agent-resource-allocator

Agent skill for resource-allocator - invoke with $agent-resource-allocator

5.00x

Quality

14%

Does it follow best practices?

Impact

80%

5.00x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-resource-allocator/SKILL.md

Quality

Content

25%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.

This reads as generated marketing/spec material for an agent rather than an operational skill: an agent profile, four large pseudocode class showcases, and command listings, with no actual workflow for Claude to follow and no executable code. The stray duplicated frontmatter block at the top of the body confirms structural carelessness. It needs radical compression, one concrete decision procedure with validation steps, and its reference material split into real bundle files.

Suggestions

Replace the pseudocode class showcases with a short, concrete decision procedure (collect metrics → analyze bottlenecks → decide allocation → apply → verify impact) with explicit validation/rollback checkpoints, since resource reallocation and scaling are risky batch operations.

Cut the body to a lean overview and move the MCP tool catalog and 'npx claude-flow' command reference into real files under references/ (e.g. references/commands.md, references/mcp-tools.md), keeping SKILL.md under ~100 lines.

Delete the stray second frontmatter block and the duplicated profile/summary boilerplate, and make code examples executable (real flags, complete commands) instead of classes relying on undefined helpers.

Dimension	Reasoning	Score
Conciseness	The ~680-line body is heavily padded with ~19KB of decorative class scaffolding (AdaptiveResourceAllocator, PredictiveScaler, DeepQNetworkAgent training loops, AdaptiveCircuitBreaker) that restates patterns Claude already knows and adds little actionable information per token. This matches 'severely verbose; heavily padded' rather than the merely 'noticeably verbose' anchor 2.	1 / 5
Actionability	There is some concrete guidance — the 'npx claude-flow ...' command blocks are near-executable — but the bulk of the code is pseudocode depending on undefined helpers (CPUAllocator, this.calculateOptimalAllocation, mcp.neural_train, MultiObjectiveGeneticSolver) whose implementations are never given, matching 'pseudocode instead of executable code; missing key details'.	3 / 5
Workflow Clarity	The body is a capability catalog rather than a sequenced process; the only ordering (analyze → predict → optimize → execute) is buried inside illustrative code, and there are no validation checkpoints despite batch/destructive operations like swarm scaling and resource reallocation, which per the feedback-loop guidance would cap this at 3 even if sequencing were better.	2 / 5
Progressive Disclosure	Everything is inlined in one monolithic file: the class catalogs, MCP integration hooks, CLI command reference, and KPI definitions each clearly belong in separate reference files, and no bundle files (references/, scripts/, assets/) exist at all. Section headers exist, keeping it above the unstructured anchor 1, but the inlining matches 'content that clearly belongs in separate files is inlined'.	2 / 5
	Total	8 / 20 Passed

Description

3%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 fails as a trigger: it is invocation boilerplate that says nothing about what the skill does or when to use it. The real description ('Adaptive resource allocation, predictive scaling and intelligent capacity planning') was mistakenly placed in a second, stray frontmatter block in the body instead of the actual frontmatter. Rewriting the frontmatter description with concrete capabilities plus a 'Use when...' clause would move every dimension up substantially.

Suggestions

Replace the frontmatter description with the intended one from the stray second frontmatter block, expanded with concrete actions, e.g. 'Allocates CPU/memory/network resources adaptively, predicts scaling needs from workload patterns, and profiles system performance. Use when the user mentions resource allocation, capacity planning, predictive scaling, or swarm performance tuning.'

Remove the duplicated second '---' frontmatter block from the body, which currently splits the skill's identity across two metadata blocks.

Add natural trigger phrases and synonyms (resource allocation, capacity planning, scaling, bottlenecks) so the skill is discoverable by what users actually say rather than by its internal name.

Dimension	Reasoning	Score
Specificity	The description ('Agent skill for resource-allocator - invoke with $agent-resource-allocator') contains no concrete actions or capability statements at all — it is pure invocation metadata. It is vaguer than the anchor-2 example ('Processes PDF files'), which at least names a generic action.	1 / 5
Completeness	Neither 'what does this do' (no capabilities are described) nor 'when should Claude use it' (no 'Use when...' clause or equivalent) is present. Even the domain ('Adaptive resource allocation...') appears only in the body's stray second frontmatter, not in the evaluated description.	1 / 5
Trigger Term Quality	'resource-allocator' is an internal skill identifier, not a phrase a user would naturally say; there are no natural trigger keywords or synonyms anywhere in the description. This matches the anchor 'no natural keywords; only technical jargon or entirely generic language'.	1 / 5
Distinctiveness Conflict Risk	The text is a generic meta-label with no distinct triggers, so it risks colliding with any resource-management or scaling skill; it is saved from a 1 only because it at least names a resource-allocation domain rather than being about 'anything'.	2 / 5
	Total	5 / 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
skill_md_line_count	SKILL.md is long (679 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: ruvnet/ruflo
Path: .agents/skills/agent-resource-allocator/SKILL.md
Commit: b14c79e

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.