lfg

Run the full autonomous shipping pipeline end-to-end, hands-off with no check-ins. Use only when the user explicitly asks to build or ship something autonomously all the way to an open PR, or invokes lfg directly — it pushes and opens a PR without stopping. Not for in-the-loop work where the user reviews each step: use ce-plan, ce-work, ce-debug, or ce-commit-push-pr instead.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured orchestration skill: a numbered pipeline with explicit gates and recovery logic, concrete commands and skill invocations, and clean one-level-deep progressive disclosure into real reference files. The only weakness is mild verbosity in the 'Only it carries…' justification clauses.

Suggestions

Tighten the recurring 'Only it carries X, Y, Z…' justification clauses — state what to read and the one critical rule it enforces, dropping the enumerated rationale that pads each step.

Consider folding the repeated 'before step 1' / 'first' / 'now' read directives into a single upfront reading list, since several references are requested at overlapping moments.

Dimension	Reasoning	Score
Conciseness	The body is dense and procedural, assuming Claude knows git/PR/CI concepts, but the repeated 'Only it carries…' justification enumerations are somewhat padded and could be trimmed, placing it just below the lean 5 anchor.	4 / 5
Actionability	Provides concrete executable guidance — `git remote`, `gh pr view --json number,url,state`, and specific skill invocations with modes like `mode:return-to-caller <plan-path>` and `mode:pipeline branding:on` — with minor gaps where detail is delegated to reference files.	4 / 5
Workflow Clarity	A clearly sequenced 10-step pipeline with explicit 'GATE: STOP' validation checkpoints, defined stop conditions (blocked status, invalidating findings), and feedback logic (re-invoke ce-plan only when no blocker and no plan exists), matching the top anchor for sequence + validation + recovery.	5 / 5
Progressive Disclosure	The body is an orchestration overview that points to well-signaled, one-level-deep reference files (stage-routing.md, plan-brief.md, work-return.md, review-followup.md, shipping-tail.md, task-visibility.md), all of which exist in ./references/, with content appropriately split between the overview and the detail files.	5 / 5
	Total	18 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-scoped description that clearly states what the skill does, when to use it, and when not to, while distinguishing it from related in-the-loop skills. Trigger phrasing is natural and concrete, with only minor room for additional synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain (autonomous shipping pipeline) and several concrete actions — 'Run the full autonomous shipping pipeline end-to-end', 'it pushes and opens a PR without stopping', 'hands-off with no check-ins' — with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the comprehensive 5.	4 / 5
Completeness	Explicitly answers both what ('Run the full autonomous shipping pipeline end-to-end, hands-off') and when ('Use only when the user explicitly asks to build or ship something autonomously…or invokes lfg directly'), with concrete trigger phrases plus a negative-when clause, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say — 'build or ship something autonomously', 'all the way to an open PR', 'invokes lfg directly' — giving good keyword coverage, though a few synonyms are missing so it stops short of the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (hands-off, no check-ins, all the way to an open PR) and explicitly contrasts against sibling skills ('Not for in-the-loop work…use ce-plan, ce-work, ce-debug, or ce-commit-push-pr instead'), giving minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: EveryInc/compound-engineering-plugin
Path: skills/lfg/SKILL.md
Commit: 26bf5b1

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.