continue-work
Drive the current work to completion autonomously - build the real list of what is outstanding from the conversation itself, decide every open fork yourself…
Skill by TheMoMatthias
Chalk Labs
Need help deploying continue-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/themomatthias-continue-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: documents, 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/continue-work
What's inside
- Skill name
continue-work- Description
- Drive the current work to completion autonomously - build the real list of what is outstanding from the conversation itself, decide every open fork yourself instead of asking, work the list to done without pausing to check in, and report once at the end. Use when the user says continue, carry on, keep going, don't stop, finish it, stop asking me, just decide, work through everything, do it all, or invokes /continue-work; and whenever a session is mid-task and the user wants it to run unattended rather than hand back after each step.
- License
- unknown
- Instructions
- 103 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from TheMoMatthias/MM-toolbox
- 0.559score
plan-review
TheMoMatthias
The scheduled, read-only plan-conformance pass of the journal-and-queue framework — every four hours compare each open lane's landed tranches and stated NEXT…
SkillAFreshness: AClaude Code +9 - 0.519score
automate-lane-check
TheMoMatthias
Where does THIS lane stand - its register row, its OPEN findings, what it last landed, and WHICH RULINGS LANDED WHILE IT WAS BUSY.
SkillBFreshness: BClaude Code +9 - 0.519score
automate-lane-status
TheMoMatthias
One pass over every lane of a parallel-session programme - what it DID, what it still OWES, what it is DOING right now, and the one column that exists nowhere…
SkillBFreshness: BClaude Code +9 - 0.519score
automate-orchestrator
TheMoMatthias
Re-establish and operate the journal-and-queue coordination framework for a programme of parallel Claude sessions — lanes as durable journals, sessions as…
SkillBFreshness: BClaude Code +9 - 0.519score
automate-realign
TheMoMatthias
The orchestrated variant of /realign - close out a report, summary or "I'm finished" claim without leaving anything on the field.
SkillBFreshness: BClaude Code +9 - 0.519score
lane-tranche
TheMoMatthias
The specialist lane's session discipline under the journal-and-queue framework — read your journal, act on your inbox, do exactly ONE tranche of your NEXT…
SkillBFreshness: BClaude Code +9 - 0.519score
to-execution-plan
TheMoMatthias
Turn an idea, grill outcome, wayfinder map, spec or prototype into a granular two-layer execution plan.
SkillBFreshness: BClaude Code +9 - 0.519score
orchestrator-pass
TheMoMatthias
Run ONE pass of the interactive dispatcher half — read the digest, put every open OPERATOR row in QUEUE.md to the operator as selectable batches with a push…
SkillBFreshness: BClaude Code +9 - 0.516score
implement
TheMoMatthias
Implement all suggested code changes, then test them to ensure correctness.
SkillBFreshness: BClaude Code +9 - 0.494score
tdd
TheMoMatthias
Test-driven development.
SkillBFreshness: BClaude Code +9 - 0.494score
codebase-design
TheMoMatthias
Shared vocabulary for designing deep modules.
SkillBFreshness: BClaude Code +9 - 0.494score
improve-codebase-architecture
TheMoMatthias
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 8, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/TheMoMatthias/MM-toolbox
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from TheMoMatthias
- 0.559score
plan-review
TheMoMatthias
The scheduled, read-only plan-conformance pass of the journal-and-queue framework — every four hours compare each open lane's landed tranches and stated NEXT…
SkillAFreshness: AClaude Code +9 - 0.519score
automate-lane-check
TheMoMatthias
Where does THIS lane stand - its register row, its OPEN findings, what it last landed, and WHICH RULINGS LANDED WHILE IT WAS BUSY.
SkillBFreshness: BClaude Code +9 - 0.519score
automate-lane-status
TheMoMatthias
One pass over every lane of a parallel-session programme - what it DID, what it still OWES, what it is DOING right now, and the one column that exists nowhere…
SkillBFreshness: BClaude Code +9 - 0.519score
automate-orchestrator
TheMoMatthias
Re-establish and operate the journal-and-queue coordination framework for a programme of parallel Claude sessions — lanes as durable journals, sessions as…
SkillBFreshness: BClaude Code +9 - 0.519score
automate-realign
TheMoMatthias
The orchestrated variant of /realign - close out a report, summary or "I'm finished" claim without leaving anything on the field.
SkillBFreshness: BClaude Code +9 - 0.519score
lane-tranche
TheMoMatthias
The specialist lane's session discipline under the journal-and-queue framework — read your journal, act on your inbox, do exactly ONE tranche of your NEXT…
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 continue-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
continue-work skill. Agent Mart. https://agentmart.dev/skills/themomatthias-continue-work (last updated 2026-10-24)