lfg

Run the full autonomous shipping pipeline end-to-end, hands-off with no check-ins: plan, implement, review and fix, commit, push a branch, open a PR, and watch CI to green. 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 to plan, ce-work to implement a plan, ce-debug to fix a bug, or ce-commit-push-pr to commit and open a PR for existing changes.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-3

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

A highly actionable, well-sequenced orchestration skill with explicit gates, validation, and well-signaled one-level references; its only weakness is length, with some repeated contractual detail that could be trimmed.

Suggestions

Consolidate the routing-carrier grammar and the repeated shipping-precondition disclosures so each constraint is stated once and referenced thereafter, reducing body length without losing the load-bearing rules.

Consider moving the detailed carrier-serialization examples and implementation_engine field list into a references file, keeping only the invocable syntax inline to tighten conciseness toward level 3.

Tighten the per-stage prose by converting explanatory sentences into imperative constraints where possible (e.g. the 'A missing remote is a terminal local-only state, not an error' framing could be a one-line rule).

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's intelligence with no concept padding, but it is long and repeats some contractual detail (routing-carrier grammar, shipping-precondition disclosures) that could be tightened; this matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the every-token-earns-its-place brevity of level 3.	2 / 3
Actionability	Gives exact executable invocation syntax — 'mode:return-to-caller implementation_engine:<compact-json> <plan-path>', 'gh pr view --json number,url,state', the carrier regex, and exact commit messages — fully copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	A clearly sequenced 1-10 pipeline with explicit 'GATE: STOP' checkpoints, per-stage validation requirements, and feedback loops (ce-plan retry, verification-evidence recovery), matching the anchor for clear sequence with explicit validation and error-recovery loops.	3 / 3
Progressive Disclosure	Heavy mechanical procedures are split into one-level-deep, well-signaled references (review-followup.md, tracker-defer.md, next-work-handoff.md) — all verified real files with no further nesting — while the orchestration logic stays inline, matching the clear-overview-with-one-level-references anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 description: concrete capabilities, explicit use-when triggers with an anti-trigger carve-out, and clear distinction from sibling skills. Voice stays in the third-person-about-the-user form and avoids the first/second-person penalty.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete pipeline actions verbatim — 'plan, implement, review and fix, commit, push a branch, open a PR, and watch CI to green' — matching the anchor that enumerates several specific actions rather than naming a domain plus a few.	3 / 3
Completeness	Explicitly answers both what (the full shipping pipeline) and when ('Use only when the user explicitly asks to build or ship something autonomously... or invokes lfg directly'), plus an explicit 'Not for...' carve-out, matching the anchor that clearly answers what AND when with explicit triggers.	3 / 3
Trigger Term Quality	Natural user phrasing is present — 'build or ship something autonomously all the way to an open PR' and 'invokes lfg directly' — covering how a user would actually request this; above level 2, which only offers some relevant keywords missing common variations.	3 / 3
Distinctiveness Conflict Risk	The end-to-end autonomous niche is distinct and it names the sibling skills (ce-plan, ce-work, ce-debug, ce-commit-push-pr) it should not collide with, so it is unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 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: a9f6d53

Reviewed: 7 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.