story-short-write

短篇网文写作。辅助短篇小说创作，从构思到成稿，聚焦情绪拉扯与节奏把控。触发方式：/story-short-write、/写短篇、「帮我写一篇短篇」「写个盐言故事」。

Quality

76%

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 ./skills/story-short-write/SKILL.md

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 delivers an executable, well-gated multi-phase workflow with strong validation feedback loops and a well-organized reference layer. Its weakest dimension is conciseness: the file is long with redundant restatements and inlined detail that could live in references.

Suggestions

Consolidate the repeated Reference Gate / 先读后写 instructions into a single canonical block and have each phase link to it, cutting redundant restatements to improve conciseness.

Move the large agent-spawn prompt templates (story-architect, character-designer, narrative-writer, consistency-checker) into a dedicated references/agents.md file and reference it by path, reducing inlined bulk.

Trim the cross-cutting topic table or move it to references/topic-index.md since the main reference table already covers most of the same pointers, keeping SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids explaining basic concepts, but it is long (≈450 lines) with several padded sections (repeated Reference Gate instructions, multiple parallel agent spawn templates, redundant restatements of rules) that could be tightened or pushed to references; fits 'mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	Provides concrete executable guidance throughout — explicit node script commands with flags (e.g. 'node scripts/check-phase2-contract.js --json {短篇目录}'), filled template blocks, and exact field schemas — with only minor gaps where a step defers to a reference file; fits 'mostly executable guidance with minor gaps'.	4 / 5
Workflow Clarity	Phases 1–4 are clearly sequenced with explicit validation checkpoints and feedback loops (Phase 2 exit-code gating with 2-round repair, Phase 3 完成门槛 checklist, Phase 4 delivery-contract verifier with retry), matching the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	5 / 5
Progressive Disclosure	SKILL.md functions as an overview with many one-level-deep, clearly-signaled references (references/*.md, genre-styles/) and a helpful cross-cutting topic table; it falls short of 5 because substantial procedural detail (phase logic, agent spawn templates) is inlined rather than offloaded to a reference, leaving some organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

78%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 well-formed in third person, gives clear what-and-when guidance with multiple concrete trigger phrases, and carves out a fairly distinct niche. Its main weakness is specificity: it states one composite capability (从构思到成稿) rather than enumerating discrete concrete actions.

Suggestions

List 2-3 discrete concrete actions the skill performs (e.g., '确定情绪目标、搭建核心框架与反转、逐场景写作、精修去AI味') instead of the single composite phrase '从构思到成稿' to lift specificity.

Add a natural English/extension synonym or two (e.g., 'short story', '网文短篇') only if the user base is bilingual, to round out trigger-term coverage toward 5.

Clarify the boundary against sibling skills (e.g., '写完整成稿，不同于 story-short-analyze 的拆解') to reduce overlap risk with the suite's other writing skills.

Dimension	Reasoning	Score
Specificity	Names the domain (短篇小说创作) and one concrete action (从构思到成稿), plus a thematic focus (情绪拉扯与节奏把控), but stays at a high level without enumerating multiple discrete capabilities; fits the 'names domain and 1-2 concrete actions, but not comprehensive' anchor.	3 / 5
Completeness	Explicitly answers both what ('辅助短篇小说创作，从构思到成稿，聚焦情绪拉扯与节奏把控') and when via a concrete '触发方式' clause with multiple trigger phrases, matching the 'clearly and explicitly answers both what AND when with concrete trigger phrases' anchor.	5 / 5
Trigger Term Quality	Lists several natural user-facing triggers ('帮我写一篇短篇', '写个盐言故事', '/写短篇') that a user might genuinely say; falls short of 5 only because it is not exhaustive of synonyms, but covers multiple natural phrases well above the midpoint.	4 / 5
Distinctiveness Conflict Risk	The 短篇网文/盐言/七猫 niche with its specific trigger phrases is mostly distinct from general writing skills, with only minor overlap risk with sibling skills like story-long-write or story-short-analyze; not a 5 because related writing skills in the same suite could overlap.	4 / 5
	Total	16 / 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_version	'metadata.version' is missing	Warning
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

	Total	13 / 16 Passed

Repository: worldwonderer/oh-story-claudecode
Path: skills/story-short-write/SKILL.md
Commit: 5de060f

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.