skill-lifecycle

The authoritative skill lifecycle state model including container states, version states, review workflow states, visibility overlay, and governance actions. Ensures agents don't introduce invalid states or transitions.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/skill-lifecycle/SKILL.md

Quality

Content

83%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.

This is a high-quality, token-efficient reference skill: dense tables of non-obvious domain facts with explicit code anchors, design-vs-code divergences, and pitfalls. The main gaps are the absence of validation/verification checkpoints around the destructive operations it documents and a monolithic single-file structure that could use light progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is dense, table-driven reference material with zero padding — no explanations of concepts Claude already knows, no introductory prose, every row carries non-obvious domain facts ('Sort by publishedAt DESC, then createdAt DESC, then id DESC'). Matches the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	Guidance is fully concrete for an instruction/reference skill: exact enum values, Java class paths, service method names, and precise rules ('Can only point to a PUBLISHED version', 'Deletes associated storage keys (individual files + bundle.zip)'). An agent can apply this directly when writing transitions, equivalent to copy-paste-ready guidance.	5 / 5
Workflow Clarity	Transitions are tabulated with sources and constraints, but the skill covers destructive operations (delete version, yank) without any validation or verification steps — no 'check current state before deleting' or post-action verification guidance. Per the rubric guideline, destructive/batch operations without validation cap workflow clarity at 3. It is not 2 because sequences and constraints are in fact clearly specified.	3 / 5
Progressive Disclosure	The body is well-organized with clearly headed sections covering distinct concerns (states, transitions, permissions, events, pitfalls), and no bundle files exist so there are no broken or nested references. It is not 5 because the ~150-line monolithic reference could split some detail (e.g., per-service transition tables or projection model details) into one-level-deep reference files to keep SKILL.md a leaner overview.	4 / 5
	Total	17 / 20 Passed

Description

58%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 and appropriately third-person, with a clear articulation of what the skill covers, but it lacks any 'use when' trigger guidance and natural trigger terms users would say. Adding explicit trigger phrases would lift completeness and trigger-term quality substantially.

Suggestions

Append a trigger clause, e.g.: 'Use when modifying skill publish, review, or unpublish flows, changing skill/version status fields, implementing governance actions (hide, yank, archive), or adding state transitions.'

Include natural trigger keywords users would say — 'publish', 'yank', 'hide', 'archive', 'skill status', 'version status' — in the description.

State the concrete outcome in third person, e.g. 'Validates state transitions and recalculation of the latest published version pointer when publishing, yanking, or deleting versions.'

Dimension	Reasoning	Score
Specificity	The description enumerates several concrete components — 'container states, version states, review workflow states, visibility overlay, and governance actions' — and states a concrete purpose ('Ensures agents don't introduce invalid states or transitions'), matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because it names the model's contents rather than the concrete actions an agent will take with them.	4 / 5
Completeness	The 'what' is clear ('The authoritative skill lifecycle state model including...'), but there is no 'when' — no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. It is not 2 because the 'what' is explicit and detailed, not vague.	3 / 5
Trigger Term Quality	Relevant domain keywords like 'lifecycle', 'states', 'review', and 'governance actions' are present, matching the 'some relevant keywords but missing common variations' anchor. Common natural terms users would say — 'publish', 'yank', 'hide', 'skill status', 'version status' — are absent, and no 'Use when...' phrasing surfaces triggers.	3 / 5
Distinctiveness Conflict Risk	The niche is clear and specific (skill lifecycle states and transitions within a skill marketplace codebase), so it is 'mostly distinct; minor overlap risk' with closely related skills such as a general skill-publishing or review-workflow skill. It is not 5 because terms like 'review workflow' and 'governance' could plausibly overlap with those adjacent skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: iflytek/skillhub
Path: .agents/skills/skill-lifecycle/SKILL.md
Commit: 7352597

Reviewed: 10 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.