intake-audit
Use when a quest does not start from a blank state and the agent must first audit, trust-rank, and reconcile existing baselines, results, drafts, or review materials before choosing the next anchor.
Best for Projects with existing code…Works with GitHub
⌘source
- author
@ResearAI- language
- TypeScript
★2.3kstars
245forks
Apr 19, 2026
✦overview.md
Key Features
- ·Audits existing project state and materials
- ·Reconciles multiple baselines or drafts into one trustworthy starting point
- ·Follows structured interaction discipline with user updates
- ·Avoids shell commands during audit phase
- ·Provides route recommendations after audit completion
Use Cases
- →Reviewing existing code review comments before starting new work
- →Auditing previous test results to establish current project status
- →Reconciling conflicting documentation drafts into a single source of truth
- →Evaluating existing security findings to determine next steps
Best for
- ✓Projects with existing code reviews or documentation
- ✓Teams inheriting codebases with previous work
- ✓Situations requiring audit of existing materials before proceeding
Not ideal for
- !Starting projects from scratch
- !Simple one-off tasks without existing context
- !Situations requiring immediate shell execution
FAQs
name
intake-audit
description
Use when a quest does not start from a blank state and the agent must first audit, trust-rank, and reconcile existing baselines, results, drafts, or review materials before choosing the next anchor.
skill_role:companion
Intake Audit
Use this skill when the quest already has meaningful state and the first job is to normalize that state instead of restarting the canonical research loop from zero. The goal is to recover one trustworthy starting state from messy existing assets, not to re-audit everything forever.
Interaction discipline
- Follow the shared interaction contract injected by the system prompt.
- For ordinary active work, prefer a concise progress update once work has crossed roughly 6 tool calls with a human-meaningful delta, and do not drift beyond roughly 12 tool calls or about 8 minutes without a user-visible update.
- Message templates are references only. Adapt to the actual context and vary wording so updates feel natural and non-robotic.
- If a threaded user reply arrives, interpret it relative to the latest intake-audit progress update before assuming the task changed completely.
- When the audit reaches a durable route recommendation, send one richer
artifact.interact(kind='milestone', reply_mode='threaded', ...)update that says what state is trusted, what still needs work, and which anchor should run next.
Tool discipline
$install
1-click copynpx skills add ResearAI/DeepScientist --skill intake-auditSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
3/ 5
goodMostly clear, but there are still a few confusing or poorly structured parts.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
2/ 5
lowSome hints are present, but an agent still has to guess many steps.