Automated README summary
Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
docfriction generates friction logs for online documentation pages, walking through each section and asking TypeSafe Jev a fixed set of typed questions. It is for developer advocates and writers who want to find where readers get stuck.
How it uses Jev
For each section, Jev answers one Choice question over ten friction types plus no_friction and other, one Score question over four reader outcomes for severity, and several Noul (yes/no) checks for prerequisites, expected result, undefined terms, code/prose match, and unexplained placeholders. Probabilities become findings via thresholds; uncertain answers are marked 'needs review'.
Primitives:choicescorenoul
Technique worth stealing
Use typed questions (Choice, Score, Noul) with probabilities and thresholds to turn subjective documentation friction into deterministic, CI-gateable findings.
Try it
uv tool install docfriction; docfriction https://docs.example.com/quickstart --dry-run; export TYPESAFE_API_KEY=...; docfriction https://docs.example.com/quickstart
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.92
- Shows a System One patternFound in material0.65
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalnot found in the excerpt0.21
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.25 / 2
- About JevFound in material0.97
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.