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)。

67

Quality

81%

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

75%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 highly actionable, well-organized SOP skill with concrete templates and a clear workflow. It could be tightened by removing redundant identity-constraint restatements and ensuring referenced shared files exist.

Suggestions

Remove the redundant '和正式 Review 的关系' table content that re-explains identity constraints already stated in 身份约束, or fold it into that section to reduce token cost.

Trim repeated '认知负荷' rationale statements in the trigger decision table to a single mention.

Verify that referenced external paths (sop-definitions/development.yaml, ../.cat-cafe-shared-refs/review-request-template.md) resolve, or note they are expected to live outside this skill bundle.

DimensionReasoningScore

Conciseness

Mostly efficient but includes redundancy: the '认知负荷' rationale repeats across the decision table, and the '和正式 Review 的关系' table re-explains identity constraints already covered in 身份约束.

3 / 5

Actionability

Fully executable: concrete git commands, a copy-paste finding-list markdown template with real example rows, category enums, severity rules, and a trigger message template.

5 / 5

Workflow Clarity

Clear multi-step sequence (前置条件 → 触发 → agent 工作 → author 处理) with the simple-skill exception applying since this advisory finding-generator involves no destructive or batch operations requiring validation checkpoints.

4 / 5

Progressive Disclosure

Well-sectioned single-file body with signaled one-level references to shared SOP and template files; minor gap is that referenced bundle files are not actually present in the skill bundle.

4 / 5

Total

16

/

20

Passed

Description

87%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 well-scoped description that clearly separates this finding-generator role from formal review authority and provides explicit what/when guidance. Minor improvements in trigger-term synonym coverage would round it out.

DimensionReasoningScore

Specificity

Names the domain (fresh-context scan of PR diff) and concrete actions (scan diff, produce finding list), with minor gaps such as not enumerating the scan categories.

4 / 5

Completeness

Explicitly answers both 'what' (scan PR diff, output finding list) and 'when' via concrete 'Use when'/'Not for' clauses with trigger phrases.

5 / 5

Trigger Term Quality

Includes natural trigger phrases ('fresh context', 'pre-review scan', '找新眼看看') users would say, but mixes languages and misses some common synonyms.

4 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche (finding generator, not approval authority) that distinguishes it from formal review skills with minimal conflict risk.

5 / 5

Total

18

/

20

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.