drift-check

Solid

Audit a set of related project documents for internal contradictions and drift from their stated mission, with a skeptical eye that distrusts suspiciously clean alignment. Use whenever the user points at multiple docs (spec, PLANNING.md, README, CLAUDE.md, .cursorrules, system prompt, TASK tracker, ADRs) and asks "are these consistent", "do my docs agree", "has my spec drifted", "check alignment", "is my README in sync", "audit my project for consistency", or shares a self-alignment/audit report. Especially trigger when documents should agree on the same facts (tech stack, metrics, feature lists, naming, architecture, tone) and the task is finding where they silently diverge, or where identical copy-pasted claims masquerade as validation. Lead with the real state of alignment and the biggest contradiction, never a vanity score. For cross-document consistency and mission-drift within a project's own materials, not verifying external claims (use reality-check) or choosing between options (use a council skill).

AI & Automation 0 stars 0 forks Updated today MIT

Install

View on GitHub

Quality Score: 78/100

Stars 20%
0
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Drift Check Audit a set of project documents — specs, planning docs, READMEs, rules files, system prompts, task trackers — for two failures: **contradiction** (the docs disagree with each other) and **drift** (the docs have wandered from the mission they claim to serve). The output the user needs is an honest map of where their materials actually stand, not reassurance. ## Core principle: clean alignment is a smell The dangerous failure mode here is the opposite of harsh — it's being agreeable. A document set that audits to "98% aligned, all green" is not evidence of health; it's usually evidence that nobody looked hard. Real document sets that evolved over time accumulate contradictions, stale references, and quiet redefinitions. If your audit comes back glowing, you didn't dig — go back and find the contradiction the rosy summary is papering over. Two things in particular masquerade as alignment: - **Identical claims are not corroboration.** When the same metric (`>95% accuracy`, `<2 seconds`) or the same sentence appears verbatim across five documents, that is copy-paste, not five independent validations. It tells you the number propagated, not that it's right or achievable. - **Unfalsifiable promises aren't aligned, they're just vague.** "Perfect memory", "seamless orchestration", ">95% accuracy" with no measurement defined — these agree across docs only because none of them mean anything checkable yet. ## Workflow ### 1. Anchor the north star Find the stated mis...

Details

Author
scoobydrew83
Repository
scoobydrew83/skills
Created
1 months ago
Last Updated
today
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category