一键导入
decisive-root-fix
Use when urgency matters and the right move is a direct, root-cause fix instead of cautious layering.
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。
菜单
Use when urgency matters and the right move is a direct, root-cause fix instead of cautious layering.
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。
基于 SOC 职业分类
Live decision-review session between graveyard shifts. Compile every decision and approval currently waiting on the user — across ALL prior shifts, not just the latest — walk them together, and RECORD each outcome onto GitHub as shaped permission rather than executing it live (execution is the graveyard's job; building/merging mid-meeting just makes the user wait). Reactions are cues to capture; even approvals are deferred to the next graveyard. End by publishing the report and — with standing permission — launching that graveyard shift.
Adversarially review a graveyard shift's brief BEFORE it's published — kill false gates, sharpen real ones, surface actionable work the shift left behind, and loop the graveyard if real work remains. Use as the closing/looping phase of graveyard-shift, right after the Shift Report is drafted and before it's published to Notion. This is what makes a graveyard shift loop until review finds no actionable-now work remaining; it is NOT run during a shift-change (that's a live meeting with the user and can't loop).
Work through the open issue backlog autonomously. Auto-ship the small clean fixes, prep draft PRs for review on bigger ones, file refined proposals when design choices need user input. For unattended sessions where the user is sleeping / away and wants to wake up to a productive set of changes.
The definition-of-done gate. Run before declaring any unit of work done or finished — before merging an auto-ship, handing back a draft PR, closing an issue, or listing an item as "shipped" in a shift report. Nine ownership questions plus a short close-out posted on the PR/issue. Any unanswerable question flips the item to a lesser bucket instead of shipping a hole.
Review a plan, issue, spec, PR, current diff, or implementation against an authoritative source of truth; identify missing, incorrect, risky, overcomplicated, or unverifiable work; patch clear gaps when requested; optionally run an advisory external reviewer (e.g. the codex-pr review loop / codex/AGY) for implementation diffs.
Review code, prompts, validators, regexes, heuristics, fallback logic, shell/wrapper authority, over-specific field ownership, and duality (two paths for two callers) for brittle patching or overengineering that masks product intent. Use when a function or feature may be over-controlled with deterministic regexes, fallback piles, quality gates, compatibility branches, large schemas, producer shells that carry creative/continuity authority, premature per-field authoring, detailed upstream contracts, or two parallel implementations of the same logical step that must stay in sync.
| name | decisive-root-fix |
| description | Use when urgency matters and the right move is a direct, root-cause fix instead of cautious layering. |
| metadata | {"short-description":"Push for direct root-cause fixes under urgency"} |
Use this skill when the defect is understood well enough that caution is becoming drag: wrong write path, wrong container, stale authoritative field, duplicated state, masking fallback, or compatibility logic that is hiding the real problem.
The goal is:
Reach for this skill when the product call is clear and the work needs sharper execution. If the product call is still unclear, resolve that first — do not stack more conditionals in place of a decision.
Answer these first:
Do not start with extra hardening. Start with the wrong truth.
Make an explicit call:
If you cannot say which path is authoritative, keep investigating. Do not stack more conditionals.
For every fallback or duplicate path, classify it:
remove now: actively causing drift or no longer needednarrow shim: temporary compatibility for a known legacy casekeep briefly: only if deleting it now would break active data and the follow-up is already definedDefault to remove now. "Maybe helpful later" is not a reason to keep it.
In the implementation:
Avoid:
Be decisive only after you know:
If one of those is unknown, investigate fast and directly. Do not compensate with extra scaffolding.
If legacy data truly needs a bridge, say exactly:
Do not let the compatibility branch become the new product truth.
Pause and ask if the fix requires:
When using this skill, structure the answer in this order:
Direct fix
What to remove
Compatibility exception
none.Execution
Reach for this skill when the conversation includes phrases like:
When urgency is high and the defect is understood, prefer the authoritative correction over defensive accumulation.