Use this skill for any non-trivial change (new feature, refactor, pipeline change, bug fix).
Procedure
Restate the task in your own words.
Ask clarifying questions only if needed to avoid wrong behavior.
Write a plan:
steps (numbered)
files to read/edit
commands to run for verification
Identify risks (silent failure modes, data assumptions, backwards compatibility).
Execute in small increments:
prefer test-first
keep diffs reviewable
avoid unrelated changes
Verify:
run listed commands
summarize results
Handoff:
if work spans sessions, update docs/HANDOFF.md.
Output format
Clarifying questions (if any)
Plan
Risks
After execution: verification summary + follow-ups
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: reblocke-forensic-metascience-plan-execute-evaluate3description: When to use4---56## When to use7Use this skill for any non-trivial change (new feature, refactor, pipeline change, bug fix).89## Procedure101. **Restate the task** in your own words.112. **Ask clarifying questions only if needed** to avoid wrong behavior.123. **Write a plan**:13 - steps (numbered)14 - files to read/edit15 - commands to run for verification164. **Identify risks** (silent failure modes, data assumptions, backwards compatibility).175. **Execute in small increments**:18 - prefer test-first19 - keep diffs reviewable20 - avoid unrelated changes216. **Verify**:22 - run listed commands23 - summarize results247. **Handoff**:25 - if work spans sessions, update `docs/HANDOFF.md`.2627## Output format28- Clarifying questions (if any)29- Plan30- Risks31- After execution: verification summary + follow-ups3233---34> Converted and distributed by [TomeVault](https://tomevault.io/claim/reblocke) — claim your Tome and manage your conversions.35<!-- tomevault:4.0:skill_md:2026-04-15 -->
Run npx skillmds@latest add tomevault-io/reblocke-forensic-metascience-plan-execute-evaluate 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.
When to use It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. 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.
tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.
tomevault-io