CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

inkos-continuation-writing

从导入正文重建正典与运行时状态,并在原续写或系列新作边界内继续创作。

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/core/skills/inkos-continuation-writing/SKILL.md
SKILL.md
Quality
Evals
Security

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 tight, token-efficient instruction skill that gives concrete directives for both continuation and series modes with an explicit evidence-handling policy. Its only real weakness is that the workflow order is implicit rather than sequenced, and the referenced "style profile" concept is undefined.

DimensionReasoningScore

Conciseness

Five lean bullets with zero padding, no explanations of concepts Claude already knows, and every token carrying a distinct operational instruction — a clear match for the "lean and efficient" anchor.

5 / 5

Actionability

The guidance is mostly executable for an instruction-only skill, with a concrete enumerated reconstruction checklist ("facts, character knowledge, relationships, unresolved promises, chronology, location, voice, and the exact continuation point") and explicit mode rules; the minor gap is that an "operational style profile" is invoked but never defined. Not 3 because the directives are specific and directly actionable rather than pseudocode-like or missing key details.

4 / 5

Workflow Clarity

The bullets imply a sequence (reconstruct state, then apply mode-specific rules, then generate complications) but the order is implicit, unnumbered, and without checkpoints — fitting the "steps listed but checkpoints missing or implicit" anchor. It is a non-destructive creative skill, so the validation cap does not apply, but it also does not qualify for the simple-skill 5 since the two-mode process is not presented as an unambiguous single action.

3 / 5

Progressive Disclosure

The skill is under 50 lines, fully self-contained with no external files needed (no references/, scripts/, or assets/ exist and the body cites none), and the bullets are well organized under a single heading — the simple-skill exception for progressive disclosure applies.

5 / 5

Total

17

/

20

Passed

Description

53%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 clearly communicates what the skill does in a distinct niche, but it omits any "when to use" trigger guidance and lacks natural trigger-term coverage. Adding an explicit use-when clause with the phrases users would naturally say would lift the two weakest dimensions.

Suggestions

Add an explicit "Use when..." clause (e.g., when the user imports an existing story and asks to continue it, write the next chapter, or start a new entry in a series).

Include natural trigger terms and synonyms users would say, such as 续写/接着写/下一章/系列新作, alongside the current domain vocabulary.

Briefly enumerate the concrete reconstruction outputs (facts, character knowledge, relationships, promises, chronology, voice) to raise specificity from 1-2 actions to several specific actions.

DimensionReasoningScore

Specificity

Names the domain (fiction continuation) and 1-2 concrete actions — "重建正典与运行时状态" (reconstruct canon and runtime state) and "继续创作" (continue writing) — but does not enumerate several specific operations as the level-4 anchor requires; it is more concrete than the minimal/generic level-2 anchor.

3 / 5

Completeness

The "what" is clearly stated (reconstruct state from imported text and continue writing within continuation/series boundaries), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the "what" is clear rather than vague.

3 / 5

Trigger Term Quality

Relevant natural keywords are present ("续写" continuation, "系列新作" series new work, "正典" canon, "导入正文" imported text), but common variations and synonyms users might say are missing, matching the "some relevant keywords" anchor rather than the good-coverage anchor.

3 / 5

Distinctiveness Conflict Risk

The canon-continuation vs. series-new-entry distinction carves out a fairly distinct niche with only minor overlap risk against generic creative-writing skills; not 5 because no explicit trigger phrases fully disambiguate it from those adjacent skills.

4 / 5

Total

13

/

20

Passed

Validation

100%

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-continuation-writing/SKILL.md

Reviewed

Table of Contents

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.