CtrlK
BlogDocsLog inGet started
Tessl Logo

workflow-runner

在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key,使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。

63

Quality

76%

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 ./skills/workflow-runner/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 a clear, validated multi-step workflow and good error handling. Its main weaknesses are mild redundancy in the HARD-GATE section and a monolithic single-file structure with no progressive disclosure to reference materials.

Suggestions

Remove the HARD-GATE block or collapse it into a short checklist, since each rule is already enforced in the corresponding step.

Move the YAML field schema and metadata.json format into a references/ file (e.g. WORKFLOW-SCHEMA.md) and link to it from the overview to improve progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly efficient operational prose, but the HARD-GATE block restates rules already embedded in the steps and a few imperative reminders ('不要跳步') are redundant, so it could be tightened.

2 / 3

Actionability

Provides concrete, executable guidance throughout: exact Read/Bash/Write/Agent tool usage, an ordered directory-check sequence, copy-paste install commands, and exact output file/JSON structures.

3 / 3

Workflow Clarity

A clearly sequenced 5-step process with explicit validation checkpoints (test -d directory checks, required-input prompting, stop-if-not-found) and an error-recovery section that skips downstream dependents on failure.

3 / 3

Progressive Disclosure

Well organized into labeled sections with no nested references, but it is a single long file with inline YAML schema and metadata.json examples that could be split into a reference file for cleaner overview navigation.

2 / 3

Total

10

/

12

Passed

Description

75%

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 clearly states both what the skill does and when to use it, with a distinct niche and explicit trigger guidance. It is slightly held back by limited action enumeration and a narrow set of trigger phrasings.

Suggestions

Broaden trigger terms to include natural variations users might say (e.g., '编排多个角色', '运行多 agent 任务', '执行 .yaml 编排').

Enumerate a few more concrete capabilities (e.g., parse workflow, topologically order steps, save per-step outputs) to lift specificity.

DimensionReasoningScore

Specificity

Names the domain ('agency-orchestrator YAML 工作流') and concrete actions ('运行...工作流', '多角色协作') but stops at a couple of actions rather than a comprehensive list of capabilities.

2 / 3

Completeness

Explicitly answers what it does ('直接运行...工作流——无需 API key,使用当前会话的 LLM 作为执行引擎') and when to trigger ('当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发').

3 / 3

Trigger Term Quality

Includes some natural trigger phrasings ('用户提供 .yaml 工作流文件', '要求多角色协作完成任务') but coverage of variations a user might actually say is narrow.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (agency-orchestrator YAML multi-role orchestration) with distinct triggers unlikely to overlap with generic skills.

3 / 3

Total

10

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
jnMetaCode/superpowers-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.