inkos-long-market-research

长篇网文市场、榜单、平台趋势与对标研究。Use for evidence-based long-form fiction market research, not for ordinary drafting.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/core/skills/inkos-long-market-research/SKILL.md

Quality

Content

80%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 well-structured, token-efficient overview that delegates detail to one real, clearly signaled reference file. Its main weakness is workflow clarity: the body gives principles rather than an explicit sequenced workflow with checkpoints, leaving the actual process to the referenced rubric.

Suggestions

Add a short explicit sequence in the body (e.g. clarify scope → gather evidence via research_web/ingest_material → separate evidence from interpretation → deliver per the rubric) so the workflow is legible without loading the reference.

Include one inline mini-example of the evidence-vs-interpretation-vs-recommendation separation so the core actionability is concrete before the reference is loaded.

Dimension	Reasoning	Score
Conciseness	Lean bullet overview that assumes Claude's competence — no padding, no explanation of concepts Claude already knows, and every bullet earns its place, matching the 'lean and efficient' anchor.	5 / 5
Actionability	Concrete, executable guidance naming specific tools (`research_web`, `ingest_material`, `retrieve_material`, `manage_book_reference`, `use_skill`) with clear directives ('Separate observed evidence, interpretation, and creative recommendation'), but no inline examples of the expected output structure, which lives in the reference file.	4 / 5
Workflow Clarity	The body lists guiding principles rather than an explicitly sequenced workflow, and the actual deliverable sequence (the 6-step rubric) is delegated to the reference; no validation checkpoints are stated, fitting the 'sequence present but checkpoints implicit' anchor.	3 / 5
Progressive Disclosure	A concise overview body with a single, clearly signaled, one-level-deep reference ('load `references/research-rubric.md` with `use_skill` only when needed') that exists on disk, matching the 'clear overview with well-signaled one-level-deep references' anchor.	5 / 5
	Total	17 / 20 Passed

Description

75%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 solid bilingual description that states the domain and several specific research facets, includes an explicit 'Use for' trigger, and adds a negative boundary to reduce conflict. It stops short of the top anchor because the positive trigger is somewhat circular and lacks concrete situational trigger phrases.

Suggestions

Replace the self-referential trigger with concrete situational ones, e.g. 'Use when the user wants current market evidence, platform differences, comparable works, audience expectations, or topic selection for a long-form project.'

Add a couple of natural synonyms users actually say (e.g. '选题'/topic selection, '受众'/audience) to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete facets — '市场、榜单、平台趋势与对标研究' (market, rankings, platform trends, benchmark research) — but frames them as research topics rather than listing discrete concrete actions, leaving a minor gap versus the comprehensive-actions anchor.	4 / 5
Completeness	Both 'what' (market/rankings/platform/benchmark research) and 'when' ('Use for evidence-based long-form fiction market research, not for ordinary drafting') are present with a negative boundary, but the positive trigger is somewhat self-referential rather than naming concrete situational triggers, so it sits below the explicit-trigger anchor.	4 / 5
Trigger Term Quality	Good natural keyword coverage ('market research', 'rankings', 'platform trends', 'comparable/benchmark works', 'long-form fiction') in both languages, but a few common synonyms a user might say (e.g. '选题'/topic selection, '受众'/audience) appear only in the body, not the description.	4 / 5
Distinctiveness Conflict Risk	Clear niche (long-form fiction market research) with an explicit negative boundary ('not for ordinary drafting') that reduces conflict with drafting skills; only minor overlap risk remains with general research skills, fitting the 'mostly distinct' anchor.	4 / 5
	Total	16 / 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: Narcooo/inkos
Path: packages/core/skills/inkos-long-market-research/SKILL.md
Commit: 0910483

Reviewed: 1 day 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.