lerim-dev/docs/cli
docs/cli/SKILL.md
# lerim skill Install Lerim's bundled skill, register instruction artifacts, and review evidence-backed skill update proposals. For the end-to-end dashboard review workflow, see [Skill Updates](../guides/skill-updates.md). ## Install ```bash lerim skill install ``` This copies the repo-shipped Lerim skill files into standard agent skill locations so supported agents can query Lerim before they start work. ## Register Targets Register any skill or instruction artifact Lerim should monitor:
$ install --global
skillsauthnpx skillsauth add lerim-dev/lerim-cli docs/cliInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 3, 2026, 4:02 AM77.7s23 files scanned
SKILL.md
lerim skill
Install Lerim's bundled skill, register instruction artifacts, and review evidence-backed skill update proposals.
For the end-to-end dashboard review workflow, see Skill Updates.
Install
lerim skill install
This copies the repo-shipped Lerim skill files into standard agent skill locations so supported agents can query Lerim before they start work.
Register Targets
Register any skill or instruction artifact Lerim should monitor:
lerim skill target add ~/.agents/skills/clean-code --description "Keep simplification guidance current"
lerim skill target list
lerim skill target show it_abc123
Supported targets include skill directories, SKILL.md, AGENTS.md,
CLAUDE.md, GEMINI.md, and related instruction files. Proposal paths are
limited to files scanned as part of the registered target; skill bundles may
also propose new files under references/, reference/, or examples/.
Targets inside a registered Lerim project are scoped to that project. Targets
outside registered projects are global and may learn from registered project
records.
Auto-Apply
Targets default to review mode. Auto-apply is opt-in and remains bounded by the target policy:
lerim skill target auto-apply it_abc123 --enable --risk low
lerim skill target auto-apply it_abc123 --disable
Automatic application only runs for pending proposals that pass validation, guard checks, risk limits, changed-file limits, added-line limits, and removed-line limits. Scripts, assets, config files, and frontmatter stay blocked unless the target policy explicitly allows them.
Refresh And Review
Run a scan to compile proposals from scoped context records:
lerim skill refresh it_abc123
lerim skill refresh clean-code --record-limit 120 --json
Review proposals before applying or rejecting them:
lerim skill proposal list
lerim skill proposal list --target-id it_abc123 --status pending_review
lerim skill proposal show ip_abc123
lerim skill proposal apply ip_abc123
lerim skill proposal reject ip_abc123
Applying is allowed only for pending, guard-accepted, validation-passing proposals whose file baselines still match the current target files. Terminal proposals such as applied or rejected proposals cannot be edited back into review.
The dashboard Skills tab shows the same proposal lifecycle with a line-numbered diff, full-file preview, and confirmation flow before writes happen.
What to do next
Add a short Lerim startup instruction to the repository's agent instruction file,
such as AGENTS.md, CLAUDE.md, or another tool-specific instruction file.
The instruction should tell agents to use Lerim when past project context may
matter, not as a ritual for every chat.
The recommended startup flow is:
lerim context-brief show
lerim working-memory show
See Agent Startup Context for the full install, instruction snippet, and verification flow.
Related Skills
lerim-dev/lerim
testing
VerifiedTrustedCommunity
Query Lerim's persistent project context before agent work. Use it to check prior decisions, constraints, preferences, and historical context through exact queries or synthesized answers.
91SKILL.mdUpdated May 15, 2026
openclaw/taskflow
tools
VerifiedTrustedCommunity
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
357,764SKILL.mdUpdated Apr 10, 2026
openclaw/extensions/lobster
tools
VerifiedTrustedCommunity
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
357,764SKILL.mdUpdated Apr 10, 2026
steipete/extensions/lobster
tools
VerifiedTrustedCommunity
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
357,588SKILL.mdUpdated Apr 13, 2026