drift-check
Skill15 starsChanged 5 months agoMITView on GitHub
Compare an investigation's CURRENT state against an EARLIER SNAPSHOT of itself and report what moved between those two points in time: problem-statement drift, evidence added or retired, Value/Confidence score movement, theme or narrative reframing, and whether confidence is genuinely accumulating or just churning. Use when the user says \"what changed since last month\", \"has this drifted\", \"compare this to the prior version\", \"is the confidence trajectory improving\", or wants to audit a scope before re-deciding. Reads scoped snapshots and git history and runs the cross-stage consistency checks. Do NOT use for finding patterns or trends WITHIN the current evidence set, that is synthesize; nor for reviewing a product-metrics dashboard, that is a metrics review. This is specifically a then-vs-now diff of the investigation. No daemon; runs on demand or on a schedule.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- scoobydrew83/skillstheir own version, first seen Nov 3, 2026
- pfeff/claude-skillstheir own version, first seen Nov 1, 2026
- nadavnaveh/skillstheir own version, first seen Oct 25, 2026
- majiayu000/test-looptheir own version, first seen Oct 13, 2026
- aribajahan/claude-skillstheir own version, first seen Sep 23, 2026
- DarynaRodriguez/seo-skillstheir own version, first seen Aug 27, 2026
Used with
Projects with it also use handoff.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- HaipingShi/coderail★ 8same name
- broomva/skills★ 4same name
- pfeff/claude-skills★ 3same name
- nadavnaveh/skills★ 2same name
- ngreenwall/claude-skills★ 2same name
- DarynaRodriguez/seo-skills★ 1same name
- marky291/claude-drift★ 1same name
- aribajahan/claude-skills★ 0same name
- majiayu000/test-loop★ 0same name
- scoobydrew83/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- calibrateSkill
- critiqueSkill
- decision-readinessSkill
- design-testSkill
- discover-sourcesSkill
- gather-evidenceSkill
- pressure-testSkill
- prioritize-backlogSkill
- scorecardSkill
- startSkill
- synthesizeSkill
- to-build-briefSkill
- write-briefSkill
The file
Files
Drift Check
Compare the current state of an investigation scope against a prior snapshot and report what moved. There is no running process: this reads the versioned files (.product-eval/<scope>/snapshots/ and git history) on demand.
Workflow
1. Pick scope and baseline
Choose the investigation scope and the baseline to compare against, a prior snapshot in .product-eval/<scope>/snapshots/, or a git ref.
2. Diff the artifacts
- Problem statement: has it drifted from the evidence that supports it?
- Evidence: items added or removed; total weight change; anything newly retired as stale (e.g. by a changelog check).
- Themes: new, faded, or merged.
- Scores: Value and Confidence movement, with drivers.
- Brief / narrative: has the framing been reworded or reframed?
3. Run consistency checks
Apply the cross-stage consistency checks from ../pressure-test/references/critic-checklist.md: problem-statement drift, persona drift, vanity-metric creep, scope vs evidence proportionality, and circular reversals in the decisions log.
4. Report the confidence trajectory
The key signal: is evidence accumulating (Confidence rising as real data arrives) or are you spinning (churn without new evidence)? Say which.
Output
A short "what moved since <baseline>" summary: scores up/down with drivers, evidence added/retired, problem or narrative drift flags, consistency violations, and the confidence trajectory. Append it to the decisions log. End with Next move: and recommend re-running readiness, refreshing evidence, or updating the brief/build brief if the decision changed.
Scheduled use
Can run as a weekly scheduled task, "what moved this week across my investigations", as a digest, not a service. Offer to set one up when the user tracks an investigation over time.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

