How do I install the Task Analysis skill?

Run npx skillmds@latest add blockscout/task-analysis 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.

Is Task Analysis safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Task Analysis?

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.

Is Task Analysis free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Task Analysis?

blockscout (@blockscout) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Task Analysis by blockscout — Agent Skill

Name: Task Analysis
Author: blockscout

Task Analysis

Analyze an input task, issue, or feature request against the existing codebase, persist the task framing under `tmp/tasks/<task-name>/task.md`, write one or more `solution_N.md` option files, align evaluation criteria with a human when tradeoffs exist, and recommend a path with explicit reasoning.

blockscout 2595431 2 files · 1.7 KB Updated Sep 17, 2026

File contents

Task Analysis Skill

Use this skill when the user wants a pre-implementation review of a task, issue, feature, or design direction.

Workflow

Follow the canonical workflow in ../../../.memory-bank/workflows/task-analysis.md.

Required Guardrails

Read the relevant .memory-bank/ context and source-of-truth code paths before proposing solutions.
Ground every option in the actual repo structure and current abstractions.
Persist each analysis under tmp/tasks/<task-name>/ using task.md, solution_N.md, and solutions.md when multiple options exist.
If multiple viable options exist, explicitly align on evaluation criteria with the human before selecting a recommendation.
If only one realistic option exists, say so and explain why.
Separate facts, assumptions, and recommendations.

Minimal Starting Reads

Start with:

../../../.memory-bank/project-context.md
../../../.memory-bank/architecture.md
../../../.memory-bank/exploration-map.md
../../../.memory-bank/gotchas.md

Then read the specific research notes, ADRs, rules, tests, and code paths relevant to the task under review.

Frequently asked questions