launch-day-conductor

Use when the user asks to "run my launch day", "build a launch day runbook / war room", or "decide CONTINUE or ROLLBACK after the push"; produces a pre-conditions gate check (launch-readiness-auditor SHIP verdict + the authoritative date in launch-registry — missing either stops the skill), a dated hour-blocked runbook with owners (morning irreversible pushes, daytime monitoring loop, evening consolidation), a forced observation-window verdict after every irreversible action against pre-declared kill criteria, a P0-P3 incident ladder with rollback playbooks, and T-0 status lines for the registry proposal protocol. Not for channel submission content and platform rules — use community-launch-runner; not for media replies — use press-media-relations. 发布日runbook/作战室/观察窗/回滚裁决/发布日指挥

Quality

83%

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

73%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 well-structured, highly actionable launch-day runbook with strong workflow clarity and explicit validation feedback loops. Its main weakness is redundancy around the registry-proposal protocol and reliance on external (non-bundled) reference paths.

Suggestions

State the "registry proposals go only via authorized operation: propose to registry-events.py, never to canonical files" rule once in the Skill Contract and reference it, instead of repeating the full caveat in Instructions step 6, Save Results, and Reference Materials.

Show the concrete registry-events.py invocation (arguments / event shape) once in Data Sources or Instructions so the action is fully copy-paste executable rather than protocol-described.

Bundle or verify the referenced files (ramp-benchmark.md, state-model.md, action-control.md, CONNECTORS.md, SECURITY.md) so the progressive-disclosure references resolve inside the skill bundle.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no concept explanations) but restates the "authorized operation: propose request to registry-events.py / never canonical registry files" caveat across the Skill Contract, Instructions step 6, Save Results, and Reference Materials, adding noticeable redundancy.	3 / 5
Actionability	Gives concrete, actionable guidance with specific paths (memory/launch/launch-day-conductor/, memory/events/launches.ndjson), scripts (registry-events.py, scripts/connectors/hn.py), runbook column lists, and enumerated verdict values, with only minor gaps such as the exact registry-events.py invocation syntax.	4 / 5
Workflow Clarity	An 8-step numbered sequence with explicit validation checkpoints (hard gate → NEEDS_INPUT, observation-window → CONTINUE/ROLLBACK, lane-join → OPEN on missing/partial receipts) and a "Done when" checklist, satisfying the feedback-loop expectation for this destructive/batch skill.	5 / 5
Progressive Disclosure	Well-organized sections with a clearly signaled one-level-deep Reference Materials list, but the referenced files are external repo paths (../../../references/, sibling SKILL.md) rather than files present in the local bundle, which limits in-bundle verifiability.	4 / 5
	Total	16 / 20 Passed

Description

92%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 specific, complete, and distinctive, with explicit trigger phrases and clear negative-scope boundaries against sibling skills. Its only weak spot is some embedded jargon and redundant trailing keywords that slightly dilute trigger-term naturalness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "a pre-conditions gate check", "a dated hour-blocked runbook with owners", "a forced observation-window verdict", "a P0-P3 incident ladder with rollback playbooks", and "T-0 status lines" — giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both what (gate check, runbook, verdicts, incident ladder, status lines) and when ("Use when the user asks to..." with concrete trigger phrases), plus negative-scope guidance, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural user phrases ("run my launch day", "build a launch day runbook / war room", "decide CONTINUE or ROLLBACK after the push") with synonyms, but the appended Chinese keywords and jargon ("SHIP verdict", "registry proposal protocol") keep it just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche (launch-day war-room conductor) and explicit disambiguation ("Not for channel submission content... use community-launch-runner; not for media replies — use press-media-relations"), giving minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

75%

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 — 12 / 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: 32 suspicious	Warning
referenced_paths_exist	Referenced path issues: 4 missing, 4 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: launch/mobilize/launch-day-conductor/SKILL.md
Commit: 5cd4a80

Reviewed: 5 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.