菜单
Produce an evidence-backed change-impact brief with `mastermind impact` or `mmcg_change_impact`. Use before editing, during implementation planning, or in PR review to trace changed symbols, callers, component/API crossings, collision risk, and likely affected consumers since a git ref.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Turn a design handoff into a task contract that can actually be checked — named source, resolved components, token names instead of raw values, and an explicit list of what stays unverifiable. Use when a Figma frame, mockup, or design spec is handed over for implementation.
Convert a PRD, ticket, or feature request into a task contract that can fail — behaviour split from outcome, product nouns resolved to symbols that exist, unspecified cases surfaced as questions, and success metrics parked where a merge gate cannot wave them through. Use when product writing is handed over for implementation.
Enumerate what a change can reach and what enforces it — privileged operations and their callers, guards and the sites that apply them, and every module that reads a secret — before designing an auth, permission, or secrets change. Feeds the security review; produces a population and a gap list, never a verdict.
Read-only review of whether the tests in a finished change actually prove its behaviour — changed code no test reaches, a test exercising a different path than the one that changed, an assertion edited to match the new output, and a suite that ran nothing. Use after implementation, and whenever a change claims to be covered.
Gather who already depends on a service, handler, or state owner before changing it, and name the runtime gaps the codegraph cannot span. Use before designing a change to an API, queue consumer, background job, migration, or shared state; it feeds the architecture review rather than replacing it.
Read-only review of a finished UI change against the codegraph — a component nothing renders, a props contract changed without its callers, a reinvented component, or a raw value where the design system has a token. Use after implementing React or Vue work; triggers "review this UI change", "check the component", or a finished frontend diff.
| name | mastermind-change-impact |
| description | Produce an evidence-backed change-impact brief with `mastermind impact` or `mmcg_change_impact`. Use before editing, during implementation planning, or in PR review to trace changed symbols, callers, component/API crossings, collision risk, and likely affected consumers since a git ref. |
| metadata | {"version":"0.1.0","authors":["mastermind"],"tags":["workflow","mmcg","impact"]} |
Base the brief on the deterministic change-impact response, not a grep-derived caller list.
Select an explicit trusted baseline such as the merge base or target branch.
Do not silently substitute HEAD~1.
Run mastermind status as a read-only preflight. Ensure the current working
tree is indexed when local changes are in scope. If the backend returns
index_stale, stop unless the request authorizes mastermind index .; do
not downgrade confidence and continue with a partial graph.
Run:
mastermind impact --since REF --format json --depth 3 --top 100
Use mmcg_change_impact through MCP when appropriate.
Verify full baseline/head object IDs and whether worktree/untracked files are included. Check every limit and precision note before ranking risk.
Report changed symbols, direct then transitive consumers, component/API crossings, and public-surface implications. Attach each conclusion to the response's changed-symbol seeds and repository-relative evidence.
Downgrade confidence when names collide, edge precision is weak, the index is stale, a work limit skipped expansion, or dynamic/reflection boundaries are likely. Removed symbols can still have old-side evidence; do not require them to exist in the live index.
Do not convert syntactic impact into a semantic guarantee. Do not say an unlisted consumer is safe. If the backend is unavailable, report the missing capability rather than inventing an impact graph.
For a blocked result, state the trusted baseline, the stable failure code, the required remediation, and that affected symbols/components/consumers are unknown until a fresh deterministic response exists.