CtrlK
BlogDocsLog inGet started
Tessl Logo

deprecate-workflow-node

当用户需要弃用一个工作流节点(保留向后兼容、隐藏出模板面板)时触发该 skill。FastGPT 工作流节点的弃用流程标准化封装,覆盖模板、Dispatcher、UI 引用等所有需要改动的位置。

68

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

77%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.

A highly actionable, well-sequenced skill body with strong validation checkpoints and concrete code for a genuinely complex migration. The main gaps are mild redundancy between the TODO template and detailed steps, and a monolithic single-file structure with no progressive disclosure into supporting files.

Suggestions

De-duplicate the 8 steps: either let the TODO 模板 reference the 详细步骤 section by anchor instead of restating each step, or merge the template into the detailed steps as per-step checkboxes.

Consider extracting the long status-badge table / field-vs-node deprecation rationale into a reference file (e.g. references/deprecation-mechanisms.md) and linking it one level deep, to slim the SKILL.md overview and add genuine progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly efficient and information-dense — concrete paths, grep commands, and before/after code that earn their tokens — but the "TODO 模板" and "详细步骤" sections restate the same 8 steps, and the "核心理念" table duplicates guidance later expanded inline. It could be tightened without losing clarity, matching 'mostly efficient but could be tightened'.

2 / 3

Actionability

Fully executable guidance throughout: exact grep commands, precise source/destination paths, `git mv` instructions, before/after TS diffs, and copy-pasteable status-badge code — matching the 'fully executable, copy-paste ready' anchor.

3 / 3

Workflow Clarity

An explicit 8-step sequence with a numbered TODO template, a dedicated validation step (lint + typecheck + local tests), a post-completion 验证清单 with checkboxes, and a 反模式 list of failure modes — clear sequence with explicit validation steps and feedback loops, which is exactly what this destructive file-moving operation requires.

3 / 3

Progressive Disclosure

Well-organized single file with clear sections and an overview→detail progression (TODO 模板 → 详细步骤), but no content is split into separate bundle files and no references are signaled — matching 'some structure but content that could be separate is inline'. No bundle files exist in references/scripts/assets.

2 / 3

Total

10

/

12

Passed

Description

85%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.

A strong description that clearly states the niche, the concrete touchpoints it covers, and an explicit trigger condition. Its only weakness is trigger-term breadth: it relies on the single word "弃用" rather than enumerating the natural variations users might say.

Suggestions

Broaden trigger terms in the description to include common variations users say, e.g. "弃用 / 废弃 / 下线 / 不再推荐使用 FastGPT 工作流节点", to match the trigger terms already listed in the body.

Soften the over-claim "覆盖…所有需要改动的位置" to a concrete scope statement (e.g. "覆盖模板、Dispatcher、UI 引用三处改动") to avoid vague padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and coverage areas — "弃用一个工作流节点", "保留向后兼容", "隐藏出模板面板", and named touchpoints "模板、Dispatcher、UI 引用" — matching the multiple-specific-actions anchor. The closing "覆盖…所有需要改动的位置" is mildly over-claiming but does not erase the concrete actions listed.

3 / 3

Completeness

Explicitly answers both: what ("FastGPT 工作流节点的弃用流程标准化封装,覆盖模板、Dispatcher、UI 引用") and when ("当用户需要弃用一个工作流节点…时触发该 skill"), an explicit trigger clause equivalent to 'Use when'.

3 / 3

Trigger Term Quality

The natural trigger term "弃用" is present and domain-appropriate, but only one variation appears in the description itself (the body adds 废弃/下线/不再推荐); this matches 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

Targets a narrow, well-defined niche — deprecating FastGPT workflow nodes — with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

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
labring/FastGPT
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.