Who Is Actor
v1.0.12This skill should be used ONLY when the user EXPLICITLY and UNAMBIGUOUSLY requests a Git repository commit-history analysis that produces aggregate collaboration-pattern metrics (commit cadence, churn, rework signals, conventional-commit compliance, bus-factor risk). The skill is scoped to repository-level technical analysis. It is NOT a performance-management, HR, ranking, or personnel-evaluation tool, and agents MUST refuse to use its output for those purposes. Any developer display names appearing in output exist solely to attribute Git commit records, not to render judgments about individuals. Activation requires an explicit, opt-in user request that BOTH (a) states a clear analyze-this-Git-repository intent AND (b) supplies a concrete repository path (or unambiguous repo reference). Generic conversational mentions of "analyze repository", "profile developers", "commit habits", "developer report card", "code quality", "team efficiency", "work habits", "engagement", "代码分析", "研发效率", "开发者画像", "提交习惯", "工作习惯", or "参与度" WITHOUT a repository path or explicit "analyze this Git repository" framing are NOT sufficient to activate this skill. In that situation the agent MUST first (1) confirm the user actually wants to run repository profiling, (2) request a concrete repository path, (3) confirm the user has authority to analyze that repository, (4) remind the user that other contributors' Git metadata will be processed, and (5) recommend Dry-Run preview — only after these are resolved may any git command be executed. Activation phrases (must include an explicit analyze-this-repo intent AND a repository path or unambiguous repo reference): "analyze the git repository at <path>", "run who-is-actor on <path>", "profile developers in this repo at <path>", "generate a developer report card for the repo at <path>", "分析仓库 <path>", "对 <path> 这个 git 仓库做开发者画像". Privacy & data-handling: relies purely on native git read-only CLI commands and standard Unix text-processing utilities. Developer emails are never collected. Commit message text and full file paths are processed strictly locally and reduced to numeric aggregates BEFORE any data leaves the local environment; only aggregated metrics (counts, averages, ratios, extension-level statistics) are forwarded to the AI model. The collection commands themselves emit raw subjects and paths — these MUST be treated as local-only intermediate values and never placed into AI prompts, tool arguments, or other off-host contexts. See "Sensitive Data Filtering Rules" for mandatory enforcement details.
by