Name: agent-agent
Rating: 65 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-agent

Agent skill for agent - invoke with $agent-agent

4.65x

Quality

48%

Does it follow best practices?

Impact

93%

4.65x

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-agent/SKILL.md

The canonical home for this skill is agent-agent in ruvnet/claude-flow

Quality

Content

38%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 rich with concrete, code-driven examples and sequenced workflows, but it is markedly verbose, leans on undefined helper functions and inconsistent MCP tool names that hurt executability, and ships as a single monolithic file with no progressive disclosure. Validation checkpoints and external reference files are the main gaps.

Suggestions

Split reference-grade material into bundle files (e.g., references/tool-catalog.md, references/examples.md, references/advanced-config.md) and keep SKILL.md a lean overview with one-level-deep, clearly signaled links.

Make code examples self-contained by defining or importing the helper functions they call (canTransition, stateKey, heuristic, PriorityQueue, buildDependencyMatrix, recursiveDecompose) and reconcile MCP tool names with the listed catalog.

Add explicit validation checkpoints to the workflows (e.g., validate the plan satisfies preconditions before execution, verify the goal state is reached afterward) and trim the restated-concept prose and marketing framing to respect the token budget.

Dimension	Reasoning	Score
Conciseness	The ~810-line body opens with marketing prose restating the description and repeatedly explains standard concepts Claude already knows (PageRank, A* search, behavior trees, utility functions, OODA loops); several sections are padded, matching the 'noticeably verbose; several unnecessary explanations or padded sections' anchor rather than the mostly-efficient anchor.	2 / 5
Actionability	Concrete JavaScript calling named MCP tools fills the body, but many examples depend on undefined helpers (canTransition, stateKey, heuristic, PriorityQueue, buildDependencyMatrix, recursiveDecompose) and reference tools whose names disagree with the listed tool catalog (mcp__sublinear_time_solver__validateTemporalAdvantage, mcp__claude_flow__* vs mcp__flow-nexus__*), leaving key execution details missing; fits the anchor with concrete but incomplete guidance rather than the mostly-executable anchor.	3 / 5
Workflow Clarity	Numbered workflows (state modeling through A* search, advanced planning 1-3, usage examples 1-5) provide a clear sequence and a feedback loop exists (the OODA loop and replan-on-deviation), but explicit validation checkpoints before execution are sparse and implicit, matching the anchor with steps listed but validation gaps; the destructive/batch cap of 3 also applies since plans drive real action execution.	3 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and the entire skill is a monolithic ~810-line SKILL.md with reference-grade material (tool catalog, many long code examples, advanced configuration) inlined that clearly belongs in separate files; the header structure offers some organization but nothing is split out, matching the 'content that clearly belongs in separate files is inlined' anchor.	2 / 5
	Total	10 / 20 Passed

Description

58%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 states a clear niche (GOAP planning) with several concrete capabilities, but it omits any "Use when..." trigger guidance, which caps completeness and weakens trigger-term quality. It is reasonably distinct from other skills yet would benefit from explicit usage triggers and more natural keywords.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger situations (e.g., 'Use when the user needs to plan multi-step objectives under constraints, decompose complex goals, or adaptively replan as conditions change').

Include more natural user-facing keywords and synonyms (e.g., 'task planning', 'goal breakdown', 'action sequencing', 'plan optimization') alongside the technical term 'GOAP'.

Fix the malformed frontmatter: the file contains two YAML blocks and the real description lives in the second one while the first publishes a placeholder ('Agent skill for agent - invoke with $agent-agent'); consolidate into a single frontmatter block.

Dimension	Reasoning	Score
Specificity	Names the GOAP domain and several concrete capabilities ("dynamically creates intelligent plans", "adaptive replanning", "multi-step reasoning", "finding optimal paths", "combining actions in creative ways"), matching the anchor that lists several specific actions with minor gaps; not a 5 because it lacks an enumerated action list, not a 3 because it goes beyond 1-2 actions.	4 / 5
Completeness	The "what" is clear (planning, replanning, reasoning, path-finding) but there is no "Use when..." or equivalent trigger guidance at all, and the rubric caps completeness at 3 when explicit trigger guidance is missing; not 4 because no when-clause is present.	3 / 5
Trigger Term Quality	Relevant terms appear ("Goal-Oriented Action Planning", "GOAP", "plans", "multi-step reasoning") but common variations/synonyms are missing and "gaming AI techniques" is not a phrase users naturally say; matches the anchor with some relevant keywords but missing common variations rather than the good-coverage anchor.	3 / 5
Distinctiveness Conflict Risk	The GOAP/gaming-AI specialization is mostly distinct from generic planning skills with only minor overlap risk; not 5 because no explicit trigger phrases sharpen the niche, not 3 because it is more specific than broad document/file skills.	4 / 5
	Total	14 / 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 (821 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: ruvnet/ruflo
Path: .agents/skills/agent-agent/SKILL.md
Commit: fa13ee4

Reviewed: about 8 hours 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.