CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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)。

Quality

89%

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

88%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 well-crafted process skill: concrete templates, explicit decision tables, validation checkpoints, and a real feedback loop for false-positive findings. Its only notable issues are a fourfold repetition of the identity constraint and references to external files that are unverifiable from the bundle, one of which is self-referential.

DimensionReasoningScore

Conciseness

The body is dense and efficient — decision tables, templates, and checklists with no padding or explanation of concepts Claude already knows. The only redundancy is the 'finding generator, not approval authority' constraint repeated in four places (identity section, footer, comparison table, next-step note), which keeps it just below the lean anchor.

4 / 5

Actionability

Fully executable guidance throughout: a copy-paste trigger message template, the exact command `git diff origin/main...HEAD`, a complete Finding List markdown template with worked example rows, category and severity enums, and concrete triage actions ('fixed (commit {sha})' / 'dismissed: {理由}'). Nothing remains abstract.

5 / 5

Workflow Clarity

The sequence is explicit and numbered with a decision branch (need fresh-context → trigger method A/B; not need → request-review), the preconditions table has an '未满足时' column serving as explicit checkpoints, and the author's triage of potentially false-positive findings (review each → fix or dismiss with reason) is a genuine feedback loop.

5 / 5

Progressive Disclosure

Well-organized sections with clearly signaled one-level-deep external references (sop-definitions, review-request-template, sibling skills), and the ~170 inline lines are cohesive process content that reasonably belongs in SKILL.md. However, no bundle files exist, the referenced paths point outside the skill directory and cannot be verified, and one reference is circular ('格式见 cat-cafe-skills/fresh-context-review/SKILL.md' points back to this file).

4 / 5

Total

18

/

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 strong description that clearly and explicitly states what the skill does, when to use it, when not to use it, and what it outputs, with a distinct niche and explicit boundaries against formal review skills. Minor gaps: limited action coverage and a few missing natural trigger synonyms.

Suggestions

Add one or two more concrete action phrases (e.g. 'scans diff for correctness, spec-mismatch, missing tests') to lift specificity from a single named action to comprehensive coverage.

Add common trigger synonyms such as 'fresh eyes', 'second pair of eyes', or 'cold review' alongside 'fresh context' and 'pre-review scan' to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

Concrete and precise: 'Author-triggered fresh-context scan of PR diff before formal review', 'Finding generator, NOT approval authority', 'Output: Finding list(附在 review request 中)'. It stays at 4 rather than 5 because it names only one core action (scan diff → produce finding list) rather than a comprehensive list of specific actions.

4 / 5

Completeness

Explicitly answers what ('Finding generator, NOT approval authority. Output: Finding list'), when ('Use when: quality-gate 通过、PR 非 trivial...'), and even when-not ('Not for: 正式 review verdict、approval、merge decision') — both facets are concrete and trigger phrases are present.

5 / 5

Trigger Term Quality

'Use when: quality-gate 通过、PR 非 trivial、想降低正式 reviewer 认知负荷' plus the frontmatter triggers 'fresh context', 'pre-review scan', '找新眼看看' are natural phrases a user would say. Missing common synonyms like 'fresh eyes', 'second pair of eyes', or 'cold review', which keeps it below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers ('fresh context', 'pre-review scan') and an explicit exclusion clause ('Not for: 正式 review verdict、approval、merge decision') that fences it off from formal-review skills, minimizing 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.

Validation — 15 / 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

Path

cat-cafe-skills/fresh-context-review/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.