CtrlK
BlogDocsLog inGet started
Tessl Logo

inkos-story-review

按题材、目标读者和用户标准审稿,展示具体问题并协作修订。Use for chapter or manuscript review with transparent criteria.

65

Quality

78%

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-story-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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.

An efficiently written, well-structured instruction skill with exemplary progressive disclosure and a strong revision-gating guardrail. Its main weakness is that two key terms ('auditor' and 'confirmed workflow') are referenced but never defined and have no corresponding bundle files, leaving the workflow partially non-executable.

Suggestions

Define or remove 'the auditor': either add the auditor script/tool to scripts/ and link it, or replace the term with a concrete instruction (e.g., 're-read persisted chapters and flag issues').

Clarify 'confirmed workflow': name the specific workflow or state its conditions concretely so the revision-authorization checkpoint is executable.

Make the review sequence explicit (e.g., a short numbered list: identify standard → audit persisted chapters → report issues with severity/evidence/impact → revise only when authorized → report application) so validation checkpoints are visible rather than implied.

DimensionReasoningScore

Conciseness

The body is lean with no padding and no explanation of concepts Claude already knows — every bullet adds non-obvious guidance (standard selection, failure semantics, revision gating, voice preservation), matching 'lean and efficient; every token earns its place'.

5 / 5

Actionability

Concrete factors (genre/audience/tone/platform) and concrete reporting fields (severity/evidence/impact) are present, but the directive to 'use the auditor for persisted chapters' references tooling absent from the bundle and 'confirmed workflow' is undefined, leaving key execution details missing — fitting 'some concrete guidance but incomplete; missing key details'.

3 / 5

Workflow Clarity

A logical review-then-gated-revision sequence with explicit guards ('do not revise merely because an audit failed', 'report whether the revised artifact was actually applied') exists, but the checkpoints depend on an undefined 'auditor' and 'confirmed workflow', so validation steps cannot be fully executed — matching 'steps present but checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

A short overview points to exactly one clearly-signaled, one-level-deep reference ('Load references/review-matrix.md ...') that exists in the bundle, with detailed criteria appropriately split out — matching 'clear overview with well-signaled one-level-deep references'.

5 / 5

Total

16

/

20

Passed

Description

83%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 concise, bilingual description that pairs a clear capability statement with an explicit 'Use for...' trigger, satisfying both the what and when requirements. It is specific and distinct, though it could broaden trigger synonyms and surface more of the diagnosis/scoring/comparison verbs the body advertises.

DimensionReasoningScore

Specificity

Names the domain plus several concrete actions — '审稿' (review), '展示具体问题' (surface specific issues), '协作修订' (collaborate on revisions) against genre/audience/standards — matching the 'several specific actions; minor gaps' anchor; not 5 because the description omits scoring/comparison/approval that the body names.

4 / 5

Completeness

Explicitly answers both what (review/surface/collaborate by criteria) and when ('Use for chapter or manuscript review with transparent criteria'), mirroring the level-5 anchor's what+when pattern exactly; not below since neither half is vague.

5 / 5

Trigger Term Quality

Includes natural user-facing terms ('chapter', 'manuscript review', '审稿') plus 'transparent criteria', but misses common synonyms like story/novel/fiction/prose, fitting 'good keyword coverage; a few natural terms missing'.

4 / 5

Distinctiveness Conflict Risk

'chapter or manuscript review with transparent criteria' carves a fairly distinct niche with minimal conflict risk, but retains minor overlap with general writing/editing skills, matching 'mostly distinct; minor overlap risk'.

4 / 5

Total

17

/

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.