When proposing MoonMind/run-quality improvements, also include:
category: "run_quality"
tags: at least one from:
retry
duplicate_output
missing_ref
conflicting_instructions
flaky_test
loop_detected
artifact_gap
signal: include at least severity (low|medium|high|critical) and brief evidence context.
Constraints
Do not modify repository source files.
Do not commit or push.
Keep proposals concise and actionable.
1---2name: fix-proposal3description: Generate one high-value follow-up workflow proposal when MoonMind execution quality issues are detected in a run.4---56# Fix Proposal Skill78## Purpose910Produce a targeted follow-up workflow proposal for MoonMind/system quality problems observed during a task run.1112## Inputs1314- `inputs.jobId`15- `inputs.repository`16- `inputs.runtimeMode`17- `inputs.taskStatus` (`succeeded` or `failed`)18- `inputs.taskSummary`19- `inputs.taskError`20- `inputs.taskContextPath` (usually `../artifacts/task_context.json`)21- `inputs.artifactsPath` (usually `../artifacts`)22- `inputs.proposalOutputPath` (usually `../artifacts/workflow_proposals.json`)2324## Detection Focus2526Look for partial or complete execution failures and degraded behavior, including:2728- Access/auth failures29- Unclear or conflicting instructions30- Retry storms or repeated retries31- Execution loops32- Duplicate/repetitive output33- Missing required references or artifact gaps3435## Workflow36371. Read `task_context.json` and available logs under `artifacts/logs/`.382. Determine whether there is a clear, high-value fix opportunity.393. If no meaningful issue is found, keep the proposal file unchanged.404. If an issue is found, append one proposal object to the JSON array at `proposalOutputPath`.415. Keep the output valid JSON and avoid duplicate titles.4243## Proposal Requirements4445Each appended item must include:4647- `title`48- `summary`49- `taskCreateRequest` (valid queue task creation envelope)5051When proposing MoonMind/run-quality improvements, also include:5253- `category: "run_quality"`54- `tags`: at least one from:55 - `retry`56 - `duplicate_output`57 - `missing_ref`58 - `conflicting_instructions`59 - `flaky_test`60 - `loop_detected`61 - `artifact_gap`62- `signal`: include at least `severity` (`low|medium|high|critical`) and brief evidence context.6364## Constraints6566- Do not modify repository source files.67- Do not commit or push.68- Keep proposals concise and actionable.
Run npx skillmds@latest add moonladderstudios/fix-proposal in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Generate one high-value follow-up workflow proposal when MoonMind execution quality issues are detected in a run. It is listed under Productivity on SkillMD.
SkillMD's automated safety review verdict for this skill is PASS. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
MoonLadderStudios (@moonladderstudios) published this skill. Their other Agent Skills are listed on their SkillMD profile.