CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lfg

Take a request all the way to done, hands-off, through the right Compound Engineering skills. A code change ends as an open pull request, pushed without stopping. Use only when the user explicitly asks for autonomous end-to-end work or invokes lfg directly. Use ce-plan, ce-work, ce-debug, or ce-commit-push-pr for work the user reviews step by step.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

96%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.

An exceptionally tight orchestration skill: concrete parameterized invocations, explicit status gates and stop conditions, and a well-organized reference bundle. The only structural weakness is mild second-level chaining among the reference files themselves.

DimensionReasoningScore

Conciseness

The body is lean and rule-dense with zero padding and no explanations of concepts Claude already knows — e.g., "Blocked status outranks an existing artifact and is never retried" — so every token earns its place, matching the 5 anchor rather than the 4 anchor's "minor instances of over-explanation".

5 / 5

Actionability

Invocations are copy-paste ready with exact modes and arguments ("invoke the ce-work skill with mode:return-to-caller <plan-path-from-step-1>", "ce-simplify-code ... mode:pipeline and size-cutoff:30", "ce-commit-push-pr ... mode:pipeline branding:on", "Run git remote once", "Output <promise>DONE</promise>"), fully matching the 5 anchor's executable guidance.

5 / 5

Workflow Clarity

The 11-step run is clearly sequenced with explicit validation gates ("Only a valid status: complete from ce-work may advance; every other status or malformed return stops the pipeline"), a bounded feedback loop for the ce-plan retry, a stop-conditions checklist, and fenced irreversible actions, matching the 5 anchor; no destructive-operation validation cap applies since gating is present.

5 / 5

Progressive Disclosure

The body is a well-signaled overview and all 8 cited reference files exist with clear statements of what each governs ("it governs steps 9 through 11"), but reference files chain into other reference files (intake.md points to five others; shipping.md to next-work-handoff.md; review-followup.md to tracker-defer.md), a mild second-level nesting that falls short of the 5 anchor's one-level-deep ideal while clearly exceeding the 3 anchor.

4 / 5

Total

19

/

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 description that explicitly states both capability and a tightly gated trigger condition, and even disambiguates against sibling skills. Trigger keywords are natural and specific, with only minor synonym coverage gaps.

DimensionReasoningScore

Specificity

The description lists several concrete behaviors — "A code change ends as an open pull request, pushed without stopping" and routing through named skills ("ce-plan, ce-work, ce-debug, or ce-commit-push-pr") — but non-code outcomes are only implied by "Take a request all the way to done", leaving minor gaps in coverage that keep it below the comprehensive 5 anchor and clearly above the 1-2-action 3 anchor.

4 / 5

Completeness

Both what ("Take a request all the way to done... A code change ends as an open pull request, pushed without stopping") and when ("Use only when the user explicitly asks for autonomous end-to-end work or invokes lfg directly") are explicitly and concretely stated, exceeding the 4 anchor where the 'when' could be more specific.

5 / 5

Trigger Term Quality

Natural trigger phrasing is present ("autonomous end-to-end work", "hands-off", "invokes lfg directly", "all the way to done"), matching real user requests, but common variations such as "just do it", "ship it", or "don't check with me" are missing, which fits the 4 anchor's "good keyword coverage; a few natural terms missing" rather than the 5 anchor's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The gated trigger ("Use only when the user explicitly asks... or invokes lfg directly") plus the explicit contrast with sibling skills ("Use ce-plan, ce-work, ce-debug, or ce-commit-push-pr for work the user reviews step by step") carves a clear niche with minimal conflict risk, matching the 5 anchor.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.