Analyze Weft Workflow Runs
SkillDev toolsAnalyze weft workflow runs for timing and friction. Use only when user types /wf-analyze.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Analyze Weft Workflow Runs skill
What this skill tells your AI
The instructions your AI receives, as published by dioptx/weft in skills/wf-analyze/SKILL.md and read by ahel’s review.
Read-only. Aggregates the event log into per-template metrics and surfaces recurring friction.
Arguments
$ARGUMENTS
Instructions
-
Run:
python3 "${CLAUDE_PLUGIN_ROOT}/core/cli.py" analyze $ARGUMENTS -
With no arguments, it reports across all templates. Pass
--template NAMEto scope to one. -
Present results in a readable format, not raw JSON.
What it outputs
- Per-template step durations (median and p90)
- Loop counts and guard-block counts per step
- Abandonment and stall counts
- Slowest step per template
- A recurring-friction section, joined from
workflow-qa.jsonl
Examples
/wf-analyze— metrics across all templates/wf-analyze --template feature-workflow— scope to one template
Signals
- GitHub stars
- 27
- Forks
- 1
- Last commit
- Aug 2026
Advanced
- Item type
- skill
- Key
wf-analyze- Source
- github.com/dioptx/weft