delegate

Strategic delegation for multi-step coding, research, or verification work. Use when a task can be split into parent reasoning plus focused sub-agent execution through the agent tool.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

90%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.

A high-quality, lean skill body with concrete executable JSON examples, a clear keep-vs-delegate decision frame, and explicit verification guidance. It is held just below top marks only by the absence of an explicit validate-fix-retry feedback loop and minor optional structuring of the prompt-shape examples.

Suggestions

Add an explicit validate→fix→retry loop in the Evaluate and Verify section (e.g. 'if tests fail, fix and re-run before committing') to reach the top workflow-clarity anchor.

Consider splitting the weak-vs-strong prompt examples into a short referenced file or a tighter inline table to push progressive disclosure to fully clean structure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it never explains what sub-agents or delegation are, and every section (Keep vs Delegate, Launch, Evaluate, Prompt Shape) earns its tokens with tight, purposeful prose and compact examples, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	It provides copy-paste-ready JSON launch examples with concrete fields (name, prompt, type, model_strength, cwd) plus a weak-vs-strong prompt contrast with a specific acceptance-criteria example, matching the 'fully executable; copy-paste ready; covers common cases' anchor.	5 / 5
Workflow Clarity	The workflow is clearly sequenced (Keep vs Delegate → Launch Focused Work → Evaluate and Verify) with explicit verification checkpoints ('Read changed files directly', 'Run the relevant tests locally', 'Inspect unexpected diffs'), but it lacks an explicit validate→fix→retry feedback loop, placing it just below the top anchor.	4 / 5
Progressive Disclosure	Content is well-organized into clearly signaled sections with no nested or buried references and no unnecessary external files (none provided), matching 'good structure; most content appropriately placed; minor organization gaps'; it stops short of 5 only because the Prompt Shape examples could optionally be split out.	4 / 5
	Total	18 / 20 Passed

Description

78%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.

A clear, well-structured description that explicitly covers both what the skill does and when to use it, with a distinctive sub-agent delegation trigger. It is slightly light on enumerating multiple concrete actions and a few natural synonyms, which keeps specificity and trigger coverage just below the top anchors.

Suggestions

Add one or two more concrete actions (e.g. 'run focused checks in parallel', 'hand off mechanical edits with a write boundary') to lift specificity toward the multi-action anchor.

Include a few natural synonyms users might say ('delegate', 'parallelize', 'fan out') alongside 'sub-agent execution' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (multi-step coding/research/verification) and one concrete mechanism (split into parent reasoning plus focused sub-agent execution via the agent tool), but does not enumerate several distinct concrete actions, fitting the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action anchor at 4.	3 / 5
Completeness	It explicitly answers both what ('Strategic delegation for multi-step coding, research, or verification work') and when ('Use when a task can be split into parent reasoning plus focused sub-agent execution through the agent tool') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	'multi-step coding, research, or verification' and 'sub-agent execution' / 'agent tool' give good natural keyword coverage a user would plausibly say, with only minor synonyms (e.g. 'delegate', 'parallel') missing, matching the 'good coverage, a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	The 'parent reasoning plus focused sub-agent execution through the agent tool' trigger carves a fairly distinct orchestration niche with minimal conflict risk, but it still overlaps broadly with general coding/research skills, so it sits at 'mostly distinct, minor overlap' rather than the fully distinct anchor at 5.	4 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: Hmbown/Codewhale
Path: crates/tui/assets/skills/delegate/SKILL.md
Commit: 21282f1

Reviewed: 6 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.