CtrlK
BlogDocsLog inGet started
Tessl Logo

inkos-short-story-analysis

商业短篇拆稿、情绪链、证据链和反转机制分析。Use to deconstruct a short story into transferable craft.

61

Quality

71%

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-short-story-analysis/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 lean, well-disclosed analysis skill: concise overview in the body with a verified one-level reference, concrete tooling and dimensions, but the workflow is an unnumbered bullet list without explicit checkpoints.

Suggestions

Convert the bullet list into a numbered workflow with explicit checkpoints (e.g., 1. Read fully → 2. Ingest with `ingest_material` → 3. Run each template dimension → 4. Cross-check each conclusion against quoted evidence → 5. Respond in the user's language).

Add a brief validation step such as confirming every claimed mechanism cites a story excerpt, so the analysis has an explicit feedback loop rather than an implicit one.

Optionally inline a one-line example of the expected output shape next to the template reference so the body alone is enough to start.

DimensionReasoningScore

Conciseness

The body is a short bullet list with zero padding — it assumes Claude's competence ("Read the whole supplied story", "Extract methods rather than replacement prose") and every line earns its place.

5 / 5

Actionability

Concrete guidance is present — a named tool (`ingest_material`), an explicit list of analysis dimensions, and a reference template to load — but the body delegates the actual per-dimension method to the template rather than giving copy-ready steps, leaving a minor gap.

4 / 5

Workflow Clarity

A rough sequence is implied by the bullets (read → ingest → analyze → extract → respond), but they are unnumbered with no explicit checkpoints or validation feedback loop, so the sequence is present yet checkpoints are only implicit.

3 / 5

Progressive Disclosure

The body is a concise overview that signals a single one-level-deep reference ("Load `references/deconstruction-template.md`"), and that file exists in the bundle, giving clear navigation and an appropriate content split.

5 / 5

Total

17

/

20

Passed

Description

62%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 bilingual, domain-specific description with a clear niche and several concrete actions, but its trigger guidance is implicit ("Use to…") rather than an explicit "Use when…" condition and it lacks common natural synonyms.

Suggestions

Replace "Use to deconstruct a short story…" with an explicit "Use when…" clause listing natural user phrases, e.g. "Use when the user supplies a short story and asks why it works, how it is structured, or what can be learned from it."

Add natural synonyms and English equivalents of the Chinese jargon ("analyze", "break down", "emotional arc", "evidence chain", "reversal/twist") so trigger terms match what users actually say.

Keep the bilingual phrasing but lead with the trigger condition so the "when" is as prominent as the "what".

DimensionReasoningScore

Specificity

Lists several concrete actions — "拆稿", "情绪链", "证据链", "反转机制分析", "deconstruct a short story into transferable craft" — naming the domain with multiple specific operations, though the repeated "分析" keeps it just short of comprehensive.

4 / 5

Completeness

The "what" is clear (deconstruct stories into transferable craft via the named chains), but the trigger is only weakly implied by "Use to…" rather than an explicit "Use when…" clause, so per the rubric cap completeness stays at 3.

3 / 5

Trigger Term Quality

Contains relevant terms ("short story", "deconstruct", "transferable craft") plus bilingual craft jargon, but misses common natural variations users would say such as "analyze", "break down", "why it works", or "how it's structured".

3 / 5

Distinctiveness Conflict Risk

It carves a clear niche — short-story deconstruction and craft extraction — with distinct triggers and minimal overlap risk against other skills.

5 / 5

Total

15

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Narcooo/inkos
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.