launch-readiness-auditor

Use when the user asks to "audit our launch plan", "are we ready to launch", or evaluate launch execution/outcomes; runs one typed RAMP preflight, execution, or outcome profile without mixing time horizons. Not for recording launch state — use launch-registry; not for running launch day — use launch-day-conductor. 发布就绪审计/RAMP分阶段评估/发布前放行

Quality

84%

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

81%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.

The body is a lean, domain-assuming instruction set with concrete commands, an explicit validation checklist, and a revalidate feedback loop. Its main gaps are minor reference-list duplication and several referenced files that are not present in the skill bundle, which slightly weaken conciseness and progressive disclosure.

Suggestions

De-duplicate the 'Runtime Reads' bullet list and the 'Runtime and Setup' paragraph, which re-state overlapping reference paths.

Verify the referenced files (auditor-runbook.md, scoring-semantics.md, ramp-benchmark.md, runtime-invocation.md, measurement-protocol.md) exist at the cited ../../../references/ location, or mark them as root-install-only vs. standalone-bundle.

Inline one minimal run.json example so the rubric-score.py invocation is copy-paste runnable without opening an external file.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes RAMP/item-ID fluency rather than explaining basics Claude already knows; not a 5 because the 'Runtime Reads' list and the 'Runtime and Setup' paragraph re-list overlapping reference paths, a minor trim opportunity.	4 / 5
Actionability	Provides concrete, executable guidance such as `python3 "$AARON_SKILLS_ROOT/scripts/rubric-score.py" score <run.json>`, an env-var resolution expression, and exact veto IDs (RAMP-R1/A1/M1/P1); not a 5 because most worked detail lives in referenced files rather than inline copy-paste examples.	4 / 5
Workflow Clarity	Clear sequenced procedure (declare profile → score → verify vetoes → report → persist) with an explicit Validation Checkpoints checklist and a persistence feedback loop ('validate the complete v3 draft... revalidate the target'), matching the top anchor.	5 / 5
Progressive Disclosure	Well-organized overview with one-level-deep references signaled via clear sections (Runtime Reads, Reference Materials); not a 5 because only references/auditor-runtime.md exists in the bundle while several referenced paths (auditor-runbook.md, scoring-semantics.md, ramp-benchmark.md, runtime-invocation.md, measurement-protocol.md) are not present in ./references/.	4 / 5
	Total	17 / 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.

The description is strong: it states a concrete capability, gives natural trigger phrases, and explicitly disambiguates from neighboring skills. Its main weakness is trigger-term breadth — only two phrasings are given — which keeps trigger quality and specificity at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the launch-audit domain and concrete actions ('runs one typed RAMP preflight, execution, or outcome profile without mixing time horizons'); not a 5 because the underlying action set is essentially one audit operation with three profile variants rather than multiple distinct concrete actions.	4 / 5
Completeness	Explicitly answers both what ('runs one typed RAMP preflight, execution, or outcome profile') and when ('Use when the user asks to...') with concrete trigger phrases, matching the anchor.	5 / 5
Trigger Term Quality	Includes natural user phrases ('audit our launch plan', 'are we ready to launch') that users would actually say; not a 5 because coverage of synonyms/variations is narrow (no 'launch readiness', 'go/no-go', 'ship readiness' phrasing).	4 / 5
Distinctiveness Conflict Risk	Clear niche (launch readiness auditing) with explicit exclusion of sibling skills ('Not for recording launch state — use launch-registry; not for running launch day — use launch-day-conductor'), minimizing conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 9 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: launch/mobilize/launch-readiness-auditor/SKILL.md
Commit: 9df28a0

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.