalizer -> sentiment-priority-scorer -> summary-generator -> action-suggester -> lead-storage

Execute Workflow

1. Accept raw WhatsApp export input as plain text, JSON, or file contents already loaded by Supervisor.
2. Detect and parse the source format, including WhatsApp export lines like DD/MM/YYYY, HH:MM - sender: message.
3. Normalize each event into exactly three fields:
   • timestamp (RFC 3339 date-time string)
   • sender (non-empty string)
   • content (string; allow empty message bodies)
4. Merge multiline continuation lines into the previous message when they do not start with a new timestamp marker.
5. Preserve message ordering. If timestamps collide, preserve original source order.
6. Ignore chat-system boilerplate as lead content (encryption notice, group created, member added) while preserving raw line fidelity for audit.
7. Validate output against references/parsed-message-array.schema.json.
8. Return only the validated array.

Enforce Boundaries

• Never infer or extract leads.
• Never write to databases or files.
• Never generate summaries or action plans.
• Never send or schedule outbound communication.
• Never bypass Supervisor routing.

Handle Errors

1. Return explicit parse errors for malformed entries.
2. Include line offsets when source lines are available.
3. Fail closed if output cannot satisfy the schema.