experiment-tracker
Experiment Tracker
Overview
This skill turns messy validation history into a usable decision state. The goal is to track what was actually learned, separate strong from weak signals, and recommend the next best experiment.
Load references/signal-quality.md when weighing evidence. Load
references/decision-states.md when deciding whether to continue, narrow,
pivot, or stop.
When to use
- When multiple validation tests have been run
- When the user has conflicting or noisy evidence
- When a next experiment should build on prior evidence rather than restarting
Do NOT use when:
More from accolver/skill-maker
skill-maker
Create or iteratively improve agent skills with eval-driven refinement when the task is to build a new SKILL.md package or tune an existing skill’s trigger accuracy and performance.
26git-conventional-commits
Generate conventional commit messages from staged git changes when the task is to name or format a commit, not to review code or write release notes.
16pdf-toolkit
Operate the bundled PDF scripts to extract, OCR, create, merge, split, or convert PDFs when the task explicitly involves PDF document processing.
14nostr-event-builder
Construct valid Nostr event JSON and tag structures from requirements when the task is to create or validate concrete events rather than choose which NIPs to use.
12error-handling
Standardize application error handling—taxonomy, propagation, response shapes, logging, and correlation IDs—when the task is to improve consistency of existing error behavior across a codebase.
12pr-description
Generate pull-request descriptions from branch diffs when the task is to explain change scope, motivation, testing, risk, and reviewer guidance for a reviewable branch.
12