CtrlK
BlogDocsLog inGet started
Tessl Logo

verification-loop

为 Claude Code 会话提供的全面验证系统。

45

Quality

47%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/verification-loop/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

The body is a concise, highly actionable multi-stage verification workflow with executable commands and a useful report template. Its main weakness is uneven validation feedback loops across the later stages.

Suggestions

Add explicit validate->fix->retry checkpoints to the lint, security, and diff-review stages so every stage has a clear pass/fail decision gate.

Clarify the coverage threshold enforcement (e.g. 'fail the stage if coverage < 80%') so the test stage has a concrete go/no-go rule.

Specify what 'critical' type errors vs warnings mean for the type-check stage's stop/continue decision.

DimensionReasoningScore

Conciseness

The body is lean and command-focused, with no padding or explanation of concepts Claude already knows; every section earns its place with concrete shell commands, matching the lean-and-efficient anchor.

3 / 3

Actionability

Each stage provides concrete, executable commands with language-specific variants (npm/pnpm, tsc/pyright, ruff) and a copy-paste-ready report template, matching the fully-executable anchor.

3 / 3

Workflow Clarity

A clear 6-stage sequence with an explicit stop-and-fix checkpoint after the build stage exists, but later stages (lint, security scan, diff review) lack explicit validate->fix->retry feedback loops, matching the 'sequence present but checkpoints missing or implicit' level 2 rather than the consistent-checkpoint level 3.

2 / 3

Progressive Disclosure

Content is well-organized into clearly labeled sections (six numbered stages, output format, continuous mode, hooks integration) within a single appropriately-scoped file with no deep or nested references, matching the clear-overview anchor.

3 / 3

Total

11

/

12

Passed

Description

7%

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 too vague to effectively route users to this skill: it states a broad domain without concrete actions, trigger terms, or a 'Use when...' clause. It would likely be missed or confused with general QA tooling.

Suggestions

Add concrete actions, e.g. 'Runs builds, type-checks, lint, tests, secret scans, and diff review before submitting a PR.'

Append an explicit 'Use when...' trigger clause: 'Use when finishing a feature, before creating a PR, after refactoring, or when you need to pass quality gates.'

Include natural trigger terms users would say (PR, quality gate, build fails, coverage, type errors) to improve discovery.

DimensionReasoningScore

Specificity

The description only offers '全方位验证系统' (comprehensive verification system), naming a domain but no concrete actions such as running builds, type-checks, or tests; matches the vague-anchor level rather than level 2 which requires naming some actions.

1 / 3

Completeness

It weakly states 'what' (a verification system) and entirely lacks any 'when to use' / 'Use when...' trigger clause; both halves are weak or missing, matching the score-1 anchor rather than the 'what present, when implied' level 2.

1 / 3

Trigger Term Quality

No natural trigger terms a user would say (e.g. 'before a PR', 'quality gate', 'build is failing') appear; the phrasing is generic technical jargon with no common variations, matching the score-1 anchor.

1 / 3

Distinctiveness Conflict Risk

'Claude Code 会话的全方位验证系统' ties it to Claude Code sessions, giving it a partial niche, but 'comprehensive verification system' is generic enough to overlap with other QA/review skills, matching the score-2 'somewhat specific but could overlap' anchor rather than a clearly distinct niche.

2 / 3

Total

5

/

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
xu-xiang/everything-claude-code-zh
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.