Change intelligence skill that compares previous and current knowledge snapshots, surfaces what was newly added, which claims changed, what conclusions are n...
15 installs1 stars
Documents
what-changed
Try itPart of the Overpowered skill suite. Explain material semantic differences between versions or snapshots and assess why they matter. Use for policies, procedures, contracts, requirements, datasets, configurations, APIs, schemas, reports, or other evolving artifacts when the user cares about impact rather than a raw line diff.
What it does
Part of the Overpowered skill suite. Explain material semantic differences between versions or snapshots and assess why they matter. Use for policies, procedures, contracts, requirements, datasets, configurations, APIs, schemas, reports, or other evolving artifacts when the user cares about impact rather than a raw line diff.
The skill document
What Changed
Core rule
Report changes in meaning and consequence, not just changed text or rows.
Procedure
- Identify baseline and new version, including effective dates/status when available.
- Normalize formatting-only differences so they do not dominate the analysis.
- Detect material changes in:
- obligations / permissions / prohibitions;
- thresholds, values, units, dates, SLAs;
- roles and responsibilities;
- definitions and scope;
- records added/removed/modified;
- schema/API/config behavior;
- dependencies or referenced rules.
- Classify each change:
- material behavior/policy change;
- potentially breaking;
- compatible/additive;
- editorial/formatting;
- uncertain.
- Explain the likely impact and which downstream artifacts or processes should be checked.
- Use
know-enoughonly when impact analysis requires external organizational context. - Use
reconcilewhen downstream artifacts still encode conflicting rules.
Output contract
Change
Previous → New
Type / severity
Why it matters
Potentially affected artifacts/processes
Evidence location
End with a short action list, not a generic summary.
Deep reference
Read references/change-severity.md when there are many changes to prioritize or when severity is not obvious.
Gotchas
- A small textual edit can be a large policy change.
- A large textual rewrite can be semantically neutral.
- Do not infer downstream impact without evidence when the dependency is unknown; label it “potential.”
- For data snapshots, distinguish changed values from newly missing or duplicate records.
- Effective status matters: draft vs approved can matter more than textual recency.
Stop condition
Stop when all material semantic changes are explained and their known or plausible impact is bounded.
Related skills
Compare fast-changing online services using current, scoped sources for features, pricing, access rules, and policy limits.
1 installs
Smart text comparison tool with format-aware diffing, AI explanation, and 3-way merge. Covers structured JSON, YAML, CSV, code, and plain text.
4 installs
Compare two versions of a .docx document and produce a single Word file in tracked-changes (revision / tracking) mode, as if a human had edited the old file into the new one with Track Changes turned on. Use whenever the user has two versions of a DOCX (e.g., successive drafts of a paper, report, or contract — often AI-generated or AI-assisted revisions) and wants to see the differences as native Word revisions (insertions/deletions) that can be accepted/rejected in Word. Triggers: "对比两个版本的 docx", "tracked changes", "tracking mode", "修订模式对比", "compare two Word documents", "diff two drafts", "生成修订对比文件". Do NOT use for: creating new documents from scratch (use docx skill), single-file editing with revisions (use docx WIR engine), or PDF-only comparisons.
Analyze repository changes from the last release to the current revision and recommend the correct semantic version bump. Use when the user asks what version...
1 installs
Part of the Overpowered skill suite. Route knowledge-work and enterprise-automation tasks through the smallest relevant combination of Overpowered skills, and invoke gear-up only when a material execution capability is genuinely missing. Use when multiple suite skills may apply or when starting a non-trivial task involving organizational knowledge, conflicting evidence, evolving artifacts, business rules, process automation, risky side effects, verifiable completion, or an uncovered capability gap.