원클릭으로 Manus에서 모든 스킬 실행

skill-repair-loop

스타0

포크0

업데이트2026년 7월 3일 12:42

Repairs a Claude Skill after a bad output by identifying the exact failure, patching SKILL.md, and adding a regression test. Use when a skill output is generic, wrong, overhyped, off-format, or fails the user's expectations.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

Arnie016

Arnie016/fable-mythos

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Skill Repair Loop

Mission

Improve a Claude Skill based on a real failed output. Do not rewrite the whole skill unless necessary — patch the smallest instruction that would have prevented the failure.

Required input

The current SKILL.md
The bad output
What was wrong with it (infer from the output if unstated)

If the bad output itself is missing, ask for it. You cannot diagnose a failure you haven't seen — do not repair from a description alone.

Workflow

Classify the failure:
- Trigger failure — skill didn't fire, or fired wrongly (fix: description)
- Format failure — wrong sections/structure (fix: output format)
- Voice failure — generic or off-tone (fix: examples file, not more adjectives)
- Reasoning failure — wrong angle, bad judgment (fix: workflow step)
- Overclaiming — invented facts/hype (fix: hard constraint)
- Missing constraint — did something the skill never forbade
- Capability gap — the executor model can't follow the instruction as written (fix: simplify it or replace prose with a worked example — do NOT add more prose)
- Instruction bloat — the skill is so long the model skimmed it (fix: cut)
Locate the single missing or weak instruction responsible.
Patch minimally: keep it short, make it operational, no vague style adjectives. Add an example only if the instruction can't carry the fix alone.
Replay mentally: would the patched skill have produced the right output on the original failing input? If not, the diagnosis is wrong — go back to step 1.
Add one regression test to the skill's evals: input, expected behavior, the failure it prevents.

Output format

Diagnosis

The exact failure and its type.

Minimal patch

The changed lines of SKILL.md, before/after.

Regression test

One new eval case in the repo's JSONL format.

Why this patch works

Two sentences max.

이 저장소의 다른 Skills

같은 저장소

agent-task-compiler

Arnie016/fable-mythos

Compiles a vague project idea into agent-ready work - a sprint spec, a contract of testable assertions, and an ordered task list with acceptance criteria. Use when the user wants to hand a project to Codex, Claude Code, or coding agents, break down a build, or turn an idea into tickets/tasks.

2026-07-050

skill-author

Arnie016/fable-mythos

Creates a new Claude Skill to fable-mythos standard - a tight SKILL.md plus eval cases and an example. Use when the user wants to turn a repeated workflow, a giant pasted prompt, or a recurring task into a reusable skill.

2026-07-050

video-prompt-director

Arnie016/fable-mythos

Turns a scene idea into production-ready prompts for AI video models (Seedance, Veo, Higgsfield, Kling, Sora). Use when the user wants video generation prompts, a scene broken into shots, camera directions, or is fighting inconsistent characters across generated shots.

2026-07-050

voice-capsule

Arnie016/fable-mythos

Builds a reusable personal style guide (voice capsule) from the user's real writing samples so any model can write closer to their voice. Use when the user wants output to sound like them, asks to capture their voice or style, or complains that AI writing sounds generic.

2026-07-050

linkedin-signal-posts

Arnie016/fable-mythos

Turns messy project notes into high-signal LinkedIn posts for AI, research, startup, hackathon, education, or technical audiences. Use when the user asks for a LinkedIn post, launch post, achievement post, founder update, research announcement, or polished social post.

2026-07-030

name	skill-repair-loop
description	Repairs a Claude Skill after a bad output by identifying the exact failure, patching SKILL.md, and adding a regression test. Use when a skill output is generic, wrong, overhyped, off-format, or fails the user's expectations.

Skill Repair Loop

Mission

Improve a Claude Skill based on a real failed output. Do not rewrite the whole skill unless necessary — patch the smallest instruction that would have prevented the failure.

Required input

The current SKILL.md
The bad output
What was wrong with it (infer from the output if unstated)

If the bad output itself is missing, ask for it. You cannot diagnose a failure you haven't seen — do not repair from a description alone.

Workflow

Classify the failure:
- Trigger failure — skill didn't fire, or fired wrongly (fix: description)
- Format failure — wrong sections/structure (fix: output format)
- Voice failure — generic or off-tone (fix: examples file, not more adjectives)
- Reasoning failure — wrong angle, bad judgment (fix: workflow step)
- Overclaiming — invented facts/hype (fix: hard constraint)
- Missing constraint — did something the skill never forbade
- Capability gap — the executor model can't follow the instruction as written (fix: simplify it or replace prose with a worked example — do NOT add more prose)
- Instruction bloat — the skill is so long the model skimmed it (fix: cut)
Locate the single missing or weak instruction responsible.
Patch minimally: keep it short, make it operational, no vague style adjectives. Add an example only if the instruction can't carry the fix alone.
Replay mentally: would the patched skill have produced the right output on the original failing input? If not, the diagnosis is wrong — go back to step 1.
Add one regression test to the skill's evals: input, expected behavior, the failure it prevents.

Output format

Diagnosis

The exact failure and its type.

Minimal patch

The changed lines of SKILL.md, before/after.

Regression test

One new eval case in the repo's JSONL format.

Why this patch works

Two sentences max.