implement
Build a specific feature or improvement using Factory's multi-agent system.
Skill by boston-harness-group
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/boston-harness-group-implement
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, agent-building
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 and code. 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/implement
What's inside
- Skill name
implement- Description
- Build a specific feature or improvement using Factory's multi-agent system. Runs the Factory CEO in focus mode to study the codebase, generate a hypothesis, build the change, review it, and evaluate the result. Use when the user says 'implement X', 'build X', 'add X feature', or wants autonomous multi-agent development on a specific task.
- License
- MIT
- Instructions
- 49 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# /factory:implement
Build a specific feature or improvement using the Factory's multi-agent system.
The user wants to build: **$ARGUMENTS**
## Prerequisites
The `factory` CLI must be installed. Check and install from the plugin's bundled source:
```bash
command -v factory >/dev/null 2>&1 || uv tool install "${CLAUDE_PLUGIN_ROOT}"
```
## Execution
The project must have `.factory/` initialized (run `factory ceo "$(pwd)"` or `/factory:study` first). Focus mode requires improve mode — it will error if the project hasn't been set up yet.
Run the Factory CEO in **focus mode** on the current project:
```bash
factory ceo "$(pwd)" --focus "$ARGUMENTS"
```
This will:
1. **Study** the codebase and generate observations
2. **Strategize** a single targeted hypothesis for "$ARGUMENTS"
3. **Build** the change on a feature branch with a PR
4. **Review** the change against guard rules and scope constraints
5. **Evaluate** before/after scores to verify improvement
6. **Keep or revert** based on eval results and precheck gates
7. **Archive** learnings for future cycles
## If the CLI is not available
If `factory` cannot be installed (e.g. no `uv` available), tell the user:
```
To use /factory:implement, install the Factory CLI:
uv tool install /path/to/remote-factory
# or from git
uv tool install git+https://github.com/akashgit/remote-factory
Then re-run this command.
```From boston-harness-group/remote-factory, MIT.
More from boston-harness-group/remote-factory
- 0.667score
factory
boston-harness-group
Launch the Factory CEO agent to autonomously evolve any software project through systematic experimentation.
SkillAFreshness: A★ 72Claude Code +9 - 0.629score
pipeline
boston-harness-group
Design and execute a custom multi-agent pipeline for any goal.
SkillBFreshness: B★ 72Claude Code +9 - 0.629score
pipeline-subagents
boston-harness-group
Design and execute a custom multi-agent pipeline using Claude Code subagents directly.
SkillBFreshness: B★ 72Claude Code +9 - 0.629score
status
boston-harness-group
Show the current Factory status for this project, including project state, experiment history, eval scores, and active backlog.
SkillBFreshness: B★ 72Claude Code +9 - 0.629score
study
boston-harness-group
Analyze the current codebase using Factory's observation engine and code graph.
SkillBFreshness: B★ 72Claude Code +9 - 0.608score
workflow-design-v2
boston-harness-group
Run the design-v2 workflow.
SkillBFreshness: B★ 72Claude Code +9
Signals
- Stars
- 72
- Forks
- 30
- Open issues
- 51
- Last commit (this folder)
- Apr 28, 2026 (6 months ago)
- Last release
- Aug 7, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from boston-harness-group
- 0.667score
factory
boston-harness-group
Launch the Factory CEO agent to autonomously evolve any software project through systematic experimentation.
SkillAFreshness: A★ 72Claude Code +9 - 0.629score
pipeline
boston-harness-group
Design and execute a custom multi-agent pipeline for any goal.
SkillBFreshness: B★ 72Claude Code +9 - 0.629score
pipeline-subagents
boston-harness-group
Design and execute a custom multi-agent pipeline using Claude Code subagents directly.
SkillBFreshness: B★ 72Claude Code +9 - 0.629score
status
boston-harness-group
Show the current Factory status for this project, including project state, experiment history, eval scores, and active backlog.
SkillBFreshness: B★ 72Claude Code +9 - 0.629score
study
boston-harness-group
Analyze the current codebase using Factory's observation engine and code graph.
SkillBFreshness: B★ 72Claude Code +9 - 0.608score
workflow-design-v2
boston-harness-group
Run the design-v2 workflow.
SkillBFreshness: B★ 72Claude Code +9
Cite this page
implement skill. Agent Mart. https://agentmart.dev/skills/boston-harness-group-implement (last updated 2026-10-24)