break-down-work
Splits a feature or project into small, ordered tasks that each end in something testable.
Skill by YauhenBichel
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/yauhenbichel-break-down-work
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/break-down-work
What's inside
- Skill name
break-down-work- Description
- Splits a feature or project into small, ordered tasks that each end in something testable. Use before starting work that takes more than an hour.
- License
- Apache-2.0
- Instructions
- 22 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## Steps 1. Identify the riskiest unknown. Draft a task to probe it. 2. List all remaining work. Order by dependency. 3. Assign each task one outcome, one verification command (e.g., `uv run pytest tests/test_core.py`), and a size under four hours. 4. Insert a walking skeleton task early. Connect core modules with minimal glue code. 5. Mark independent work with `[parallel]`. Schedule it after the skeleton passes. 6. Review the list. Split any task longer than half a day. Reorder to expose risks early. ## Checklist - [ ] Verify each task has one outcome and a verification command - [ ] Verify tasks follow dependency order with riskiest unknown first - [ ] Verify walking skeleton connects core paths before polishing - [ ] Verify independent work is marked `[parallel]` - [ ] Verify no task exceeds four hours of effort - [ ] Verify verification uses concrete commands or file checks ## Output - A numbered list of tasks with outcome, verification, and size - Parallel markers and dependency notes where applicable - A brief summary of the walking skeleton path
From YauhenBichel/engineering-skills, Apache-2.0.
More from YauhenBichel/engineering-skills
- 0.565score
estimate-and-risks
YauhenBichel
Gives an honest estimate with ranges and the risks behind it.
SkillAFreshness: AClaude Code +9 - 0.564score
handle-errors-and-logging
YauhenBichel
Designs error handling and logs that make failures visible and diagnosable.
SkillAFreshness: AClaude Code +9 - 0.564score
incident-response
YauhenBichel
Handles a production incident and writes the postmortem.
SkillAFreshness: AClaude Code +9 - 0.564score
ml-experiment
YauhenBichel
Runs a machine-learning experiment that can be trusted.
SkillAFreshness: AClaude Code +9 - 0.564score
model-data
YauhenBichel
Designs a database schema or data model.
SkillAFreshness: AClaude Code +9 - 0.564score
dependencies
YauhenBichel
Adds, upgrades or removes dependencies safely.
SkillAFreshness: AClaude Code +9 - 0.564score
explain-code
YauhenBichel
Explains code clearly to another developer.
SkillAFreshness: AClaude Code +9 - 0.561score
algorithms
YauhenBichel
Chooses and implements the right algorithm and data structure.
SkillAFreshness: AClaude Code +9 - 0.561score
clarify-requirements
YauhenBichel
Turns a vague request into a short, testable spec.
SkillAFreshness: AClaude Code +9 - 0.558score
implement-feature
YauhenBichel
Implements a feature in an existing codebase, end to end, with tests.
SkillAFreshness: AClaude Code +9 - 0.558score
ci-cd
YauhenBichel
Sets up or fixes continuous integration and delivery.
SkillAFreshness: AClaude Code +9 - 0.558score
containers-and-deploy
YauhenBichel
Packages and deploys services with containers.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 9, 2026 (19 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from YauhenBichel
- 0.580score
when-free
YauhenBichel
Which days and times am I free?
ConnectorAFreshness: ALocalRead-only↓ 30/wkClaude Code +5 - 0.565score
estimate-and-risks
YauhenBichel
Gives an honest estimate with ranges and the risks behind it.
SkillAFreshness: AClaude Code +9 - 0.564score
write-cli-app
YauhenBichel
One argparse GitHub PR CLI in pkg/ with urllib.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
incident-response
YauhenBichel
Handles a production incident and writes the postmortem.
SkillAFreshness: AClaude Code +9 - 0.564score
explain-code
YauhenBichel
Explains code clearly to another developer.
SkillAFreshness: AClaude Code +9 - 0.564score
handle-errors-and-logging
YauhenBichel
Designs error handling and logs that make failures visible and diagnosable.
SkillAFreshness: AClaude Code +9
Cite this page
break-down-work skill. Agent Mart. https://agentmart.dev/skills/yauhenbichel-break-down-work (last updated 2026-10-24)