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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/FerroxLabs/ijfw --skill ijfw-debug命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Maintain canonical AGENTS.md (open spec). Trigger: 'agents.md', 'update AGENTS.md', or auto-fired by ijfw-team after agent generation.
First-class design intelligence. Dispatches to the best available design skill (ui-ux-pro-max, frontend-design, superpowers), then layers IJFW constraints on top. Triggers: 'design', 'redesign', 'UI', 'UX', 'dashboard', 'page', 'component', 'make it look better', 'polish', 'pretty', 'professional', 'user experience', 'layout', 'visual', 'mobile-first', 'dark mode', 'accessibility', 'colors', 'typography', 'brand'.
Check for and apply IJFW updates safely. Trigger: 'update ijfw', 'upgrade', 'latest version', 'is there a new version', /update
基于 SOC 职业分类
正在显示 SKILL.md
| name | ijfw-debug |
| description | Root-cause analysis with hypothesis tracking. Trigger: 'debug', 'broken', 'not working', 'fix this bug', /debug |
State the failure in one line: what was expected vs. what happened. Confirm reproducible before proceeding. If intermittent, note conditions.
Call ijfw_memory_recall with the symptom. Scan .ijfw/memory/ for decisions or
changes from the past 7 days that touch the affected area.
If a recent change correlates with the regression, offer revert first:
Regression likely from <change> on <date>. Revert first? (y/n)
List hypotheses ranked by likelihood:
H1 -- <most likely cause> -- evidence: <why>
H2 -- <next candidate> -- evidence: <why>
H3 -- <edge case> -- evidence: <why>
Confirm H1 before testing H2.
Apply the minimal change that addresses the root cause.
Do not fix adjacent issues -- log them as follow-ups.
Run tests/linter after every fix.
Confirm the original symptom is gone and no adjacent regression introduced.
Store result: ijfw_memory_store: <what broke>, <root cause>, <fix applied>
If two attempts at root-cause fixes both fail to clear the original symptom, stop. Do not try a third on the same hypothesis tree. Summarize in three lines: what you tried, what each attempt revealed, what you now believe is true. Then ask the user:
Two attempts didn't land it. Recommend resetting this session and starting fresh with: "<sharpened prompt>". Accumulated failed context degrades the next attempt; a fresh session with a tighter brief usually clears it on the first try.
Capture the summary in ijfw_memory_store so the next session inherits the lessons without inheriting the noise.
SYMPTOM: <one line>
ROOT CAUSE: <H1 confirmed or revised>
FIX: <what changed + file:line>
VERIFIED: yes / needs more testing
FOLLOW-UPS: <any adjacent issues deferred>