approved tags and signal metadata when applicable.
Constraints
Do not modify repository source files.
Do not commit or push.
Keep proposals concrete, scoped, and implementation-ready.
1---2name: continuation-proposal3description: Generate one best-next-step proposal after a successful task run, either the next phase in a series or a high-value improvement.4---56# Continuation Proposal Skill78## Purpose910After a successful run, propose the highest-value continuation task.1112## Inputs1314- `inputs.jobId`15- `inputs.repository`16- `inputs.runtimeMode`17- `inputs.taskStatus` (expected `succeeded`)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## Decision Rule25261. Determine whether the completed work is part of a multi-step or phased series.272. If it is part of a series, propose the next concrete task/phase.283. If it is not, propose one meaningful follow-up:29 - refactor30 - performance improvement31 - feature extension3233## Workflow34351. Read `task_context.json`, execution logs, and task summary.362. Identify the single best continuation with clear impact.373. Append one proposal object to `proposalOutputPath`.384. Keep the output as a valid JSON array and avoid duplicate titles.3940## Proposal Requirements4142Each appended item must include:4344- `title`45- `summary`46- `taskCreateRequest` (valid queue task creation envelope)4748For MoonMind/run-quality continuations, include:4950- `category: "run_quality"`51- approved `tags` and `signal` metadata when applicable.5253## Constraints5455- Do not modify repository source files.56- Do not commit or push.57- Keep proposals concrete, scoped, and implementation-ready.
Run npx skillmds@latest add moonladderstudios/continuation-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 best-next-step proposal after a successful task run, either the next phase in a series or a high-value improvement. 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.