lading-preflight

Environment validation checklist. Run this FIRST when starting a new Claude session to verify the environment is ready for optimization work. Checks Rust toolchain, ci/ scripts, build, benchmarking tools, profilers, memory tools, git state, and SMP CLI.

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

93%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 tight, highly actionable preflight skill: runnable command, explicit stop-on-failure checkpoint, and a concrete fix table, with bundle references that resolve to real files. The only gap is not explicitly instructing a re-run of preflight after applying a fix.

Suggestions

Add an explicit feedback loop step: after a fix is applied and confirmed by the user, re-run `.claude/skills/lading-preflight/scripts/preflight` to verify the check now passes before proceeding.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept explanations Claude already knows; the single command plus a fixes table means every token earns its place and it assumes Claude's competence.	5 / 5
Actionability	It gives a copy-paste runnable command and a table mapping every failed check to a specific executable fix (e.g. `cargo install cargo-nextest`, `chmod +x ci/*`), covering the common cases fully.	5 / 5
Workflow Clarity	The sequence is clear with an explicit checkpoint ("STOP on any failure") and an ask-before-proceeding gate, but the feedback loop of re-running preflight after a fix to confirm resolution is only implied, a minor validation gap.	4 / 5
Progressive Disclosure	A short, well-organized body under 50 lines with one-level-deep references to real bundle scripts (scripts/preflight and scripts/install_smp both exist), so the simple-skill exception applies and navigation is easy.	5 / 5
	Total	19 / 20 Passed

Description

80%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, third-person description that explicitly covers both what it does and when to use it, with a well-scoped niche. The main weakness is trigger-term naturalness: it relies on technical framing rather than the phrasings users actually say.

Suggestions

Add user-natural trigger phrases such as "Use when starting a session, checking your environment, or verifying the toolchain is set up" to improve trigger-term quality.

Lead with the action verbs (e.g. "Validates and reports..." instead of "Environment validation checklist") so capabilities read as performed actions.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates concrete components checked ("Rust toolchain, ci/ scripts, build, benchmarking tools, profilers, memory tools, git state, and SMP CLI"), giving broad concrete coverage, though it frames items as what is checked rather than distinct performed actions.	4 / 5
Completeness	Clearly answers what (an environment validation checklist checking the listed toolchain/components) and when ("Run this FIRST when starting a new Claude session to verify the environment is ready for optimization work") with an explicit trigger clause, so it is not capped at 3.	5 / 5
Trigger Term Quality	It has an explicit trigger ("Run this FIRST when starting a new Claude session") and terms like "environment validation", but misses the natural everyday phrases a user would say (e.g. "check my setup", "verify environment") and lacks synonyms.	3 / 5
Distinctiveness Conflict Risk	The toolchain-specific terms (lading/payloadtool, hyperfine, criterion, smp, ci/ scripts) carve a clear niche tied to optimization work, making conflict with unrelated skills minimal.	5 / 5
	Total	17 / 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: DataDog/lading
Path: .claude/skills/lading-preflight/SKILL.md
Commit: 9d2b913

Reviewed: 1 day 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.