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/ravensorb-l3io-setup
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
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/l3io-setup
What's inside
- Skill name
l3io-setup- Description
- Sets up the LiquidLogicLabs PM module in a project. Use when the user requests to 'install l3io-pm', 'configure l3io-pm', or 'setup l3io-pm'.
- License
- MIT
- Instructions
- 64 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (12)
- SKILL.md
- agent-instructions.md · assets/
- module-help.csv · assets/
- module-setup.md · assets/
- module.yaml · assets/
- customize.toml
- payload-manifest.json
- config-resolution.md · references/
- merge-config.py · scripts/
- merge-help-csv.py · scripts/
- pm-status.py · scripts/
- write-module-config.py · scripts/
SKILL.md (first lines)
# l3io-setup — Module Setup
## Overview
Records the `l3io-pm` module's project-level settings in the BMad central config, and
registers its capabilities for the help system.
**This runs only when asked.** `l3io-pm` declares no required settings, so a correct install
has no `[modules.l3io-pm]` section at all and every PM skill works without one. An absent
section is **not** a first-run — see `references/config-resolution.md` §5. Nothing here is
triggered automatically.
## On Activation
1. Read `{skill-root}/assets/module.yaml` for module identity (`code`, `name`, `module_version`) and any
declared `variables:`.
2. Resolve `{project-root}` to a real absolute path. The merge scripts reject an unresolved
`{project-root}` token in a path argument, because writing to a literal `{project-root}/`
directory under the skill folder is silent and hard to notice.
3. Follow `{skill-root}/assets/module-setup.md` — the canonical procedure, shared across every l3io
module. It states what setup writes and, just as importantly, what it must not.
## What this writes
Only the two human-authored config layers, which the installer never regenerates:
- `{project-root}/_bmad/custom/config.toml` — team-scoped, committed
- `{project-root}/_bmad/custom/config.user.toml` — user-scoped, gitignored
```bash
uv run {skill-root}/scripts/merge-config.py \
--project-root "{resolved-project-root}" \
--module-yaml "{skill-root}/assets/module.yaml" \
--answers "{answers-json-path}"
```
## What this does not write
`_bmad/_config/bmad-help.csv` — **the installer assembles it** from each module's own
`assets/module-help.csv` at install time. `{skill-root}/scripts/merge-help-csv.py` exists for the module
contract and for manual re-registration after an interrupted install; this skill does not call
it, because two writers on one file is how that file drifts.
## Completion
Report which layers were written and which keys landed in each, then print the module greeting
from `assets/module.yaml`.
## `scripts/pm_status/` — carried, never invoked here
This skill also ships `scripts/pm_status/`. Nothing in this file or in
`assets/module-setup.md` calls it — that is deliberate, not dead payload left behind by a
refactor. `l3io-setup` is `pm-status.py`'s one payload copy for the whole `l3io-pm` module
(Task 11A): `l3io-execute`, `l3io-plan`, and `l3io-sync` each self-install it from
here, reading `{skill-root}/../l3io-setup/scripts/pm_status/__main__.py` at their own activation
(`l3io-execute/steps/shared/step-00-activate.md` §2, and each of the three carries its own
copy), because `.claude-plugin/marketplace.json` declares
all five `l3io-pm` skills as one unit — provided the installer accepts each skill's SKILL.md
frontmatter (see `step-00-activate.md` §2's own note on this; a rejected sibling is not this
skill's failure to guard against, that guard already lives there). Before removing this file
as apparent dead weight, check those three skills' step-00-activate.md first — this is the one
file across the whole package they depend on being here.From ravensorb/bmad-extensions, MIT.
More from ravensorb/bmad-extensions
- 0.570score
l3io-arch-review
ravensorb
Engineering-standards architecture guardrails and review.
SkillAFreshness: AClaude Code +9 - 0.570score
l3io-execute
ravensorb
Run the l3io-pm plan — full, single epic, or single sprint.
SkillAFreshness: AClaude Code +9 - 0.570score
l3io-help
ravensorb
Read project state and recommend the exact next l3io action, or list every installed l3io skill.
SkillAFreshness: AClaude Code +9 - 0.570score
l3io-plan
ravensorb
Validate readiness, elaborate stories, estimate, build dependency graph, and produce an executable plan.
SkillAFreshness: AClaude Code +9 - 0.570score
l3io-sec-redteam
ravensorb
Red team security analysis agent.
SkillAFreshness: AClaude Code +9 - 0.570score
l3io-sync
ravensorb
Bidirectional sync between l3io-pm state and GitHub Issues.
SkillAFreshness: AClaude Code +9 - 0.570score
l3io-doctor
ravensorb
Migration and housekeeping utilities for BMad artifacts and l3io-pm state.
SkillAFreshness: AClaude Code +9 - 0.556score
l3io-pm-help
ravensorb
DEPRECATED forwarder for /l3io-help — renamed in 3.1.3.
SkillAFreshness: AClaude Code +9 - 0.556score
l3io-pm-plan
ravensorb
DEPRECATED forwarder for /l3io-plan — renamed in 3.1.3.
SkillAFreshness: AClaude Code +9 - 0.556score
l3io-pm-sync
ravensorb
DEPRECATED forwarder for /l3io-sync — renamed in 3.1.3.
SkillAFreshness: AClaude Code +9 - 0.556score
l3io-pm-execute
ravensorb
DEPRECATED forwarder for /l3io-execute — renamed in 3.1.3.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 22, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ravensorb/bmad-extensions
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ravensorb
- 0.570score
l3io-arch-review
ravensorb
Engineering-standards architecture guardrails and review.
SkillAFreshness: AClaude Code +9 - 0.570score
l3io-execute
ravensorb
Run the l3io-pm plan — full, single epic, or single sprint.
SkillAFreshness: AClaude Code +9 - 0.570score
l3io-help
ravensorb
Read project state and recommend the exact next l3io action, or list every installed l3io skill.
SkillAFreshness: AClaude Code +9 - 0.570score
l3io-plan
ravensorb
Validate readiness, elaborate stories, estimate, build dependency graph, and produce an executable plan.
SkillAFreshness: AClaude Code +9 - 0.570score
l3io-sec-redteam
ravensorb
Red team security analysis agent.
SkillAFreshness: AClaude Code +9 - 0.570score
l3io-sync
ravensorb
Bidirectional sync between l3io-pm state and GitHub Issues.
SkillAFreshness: AClaude Code +9
Cite this page
l3io-setup skill. Agent Mart. https://agentmart.dev/skills/ravensorb-l3io-setup (last updated 2026-10-24)