momentum-planner

Use when the user asks to "keep the launch momentum going after launch week", "plan a changelog / release-notes cadence as GTM", or "is this update worth a relaunch"; produces a T+1→T+30 momentum plan — a launch-moment calendar (milestone / shipped-loop / badge moments only), announcement-tier routing (major = full-channel, medium = targeted, minor = changelog-only), a relaunch legitimacy call, spike-to-owned handoff briefs, and the next Tier-1 moment with launch-stacking spacing. Not for the 30-day content-reuse map or paid amplification execution — use content-amplifier; not for planning the next launch end to end — use launch-tier-planner. 抗第二周断崖/changelog-as-GTM/relaunch/下一发布时刻

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

75%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 dense, well-structured instruction skill with concrete paths, gated writes, and clear sequencing that assumes Claude's competence throughout. The main weaknesses are mild repetition of boundary statements, placeholder-only Quick Start templates, and the absence of a rejected-proposal recovery path.

Suggestions

Collapse the repeated scope-boundary statements so each sibling skill is named once (in Reference Materials / Next Best Skill) rather than restated in the intro Scope guard, saving tokens without losing the disambiguation.

Add one fully worked Quick Start example with concrete sample numbers (e.g. a named launch, real spike/decay figures, and the resulting calendar) instead of placeholder templates.

Add a short step or sub-bullet covering what to do when a proposal to registry-events.py is rejected or needs amendment, so the workflow has an explicit recovery path.

Dimension	Reasoning	Score
Conciseness	Lean and operational with no over-explanation of concepts Claude already knows, but the scope boundaries are restated three times (Scope guard, Reference Materials, Next Best Skill) and the spike-to-owned handoffs repeat in step 6 and the reference list — minor padding that could be trimmed, sitting above the score-3 'mostly efficient' anchor.	4 / 5
Actionability	Concrete, executable guidance for an instruction-only skill — exact paths ('memory/launch/momentum-planner/YYYY-MM-DD-<launch-slug>-momentum-plan.md'), 'operation: propose' requests to 'registry-events.py', and a tier routing rule — but the Quick Start blocks use placeholder templates ('[launch]', '[traffic/signups]') rather than worked examples, leaving a minor gap below the score-5 anchor.	4 / 5
Workflow Clarity	Nine well-sequenced steps with explicit checkpoints — 'If state is absent, ask rather than assuming', NEEDS_INPUT on missing calendar records, agree-the-tier-with-user, ask-before-write, and a 'Done when' checklist — but there is no explicit handling for a rejected or failed proposal to registry-events.py, the minor validation gap that keeps it at 4 rather than 5.	4 / 5
Progressive Disclosure	Well-organized into clear sections with a Reference Materials list that signals each one-level-deep sibling-skill path and its purpose, and easy navigation; the gap keeping it below 5 is that some inline detail (tier routing rule, relaunch legitimacy criteria) could live in a local reference and the skill ships no bundle files of its own.	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.

A strong, third-person description that explicitly covers what it produces, when to invoke it via natural quoted triggers, and where its boundaries sit against sibling skills. The only weakness is the trailing multilingual tag blob, which reads as jargon rather than natural user speech.

Suggestions

Replace the trailing '抗第二周断崖/changelog-as-GTM/relaunch/下一发布时刻' tag blob with one or two natural English trigger phrases (e.g. 'post-launch momentum', 'week-2 drop') so every term is something a user would actually say.

Add 'release notes' as a standalone trigger variant alongside 'changelog / release-notes cadence' to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete outputs — 'a launch-moment calendar (milestone / shipped-loop / badge moments only), announcement-tier routing (major = full-channel, medium = targeted, minor = changelog-only), a relaunch legitimacy call, spike-to-owned handoff briefs, and the next Tier-1 moment' — giving comprehensive coverage of concrete actions, matching the score-5 anchor rather than the 4 (which expects minor gaps).	5 / 5
Completeness	Explicitly answers both what ('produces a T+1→T+30 momentum plan' with named components) and when ('Use when the user asks to...') with concrete trigger phrases, matching the score-5 anchor exactly and not the 4 where 'when' is only implicit.	5 / 5
Trigger Term Quality	Three natural quoted triggers — "keep the launch momentum going after launch week", "plan a changelog / release-notes cadence as GTM", "is this update worth a relaunch" — give good keyword coverage, but the trailing mixed-language tag blob '抗第二周断崖/changelog-as-GTM/relaunch/下一发布时刻' is jargon rather than user speech and a few common English variants are absent, so it sits just below the comprehensive-coverage anchor.	4 / 5
Distinctiveness Conflict Risk	Clear niche (post-launch momentum scheduling) with explicit disambiguation — 'Not for the 30-day content-reuse map or paid amplification execution — use content-amplifier; not for planning the next launch end to end — use launch-tier-planner' — yielding minimal conflict risk, matching the score-5 anchor.	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: 2 missing, 2 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: launch/prove/momentum-planner/SKILL.md
Commit: 64562bc

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.