CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

create-workflow-command

Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/customaize-agent/skills/create-workflow-command/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

The body is well-structured and actionable, with concrete templates and a complete worked example backed by a validation checklist. Its main weakness is conciseness: several sections restate general knowledge Claude already has and could be trimmed.

Suggestions

Trim or remove the model-selection rationale ('haiku - Fast...', 'sonnet - Balanced...', 'opus - Maximum...') and the self-evident rows of the sub-agent capability table, since Claude already knows these defaults.

Tighten the Architecture Overview and Key Principles prose; the context-bloat rationale can be one sentence instead of an explanatory paragraph plus a token-cost table.

Consider moving the full worked feature-implementation example (orchestrator + task file) into a references file and keeping only a compact inline excerpt, to deepen progressive disclosure and reduce SKILL.md length.

DimensionReasoningScore

Conciseness

The body is mostly efficient structured guidance, but several padded sections restate knowledge Claude already has (the model-selection table explaining haiku/sonnet/opus traits and the sub-agent capability table noting 'Read tool - Can read any file'), fitting anchor 3 rather than 4.

3 / 5

Actionability

Provides executable bash (mkdir -p), concrete task-file and orchestrator-command templates, and a fully worked feature-implementation example; placeholders are appropriate for a generation meta-skill, with only minor gaps, matching anchor 4.

4 / 5

Workflow Clarity

The Implementation Process (Steps 1-4) is clearly sequenced and ends with an explicit Validation Checklist of checkboxes; the skill is not destructive/batch so the cap does not apply, but the validation is review-style rather than a runnable validate->fix->retry loop, keeping it at 4 rather than 5.

4 / 5

Progressive Disclosure

No bundle files exist; the skill is a single self-contained document with well-organized, clearly headed sections (Architecture, Principles, Process, Patterns, Example, Limitations, Checklist). At ~425 lines the under-50 simple-skill exception does not fully apply, but structure and placement are good, fitting anchor 4.

4 / 5

Total

15

/

20

Passed

Description

53%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.

The description conveys a clear, fairly specific purpose but lacks an explicit 'Use when...' trigger clause, which caps completeness and weakens trigger-term quality. It is reasonably distinct from other skills but would benefit from natural user-facing trigger phrasing.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill, e.g., 'Use when the user asks to create or scaffold a multi-step workflow command that dispatches sub-agents.'

Replace technical jargon like 'file-based task prompts' and 'sub-agents' with natural trigger terms users would say, such as 'multi-step workflow', 'orchestrate agents', or 'scaffold a command'.

Expand the action list into a few distinct concrete capabilities (e.g., 'scaffolds task files, generates the lean orchestrator command, wires up step dispatch') to lift specificity toward anchor 4.

DimensionReasoningScore

Specificity

Names the domain ('workflow command') and a few concrete aspects ('orchestrates multi-step execution', 'sub-agents', 'file-based task prompts'), but presents a single compound action rather than a list of several distinct concrete actions, matching the anchor 3.

3 / 5

Completeness

Clearly states what the skill does but has no 'Use when...' trigger clause; per the judging guidelines a missing explicit trigger caps completeness at 3, matching the 'clear what, missing when' anchor.

3 / 5

Trigger Term Quality

Includes some relevant keywords ('workflow command', 'orchestrate', 'multi-step') but leans technical with 'sub-agents with file-based task prompts' and misses natural synonyms users would actually say, fitting anchor 3 rather than 4.

3 / 5

Distinctiveness Conflict Risk

Targets a clear niche (creating workflow commands via sub-agents with file-based task files) that is mostly distinct with only minor overlap risk against related orchestration skills, fitting anchor 4.

4 / 5

Total

13

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

NeoLabHQ/context-engineering-kit

Path

plugins/customaize-agent/skills/create-workflow-command/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.