Chalk Labs
Need help deploying do-work?
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/tregusti-do-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
Use cases: 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/do-work
What's inside
- Skill name
do-work- Description
- Executes a unit of work in this project. Use when asked to implement a feature, fix a bug, or complete any scoped development task in this project.
- License
- MIT
- Instructions
- 40 lines in SKILL.md · view on GitHub
Files (2)
- QA.md
- SKILL.md
SKILL.md (first lines)
# Do Work This skill should describe all meta stuff around one specific task. Adding or removing labels on issues, commiting, pushing. ## Definitions - **PRD**: Product Requirement Document, an issue that might exist. If so, it's a parent issue to some traces bullet slice "task issues". - **Task issue**: The issue that contains the Issue Spec. - **QA issue**: The issue created with the QA steps for a human to verify the implementation - **Issue spec**: The issue description and any comments on the issue that clarify the requirements or constraints. This is the source of truth for what needs to be implemented. It may be in the form of an Agent Brief or a more traditional issue description. - **Agent Brief**: A structured format for specifying work to be done, used by AFK agents. An Agent Brief is a type of issue spec, but not all issue specs are Agent Briefs. It is defined in the skill `triage`. ## Workflow 1. If github issue: - remove label `agent:implement` - add label `agent:in-progress` 2. Implement the issue spec using the `implement` skill. 3. Create a new QA issue using the `QA.md` template in this skill directory and add the `human:qa` label. If the task issue is part of a PRD, make the QA issue a _sub-issue_ to the PRD. 4. Commit the changes. 5. Push to remote. 6. If github issue, remove label `agent:in-progress`. ## Rules 1. Only work on one task/issue at a time! 2. Do not explicitly close any issues on github. Only implicitly by referencing them in commit messages and PRs.
From tregusti/skills, MIT.
More from tregusti/skills
- 0.524score
align-markdown-tables
tregusti
Align (pretty-print) GFM pipe tables so columns line up.
SkillBFreshness: BClaude Code +9 - 0.524score
implement
tregusti
Implements a task in this project.
SkillBFreshness: BClaude Code +9 - 0.523score
commit
tregusti
Provides a standardized commit message template.
SkillBFreshness: BClaude Code +9 - 0.523score
find-work
tregusti
Finds a unit of work to implement in this project.
SkillBFreshness: BClaude Code +9 - 0.521score
sandcastle-resume
tregusti
Resumes a crashed sandcastle AFK run (idle-sleep connection drop, session limit, or any other abort) by finishing the interrupted ticket in the background and…
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Aug 18, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/tregusti/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from tregusti
- 0.524score
align-markdown-tables
tregusti
Align (pretty-print) GFM pipe tables so columns line up.
SkillBFreshness: BClaude Code +9 - 0.524score
implement
tregusti
Implements a task in this project.
SkillBFreshness: BClaude Code +9 - 0.523score
commit
tregusti
Provides a standardized commit message template.
SkillBFreshness: BClaude Code +9 - 0.523score
find-work
tregusti
Finds a unit of work to implement in this project.
SkillBFreshness: BClaude Code +9 - 0.521score
sandcastle-resume
tregusti
Resumes a crashed sandcastle AFK run (idle-sleep connection drop, session limit, or any other abort) by finishing the interrupted ticket in the background and…
SkillBFreshness: BClaude 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 do-work 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
do-work skill. Agent Mart. https://agentmart.dev/skills/tregusti-do-work (last updated 2026-10-24)