CtrlK
BlogDocsLog inGet started
Tessl Logo

fresh-context-review

Author-triggered fresh-context scan of PR diff before formal review. Finding generator, NOT approval authority. Use when: quality-gate 通过、PR 非 trivial、想降低正式 reviewer 认知负荷。 Not for: 正式 review verdict、approval、merge decision。 Output: Finding list(附在 review request 中)。

74

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete templates and a clearly sequenced, checkpointed workflow, and it is well-organized with clearly signaled one-level references. Its main weakness is conciseness: the core non-goal and the 盲点正交性 rationale are reiterated more than strictly necessary.

Suggestions

Consolidate the "finding generator, not approval authority" non-goal: state it authoritatively once in 身份约束 and reference it (rather than re-explaining) in the Finding List footer, 和正式 Review table, and Common Mistakes.

Explain 盲点正交性 once in its dedicated section and have the 方式 A / 方式 B notes reference it instead of re-deriving the rationale each time.

Consider extracting the Finding List template + Category/Severity rules into a reference file if the skill grows, to keep the main body scannable.

DimensionReasoningScore

Conciseness

The body is dense and table-driven, but the "finding generator, not approval authority" non-goal is repeated across the 身份约束 section, Finding List footer, 和正式 Review table, and Common Mistakes, and 盲点正交性 is re-explained in several places — mostly efficient but could be tightened. Not a 3 because the redundancy is not load-bearing in every occurrence; not a 1 because there is no padding about concepts Claude already knows.

2 / 3

Actionability

Provides copy-paste-ready guidance: the 方式 A @-message template, the markdown Finding List template, the Category enum, Severity rules, and `fixed (commit {sha})` / `dismissed: {理由}` annotations are concrete and executable.

3 / 3

Workflow Clarity

Clear sequencing with a preconditions checklist (前條件 table), numbered Ownership/Agent/Author steps, and a fix-or-dismiss feedback loop including a 假阳性 review checkpoint. Not below 2 because checkpoints are explicit rather than implicit.

3 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets absent), but the single document is well-organized into clear sections and its references to sibling skills (receive-review, refs/review-request-template.md, sop-definitions/development.yaml) are one level deep and clearly signaled. Not below 2 because navigation is easy and references are not deeply nested.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 concrete, third-person, and explicitly covers both what the skill does and when to use it, with a clear Not-for clause that separates it from formal review skills. It is a strong, well-scoped skill description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "fresh-context scan of PR diff", "Finding generator", and "Output: Finding list(附在 review request 中)" — rather than vague language, matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers what ("Author-triggered fresh-context scan…Finding generator, NOT approval authority") and when ("Use when: quality-gate 通过、PR 非 trivial…"), plus a "Not for" scope clause. Not below 2 because both what and when are explicitly stated.

3 / 3

Trigger Term Quality

Contains natural terms a user would say ("fresh-context", "pre-review") plus an explicit "Use when:" clause; not merely technical jargon. It is not below 3 because coverage of natural trigger phrasing is good, and not above because 3 is the scale max.

3 / 3

Distinctiveness Conflict Risk

A sharp niche (pre-review finding generator) with an explicit "Not for: 正式 review verdict、approval、merge decision" clause distinguishing it from formal review skills, so conflict risk is low.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
zts212653/clowder-ai
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.