how-to-delegate

Scientific delegation framework for orchestrators — provide observations and success criteria while preserving agent autonomy. Use when assigning work to sub-agents, before invoking the Agent tool, or when preparing delegation prompts for specialist agents.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/agent-orchestration/skills/how-to-delegate/SKILL.md

Quality

Content

73%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 a highly actionable, well-sequenced delegation worksheet with strong workflow clarity and validation checkpoints. Its weakness is mild verbosity from repeated anti-pattern reminders and conceptual rationales that assume Claude lacks knowledge it already has.

Suggestions

State the 'never pre-gather / define WHAT not HOW' principles once in Core Principles and reference them from later steps instead of restating them in Steps 3, 8, and 10.

Trim conceptual rationales (e.g. 'Agents have 200k context windows... context rot') that re-explain knowledge Claude already has, keeping only the actionable directive.

Dimension	Reasoning	Score
Conciseness	The worksheet is substantive and well-structured, but repeats the same anti-patterns across multiple steps (the 'never pre-gather' rule appears in Core Principles, Step 3, Step 8, and Step 10) and includes conceptual rationales (e.g. explaining context rot) that could be tightened.	3 / 5
Actionability	Provides concrete executable commands (the Skill() call, the final Agent() invocation), a copy-paste Step 9 prompt template, decision flowcharts, and pass/fail checklists; minor gaps stem from intentional '[Example: ...]' worksheet placeholders and Step-7 indirection.	4 / 5
Workflow Clarity	A clearly sequenced 10-step workflow with an opening conditional-execution flowchart and explicit validation checkpoints (Step 8 pre-flight checklist and Step 10 ready-to-delegate checklist) plus conditional remediation instructions, matching the feedback-loop anchor.	5 / 5
Progressive Disclosure	Cleanly organized into labeled sections with one clearly-signaled one-level reference to the external agent-orchestration skill; no bundle files are provided and none are needed, though the in-file worksheet is long and could benefit from tighter separation.	4 / 5
	Total	16 / 20 Passed

Description

73%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 defines a niche orchestrator-focused delegation skill with an explicit, multi-trigger 'Use when' clause and strong distinctiveness. Its main weakness is that the 'what' is framed conceptually rather than as a concrete list of capabilities.

Suggestions

Replace abstract framing ('scientific delegation framework') with concrete actions, e.g. 'Prepare delegation prompts by gathering observations, defining success criteria, and selecting specialist sub-agents'.

Add a few more natural trigger synonyms such as 'delegate a task' or 'hand off work to an agent' to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('delegation framework for orchestrators') and 1-2 actions ('provide observations and success criteria', 'preserving agent autonomy'), but these are conceptual rather than a comprehensive list of concrete actions.	3 / 5
Completeness	Both a 'what' (scientific delegation framework providing observations and success criteria) and an explicit, multi-trigger 'when' ('Use when...') are present; the 'what' is somewhat abstract rather than a concrete action list, keeping it just below a clean 5.	4 / 5
Trigger Term Quality	Natural trigger phrases like 'assigning work to sub-agents', 'before invoking the Agent tool', and 'preparing delegation prompts for specialist agents' give good keyword coverage, though a few common variations (e.g. 'delegate a task') are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear orchestrator-delegation niche with distinct triggers (sub-agents, Agent tool, specialist agents) and minimal overlap risk with unrelated skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: Jamie-BitFlight/claude_skills
Path: plugins/agent-orchestration/skills/how-to-delegate/SKILL.md
Commit: c337daf

Reviewed: 3 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.