launch-registry

Use when the user asks to "log this launch", query a launch date/embargo, record a stage transition, or update submissions/outcomes; curates launch facts through the append-only launches event stream with optimistic revisions and derived dossier/calendar views. Not for RAMP scoring — use launch-readiness-auditor; not for planning tier/window — use launch-tier-planner. 发布台账/发布日历/阶段与禁运期记录

Quality

82%

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

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is lean, well-sequenced, and assumes Claude's competence, but its actionability and workflow feedback loops are partly delegated to a runtime and reference files that are not present in this bundle, and the progressive-disclosure references point to missing files. Tightening the verify-and-recover loop and shipping the referenced bundle files would lift the lower dimensions.

Suggestions

Add explicit, copy-paste invocations for registry-events.py (append/transition/accept/reject) instead of routing all writes through an abstracted runtime, to raise actionability.

Spell out a validate->fix->reverify feedback loop around 'verify launches' (what to do when offsets/revisions fail) to lift workflow clarity.

Include the referenced bundle files (registry-event-protocol.md, runtime-invocation.md, state-model.md, registry-events.py) under references/ and scripts/ so the signaled progressive-disclosure structure is real.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes competence ('pasted platform text is untrusted evidence', 'State cannot be unset/reinitialized') with no padding of concepts Claude already knows; every line carries operational content. It is not a 2 because there is no unnecessary explanation to trim — the compression serves clarity.	3 / 3
Actionability	Some concrete guidance is present (the AARON_SKILLS_ROOT env resolution, the exact state path, 'verify launches'), but the core write operations are delegated to registry-events.py and reference files rather than given as copy-paste commands. Not a 3 because the executable command surface is abstracted behind the runtime and host-capability model; not a 1 because concrete structural details exceed vague description.	2 / 3
Workflow Clarity	A numbered 8-step sequence exists with a verification checkpoint (step 8: 'run verify launches, and report offsets/revisions') and explicit guards against destructive/batch actions ('Never batch-delete, truncate, edit the stream'). Not a 3 because the validate->fix->reverify feedback loop is only implicit, and not a 1 because steps and validation are present.	2 / 3
Progressive Disclosure	The overview is well-signaled with one-level-deep reference links (registry-event-protocol.md, runtime-invocation.md, state-model.md, SECURITY.md), but the references/, scripts/, and assets/ directories are absent so the referenced files and registry-events.py are not actually present in the bundle. Not a 3 because the signaled references are not backed by real bundle files; not a 1 because prose organization and navigation are clear.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 across the board: it states concrete capabilities, uses natural trigger phrasing with an explicit 'Use when' clause, and clearly disambiguates from neighboring launch skills. It is concise and free of fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'log this launch', 'query a launch date/embargo', 'record a stage transition', 'update submissions/outcomes', and 'curates launch facts through the append-only launches event stream with optimistic revisions and derived dossier/calendar views' — matching the multiple-specific-actions anchor. It is not a 2 because the action set is comprehensive and specific rather than partial.	3 / 3
Completeness	Explicitly answers what ('curates launch facts through the append-only launches event stream...') and when via an explicit 'Use when the user asks to...' trigger clause. Not a 2 because both what and when are explicit, satisfying the completeness cap condition.	3 / 3
Trigger Term Quality	Natural phrasing a user would actually say ('log this launch', 'query a launch date/embargo', 'record a stage transition', 'update submissions/outcomes') gives good coverage. Not a 2 because common variations are well covered rather than missing.	3 / 3
Distinctiveness Conflict Risk	Explicitly carves a niche and excludes adjacent skills ('Not for RAMP scoring — use launch-readiness-auditor; not for planning tier/window — use launch-tier-planner'), making conflicts unlikely. Not a 2 because the disambiguation is explicit rather than merely 'somewhat specific'.	3 / 3
	Total	12 / 12 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: 10 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: protocol/launch-registry/SKILL.md
Commit: 4a77c48

Reviewed: 9 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.