LISTENINGPOST

Research

Decision Precedent Search

Find prior decisions relevant to a current question.

Configure this skill

The page and the file follow your answers.

CRM
Email
Chat
Documents
Calendar
Project tools

6 of 6 systems connected

KeepDirectMissing
Your assistantSKILL.md

Download ↓ 
Morning Brief

Build a prioritized brief for today from the caller's calendar, messages, documents and project records, using Keep MCP. Read only.

1. Read today's calendar events, open assigned tasks, direct requests since the last brief and unresolved commitments.
2. Separate active incidents, decisions waiting on the caller, external deadlines and routine work. Check for replies before calling an item outstanding. Rank by consequence and time remaining.
3. Fit proposed actions around fixed meetings and flag conflicting commitments.

Result: a dated brief with urgent changes, commitments, meeting preparation and a feasible next-action list, each tied to its source.

When to use it

Find prior decisions relevant to a current question.

What it covers

Inputs

Decision question, scope, constraints.

Result

Relevant precedents, similarities/differences and applicability limits.

What it uses

CalendarEmailDocumentsSlackProject toolsClaudeKeep memory
For developers

Retrieval instructions

Resolve people, accounts and projects by stable identifiers. Use only the sources this task needs. Cite the source and date for each finding. Keep source systems unchanged.

Data sources

Google Workspace, Slack, GitHub, Claude, Keep memory.

Procedure

  1. Resolve inputs for Decision Precedent Search: topic, time_window, project_key, person. Default time window: canonical docs + last 30 days of related threads (override if caller provides time_window). Ask only for.
  2. Run keep_search with these skill-specific intents (keep meaning; adjust wording to corpus):
  3. Additional keep_search passes for residual signal:

Related skills

Research →
Deep Dive Reading List→Create a purposeful reading sequence for a defined question.Duplicate Doc Clusters→Group exact and near-duplicate documents without losing version history.Experiment Archive Search→Find prior experiments relevant to a proposed hypothesis.