BB nex-decision-journal
Personal decision journal and reasoning tracker that helps you become a better decision maker over time. Log important decisions before you make them, capture your reasoning, options considered, confidence level, and predictions. Set follow-up dates to review outcomes later. Record what actually happened, whether your prediction was correct, partially correct, or wrong, and capture lessons learned. Over time, build a searchable archive of your decision history with statistics that reveal patterns in your judgment: where you're overconfident, where you're underconfident, which categories you decide well in, and which ones need work. Perfect for founders (oprichters), CEOs, managers (managers), freelancers (freelancers), entrepreneurs (ondernemers), team leads, investors, agency owners, consultants, and anyone making high-stakes business or personal decisions. Track hiring decisions (aanwervingen), product strategy (productstrategie), pricing changes (prijswijzigingen), partnership deals, investment choices (investeringskeuzes), technical architecture decisions, marketing experiments, sales strategies, career moves (carrierestappen), and personal life decisions. Includes reflection tools that surface overconfidence bias, underconfidence patterns, accuracy breakdowns by category, and a complete lessons-learned knowledge base built from your own experience. Supports decision categories, tags, stakes levels, reversibility flags, confidence scoring on a 1-10 scale, flexible follow-up scheduling (1 week to 1 year), full-text search, timeline view, and CSV/JSON export. All data stored locally in SQLite. No external APIs, no telemetry, no tracking. Your decisions are yours. Works in English and Dutch. Decision log, beslissingenlogboek, besluitvorming, beslissingsarchief, decision tracker, judgment tracker, outcome tracker, prediction journal, reflection tool, thinking tool, metacognition.
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1912 chars, limit 1024 - note
description-budgetdescription takes 1912 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 33 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2775 tokens
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1912: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 22 headings
- +3Step-by-step instructions: 33 items
- +3Output format is stated explicitly
- +4Has examples (14 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.