菜单
Use when an agent violates a loaded skill despite it being present in context — a gap exists between what the skill says and what the agent did. Also use when reviewing skill effectiveness after a violation, or when deciding whether a skill needs enhancement vs the failure is tolerable.
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。
| name | skill-fails |
| description | Use when an agent violates a loaded skill despite it being present in context — a gap exists between what the skill says and what the agent did. Also use when reviewing skill effectiveness after a violation, or when deciding whether a skill needs enhancement vs the failure is tolerable. |
| license | CC-BY-NC-4.0 |
When an agent violates a loaded skill, a gap exists between the skill's instructions and the agent's behavior. This skill provides a 4-step post-mortem to close that gap with a targeted enhancement — or decide the failure is tolerable.
Do NOT use when: skill wasn't loaded (teach, don't fix), agent followed skill but got wrong result (skill is wrong, not unenforced), or context couldn't contain the skill at all.
| Step | Question |
|---|---|
| 1. Capture violation | What did the agent do vs what does the skill say? Quote both. |
| 2. Classify gap | Why did the instruction fail to prevent the behavior? Use taxonomy below. |
| 3. Assess tolerability | Context window % at failure × severity. Fix or tolerate? |
| 4. Propose enhancement | One targeted edit to close that specific gap. |
| Gap | Symptom | Fix |
|---|---|---|
| Passive language | Rule stated but no enforcement gate. Agent reads, doesn't internalize. | Add a concrete check. |
| Missing anti-pattern | Skill shows correct behavior, never wrong. Agent violates without recognizing it. | Add counter-example. |
| Rationalization loophole | Agent's excuse not covered in prevention table. | Add the excuse + counter. |
| Cognitive-load bypass | Rule buried in prose. Agent under pressure skims past it. | Move to scannable position (red flag, bold, gate). |
| Contradictory guidance | Two rules conflict. Agent picks the easier one. | Resolve contradiction. |
| Context-window attenuation | Skill loaded early, details lost by action time. | Rarely a skill fix. Move critical rules earlier or add gate. |
Context window fullness at failure time is the primary toleration factor.
| Context % | Minor severity | Severe severity |
|---|---|---|
| < 50% | Fix — agent had room | Fix — no excuse |
| 50–80% | Judgment call | Fix — severity demands it |
| > 80% | Tolerate — context explains it | Fix anyway |
Severe = security, data loss, irreversible, user-visible breakage. Minor = style, verbosity, suboptimal structure.
One edit, not a rewrite:
Gap: [type]
Skill says: "[quote]"
Agent did: "[quote]"
Proposed fix: [one edit — gate, counter-example, rationalization row, or reorder]
Violation: Agent wrote bullet-point checklist as commit body: "Merged: - A + B - C..."
Skill said: "Body tells a story, not a checklist."
Gap: Passive language. No enforcement — just "read aloud."
Context: ~60%. Fix needed.
Fix: Added concrete body gate rejecting bullets/lists/headers. Added to Rationalizations and Common Mistakes.
| Mistake | Fix |
|---|---|
| Rewriting the skill instead of a targeted edit | One edit, one gap. |
| Blaming the agent | Skills prevent failures. If it didn't, the skill has a gap. |
| Fixing context-window failures in the skill | Long context is environmental. Only fix if severe. |
| Adding a rule without a gate | Rules without enforcement are passive. |
After proposing an enhancement:
Use when removing dead code, renaming symbols, or refactoring — any change with no external consumers. Triggers on deprecating dead code, wrapper shims, compatibility aliases, TODO-future-cleanup, or refactors that patch structure instead of simplifying.
Use when configuring custom providers for OpenCode.
Use when writing new React components that involve state derived from props, event-driven side effects, or external subscriptions. Also use when auditing existing code for unnecessary useEffect calls, reviewing useEffect-heavy components, or refactoring to eliminate cascading renders. Applies to React 18+ codebases.
Use when about to make git commits, when tempted to bundle unrelated changes behind a single message, or when commit history needs to support git bisect, revert, and cherry-pick workflows. Also use when reviewing a branch before creating a PR. If you are writing a plan, specify that the executor must load this skill before start working.
Use when configuring or enhancing oxlint rules for a JavaScript/TypeScript project, when deciding which lint rules to enable beyond the default correctness category, or when evaluating whether a lint rule's autofix status and noise level make it worth enabling. Also use when bulk-enabling pedantic or style categories has produced excessive noise.
Use when a user provides examples prefixed by "for example", "such as", "e.g.", "like", or ends a list with "etc." / "and so on". For architecture/design tasks, abstract first to identify the concept, then enumerate. For research/clarification tasks, enumerate first — the concept organizes the output but the list is the deliverable.