cursor/skills/vibeflow-stats/SKILL.md
Compiles statistics from audit reports: PASS/PARTIAL/FAIL rates, most violated patterns, most failing DoD checks, and quality trends. Use after running several audits to spot improvement areas.
npx skillsauth add pe-menezes/vibeflow vibeflow-statsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Show statistics from audit reports. Reads all audits and compiles pass/fail rates, most violated patterns, and common DoD gaps.
Usage: Run this skill with no input. It reads .vibeflow/audits/.
Detect the language of the user's conversation context. Write ALL output in that same language. Technical terms in English are acceptable regardless of the detected language.
Check if .vibeflow/audits/ directory exists and contains .md files.
Read ALL .md files in .vibeflow/audits/.
For each audit file, extract:
**Verdict:** line)[x] and failed [ ] checkboxes
in the ### DoD Checklist section[ ] in the ### Pattern Compliance
section, with the pattern name### Convention Violations
section (if present)Compile the statistics and report directly in the chat (do NOT save to file). Use this format:
## Vibeflow Stats
**Audits analyzed:** N
### Verdicts
- PASS: N (X%)
- PARTIAL: N (X%)
- FAIL: N (X%)
### DoD
- Total checks: N
- Pass rate: X%
- Most failing checks:
1. "<check description>" — failed N times
2. "<check description>" — failed N times
3. "<check description>" — failed N times
### Patterns
- Most violated patterns:
1. <pattern name> — N violations
2. <pattern name> — N violations
3. <pattern name> — N violations
### Convention Violations
- Total: N violations across N audits
- Most common: <list top 3 if available>
### Trend
<If ≥3 audits exist, note if quality is improving (more PASS over time),
stable, or degrading. Base on chronological order of audit dates.>
testing
Updates .vibeflow/ with corrections, new conventions, architectural decisions, or new patterns from natural language feedback. Also imports from external repos via --from <url|path>. Use to keep .vibeflow/ accurate as the project evolves.
data-ai
Fast-tracks small tasks into a prompt pack in one command. Skips discover, generates an ephemeral spec in memory. Use for well-defined tasks that fit in ≤4 files.
development
Generates a self-contained prompt pack from a spec. Embeds real code patterns from .vibeflow/ so any coding agent follows the project's conventions. Use when handing off implementation to a separate session or agent.
testing
Implements a feature from its spec with guardrails: budget, DoD, anti-scope, and pattern compliance. Runs a 7-phase pipeline (find spec → extract guardrails → load patterns → plan → implement → test → self-verify DoD). Use after gen-spec when ready to implement.