Findings Capture

SkillProductivity

Lets your agent break down and manage complex multi-step tasks with enforced, verifiable steps.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Findings Capture skill

About this capability

Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration

What this skill tells your AI

The instructions your AI receives, as published by a5c-ai/babysitter in library/methodologies/planning-with-files/skills/findings-capture/SKILL.md and read by ahel’s review.

Capture and persist research findings, discoveries, and decision rationale to findings.md.

Agent

Findings Curator - pwf-findings-curator

Workflow

  1. Initialize findings.md with structured section headers
  2. Capture findings during execution with timestamps
  3. Apply 2-Action Rule: persist after every 2 operations
  4. Record decisions with supporting rationale
  5. Deduplicate and organize on final flush
  6. Analyze coverage for verification

Inputs

  • projectPath - Root path for planning files
  • phaseName - Current phase name
  • findings - Array of finding objects
  • decisions - Array of decision objects

Outputs

  • Updated findings.md with organized, timestamped entries
  • Coverage analysis for verification

Process Files

  • planning-orchestrator.js - Findings initialization and appending
  • planning-execution.js - 2-Action Rule batches and final flush
  • planning-verification.js - Coverage analysis

Signals

GitHub stars
2k
Forks
106
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
findings-capture
Source
github.com/a5c-ai/babysitter