CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-hierarchical-coordinator

Agent skill for hierarchical-coordinator - invoke with $agent-hierarchical-coordinator

59

9.66x
Quality

41%

Does it follow best practices?

Impact

87%

9.66x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-hierarchical-coordinator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers concrete, well-organized swarm-coordination guidance with specific MCP tooling, but it is padded with generic management advice, embeds a core protocol in non-executable pseudocode, and omits validation checkpoints. Its monolithic structure gains nothing from progressive disclosure since no supporting files are provided.

Suggestions

Replace the invented mcp__claude-flow__memory_usage { ... } block syntax with actual executable call forms (e.g. real shell invocations matching the bash MCP examples) so the mandatory protocol is copy-paste ready.

Add explicit validation/feedback checkpoints to the workflow (e.g. verify a spawned worker's status before delegation, validate integrated deliverables, re-assign on threshold breach) to support the batch/swarm operations.

Trim generic delegation boilerplate Claude already knows (task decomposition truisms, best-practices platitudes) and move large reference blocks (memory key structure, full MCP integration list, metrics) into separate reference files linked from the overview.

DimensionReasoningScore

Conciseness

The body supplies concrete MCP commands but pads them with management boilerplate Claude already knows (e.g. 'Break down complex objectives into manageable sub-tasks', 'Provide detailed requirements and acceptance criteria'), so it is mostly efficient yet includes unnecessary explanation that could be tightened.

2 / 3

Actionability

Concrete bash MCP commands with flags appear throughout (swarm_init, agent_spawn, task_orchestrate), but the central 'MANDATORY MEMORY COORDINATION PROTOCOL' uses an invented non-executable syntax (mcp__claude-flow__memory_usage { action: "store", ... }) that is pseudocode rather than copy-paste-ready, leaving a key detail gap.

2 / 3

Workflow Clarity

The three phases (Planning, Execution, Integration) are sequenced, but the swarm/batch workflow lacks validation checkpoints or validate-then-retry feedback loops despite spawning agents and integrating deliverables, which caps workflow_clarity at 2 per the batch-operations guideline.

2 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets absent) and the ~290-line body is a monolithic document with inline memory protocol, worker types, MCP integrations, metrics, and best practices that could be split into separate reference files; section structure exists but content that should be separate is inline.

2 / 3

Total

8

/

12

Passed

Description

32%

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 frontmatter description is a generic stub that names the skill domain and its invocation token but states no concrete capabilities and gives no 'when to use it' guidance. It distinguishes itself only by name rather than by behavior or triggers.

Suggestions

State the concrete capabilities the skill performs, e.g. 'Decomposes objectives into sub-tasks, spawns specialized worker agents, delegates work, and monitors swarm progress.'

Add an explicit trigger clause such as 'Use when coordinating a multi-agent swarm, delegating sub-tasks to specialized workers, or synchronizing hierarchical agent teams.'

Replace the invocation-syntax token with natural user-facing keywords (swarm coordination, task delegation, hierarchical agents) so it surfaces for the right requests.

DimensionReasoningScore

Specificity

The description names the domain concretely ("hierarchical-coordinator") but lists no concrete capabilities — only "Agent skill for hierarchical-coordinator" — so it names the domain without enumerating actions, matching the score-2 anchor partially.

2 / 3

Completeness

The 'what' is weak (merely 'Agent skill for hierarchical-coordinator') and the 'when' is entirely absent with no 'Use when...' clause, matching the score-1 anchor where both what and when are weak or missing.

1 / 3

Trigger Term Quality

It surfaces one relevant token ("hierarchical-coordinator" and the invocation string "$agent-hierarchical-coordinator") but provides no natural-language keywords a user would say (e.g., swarm, delegation, coordination), matching 'some relevant keywords but missing common variations.'

2 / 3

Distinctiveness Conflict Risk

The 'hierarchical-coordinator' niche is fairly specific and unlikely to collide with unrelated skills, but with no behavioral triggers stated it could still overlap with other coordination/swarm skills, matching 'somewhat specific but could still overlap.'

2 / 3

Total

7

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/claude-flow
Reviewed

Table of Contents

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.