workerflow-internal-workflow

Use when a QwenPaw-backed Worker needs to decide whether to do work directly, use native subagents for internal parallelism, or create a temporary QwenPaw agent with a custom AGENTS.md and skills.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/workerflow/skills/agent/worker-internal-workflow/SKILL.md

Quality

Content

82%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 content is highly actionable with concrete tool names, a complete lifecycle, and executable JSON examples for the common cases. Its weakest spot is an implicit validate-before-merge checkpoint for a batch operation, plus mild redundancy across the rules sections.

Suggestions

Add an explicit validation/merge-quality checkpoint before step 10 (merge results), e.g. verify every node returned the required fixed output shape before merging.

Consolidate overlapping guidance across "Subagent template rules", "Fan-out rules", and "Rules" to remove redundancy.

Consider moving the large DAG nodes example into a referenced file to keep SKILL.md a leaner overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight, using a decision table, terse rules, and two real JSON examples rather than explaining concepts Claude already knows; minor redundancy between the "Subagent template rules", "Fan-out rules", and "Rules" sections keeps it just short of fully lean.	4 / 5
Actionability	It provides a numbered 13-step lifecycle, named tools (workflow_run, workflow_update, delete_temp_agent, cleanup_shared), and copy-ready JSON examples covering both the subagents and DAG nodes cases.	5 / 5
Workflow Clarity	The lifecycle is a clear numbered sequence with recovery checkpoints (retry once, mark missing/failed, finally delete temporary agents), but for a batch operation it lacks an explicit validate-before-merge gate, so a couple of checkpoints remain implicit.	4 / 5
Progressive Disclosure	As a self-contained single-file skill it is well organized with clear section headers (Decision, Native Subagent, Temporary Agent, File sharing, Workflow visibility, Fan-out rules, Rules) and no nested references, though the full DAG example and template rules make it somewhat long for one file.	4 / 5
	Total	17 / 20 Passed

Description

71%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 clearly states what the skill does and when to use it, with a well-scoped niche and explicit boundary against the team workflow. Its main weakness is trigger-term naturalness, since the phrasing relies on internal jargon rather than user-facing keywords.

Suggestions

Soften the jargon in the trigger clause or add natural synonyms (e.g. "splitting work inside a Worker", "internal fan-out") so the description matches language a user would actually say.

Consider mentioning the decision-table outcomes (e.g. "or fall back to the team workflow") to make the 'what' more comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates three concrete decision paths ("do work directly, use native subagents for internal parallelism, or create a temporary QwenPaw agent with a custom AGENTS.md and skills"), with only minor coverage gaps relative to the body's full decision table.	4 / 5
Completeness	It answers both "what" (decide among direct / native-subagent / temporary-agent paths) and "when" ("Use when a QwenPaw-backed Worker needs to decide..."), with the when reasonably explicit but not phrased as a concrete trigger-phrase list.	4 / 5
Trigger Term Quality	The "Use when..." clause supplies several relevant terms (QwenPaw-backed Worker, subagents, internal parallelism, AGENTS.md) but they lean on system-internal jargon and lack common synonyms or variations a user would naturally say.	3 / 5
Distinctiveness Conflict Risk	It carves out a clear niche (internal Worker splitting) and explicitly contrasts it with TeamHarness delegation, giving it distinct triggers and minimal conflict risk.	5 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: agentscope-ai/AgentTeams
Path: plugins/workerflow/skills/agent/worker-internal-workflow/SKILL.md
Commit: 223ddc2

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.