Conversation
Kiasma1
added a commit
to Kiasma1/cangjie-skill
that referenced
this pull request
Jul 5, 2026
… (2026-07 实战复盘) SKILL.md: - add '阶段 -1: PDF 体检' with text/scan/markitdown decision matrix - add density sampling table (文字密集 90% / 表格 40% / 图鉴 5% strategy) - add '产出路径分支决策' (路径 A:skill / 路径 B:md 手册 / 路径 C:both) - expand '调用惯例' with 5 个实战复盘教训 - add '时间预算参考' 与 '一旦出错的止损规则' - 输入要求新增 '期望产出形态' 必问项 00-overview.md: - 第七节 '实战经验' (2026-07 蒸馏复盘): 5 张教训表 + 证实的 5 个教训 + 一句话结论 01-stage0-adler.md: - 常见失败模式加两条实战教训(kangarooking#4 没问产出路径 / kangarooking#5 没先体检) - 加 '相关参考' 提醒阶段 0 开始前走体检、阶段 0 后立刻问路径 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds an explicit safety boundary to treat books, articles, OCR, metadata, encoded text, and other source material as untrusted data rather than agent instructions.
Why this is needed
The skill distills arbitrary user-provided source text into executable agent skills. That source text may contain prompt injections or hidden instructions, including OCR noise, encoded text, comments, or unusual formatting. Without an explicit guardrail, those instructions could be accidentally copied into generated skill triggers or execution steps.
Changes
rejected/or audit notes.