plan-task
Use when asked to plan, design, architect, scope, or break down a feature or change before implementation.
Skill by drimchansky
Chalk Labs
Need help deploying plan-task?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/drimchansky-plan-task
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
Use cases: design, productivity
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/plan-task
What's inside
- Skill name
plan-task- Description
- Use when asked to plan, design, architect, scope, or break down a feature or change before implementation.
- License
- unknown
- Instructions
- 141 lines in SKILL.md · view on GitHub
Files (3)
- AGENTS.md
- SKILL.md
- references
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from drimchansky/agents-kit
- 0.582score
create-notion-page
drimchansky
Use when asked to create a Notion page — drafts the requested content and creates the page through the session's Notion tools, private by default unless the…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
decompose-task
drimchansky
Use when an approved design doc (ADR, accepted RFC, epic-scale ask) should become several tickets and task folders — proposes the decomposition into ordered…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
explore
drimchansky
Use when asked to explore, explain, walk through, describe, teach, or analyze a topic — code, a library or API, a protocol, a system, a concept, or a domain…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
fix-findings
drimchansky
Use when asked to fix code or documentation findings from a session review, PR comments, or a pasted or saved list.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
implement-task
drimchansky
Use when asked to implement, execute, run, or carry out a task's plan from a task folder (canonically under `.agents/tasks/`) — by task folder path, or the…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
prepare-epic
drimchansky
Use when asked to prepare, draft, or write up an epic or its description — drafts it to a file in the kit's default epic shape from a raw description, a PRD…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
prepare-ticket
drimchansky
Use when asked to prepare, draft, or write up a ticket or issue from a described task — turns it into a self-contained ticket file describing the real…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
publish-pr-review
drimchansky
Use when asked to publish review-code's findings to the PR on GitHub — offers its Critical/Major findings, its Minor findings, and its improvements as counted…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
format-dictation
drimchansky
Use when asked to format dictated text or a transcript, applying spoken punctuation, layout, emoji, and editing commands while preserving the speaker's wording.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
implement
drimchansky
Use when asked to implement, build, fix, or change something directly — described in the session or pointing at a file, issue, or diff — with no task folder…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
init-config
drimchansky
Use when asked to create, update, or repair this machine's agents-kit config — discovers task roots or configures a requested runbook directory, compares…
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
proofread
drimchansky
Use when asked to proofread, check, review, or polish a message, email, or piece of writing.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 6, 2026 (24 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/drimchansky/agents-kit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from drimchansky
- 0.582score
decompose-task
drimchansky
Use when an approved design doc (ADR, accepted RFC, epic-scale ask) should become several tickets and task folders — proposes the decomposition into ordered…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
create-notion-page
drimchansky
Use when asked to create a Notion page — drafts the requested content and creates the page through the session's Notion tools, private by default unless the…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
fix-findings
drimchansky
Use when asked to fix code or documentation findings from a session review, PR comments, or a pasted or saved list.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
implement-task
drimchansky
Use when asked to implement, execute, run, or carry out a task's plan from a task folder (canonically under `.agents/tasks/`) — by task folder path, or the…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
explore
drimchansky
Use when asked to explore, explain, walk through, describe, teach, or analyze a topic — code, a library or API, a protocol, a system, a concept, or a domain…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
prepare-epic
drimchansky
Use when asked to prepare, draft, or write up an epic or its description — drafts it to a file in the kit's default epic shape from a raw description, a PRD…
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get plan-task running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
plan-task skill. Agent Mart. https://agentmart.dev/skills/drimchansky-plan-task (last updated 2026-10-24)