CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentlas-network

Use when the user types /agentlas-network, /agentlas network, $hephaestus-network, or /hep-network to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./codex/plugins/agentlas-core-engine-meta-agent/skills/agentlas-network/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 maximally lean and presents a clear, validation-checkpointed tool sequence, but it is a stub: all arguments are placeholders and the entire execution protocol is delegated to a referenced file that is missing from the bundle. As written, a consumer cannot actually execute the workflow from this skill.

Suggestions

Fix or inline the broken reference: either ship hephaestus-network/SKILL.md in the bundle or inline the essential execution protocol steps, since the body currently points to a nonexistent file for all detail.

Replace the '...' placeholder arguments with one concrete worked example showing realistic values for workOrder, selection, federatedSelection, and toolInventory so the MCP sequence is executable.

Add a short failure-recovery note for the two validation calls (e.g. what to do when validate_selection or validate_execution_receipt rejects), which would also strengthen workflow clarity.

DimensionReasoningScore

Conciseness

The body is ~15 lines with zero padding: a heading, a one-line purpose ("Federated Local + Cloud + Hub workforce staffing orchestrator"), an alias note, a compact MCP call sequence, and a single delegation pointer. Every token earns its place and nothing explains concepts Claude already knows — anchor 5.

5 / 5

Actionability

The MCP sequence names four concrete tools with their parameters, but every argument is an unfilled placeholder ("workOrder=...", "selection=...", "goalId=activeGoalId?") and no worked example shows how to populate them, so nothing is executable as written. This matches anchor 3 (concrete guidance but incomplete; pseudocode rather than executable code) better than 4's 'concrete code with minor gaps'.

3 / 5

Workflow Clarity

The sequence (search_candidates → validate_selection → prepare_execution → validate_execution_receipt) is clearly ordered with two explicit validation checkpoints, matching anchor 4 (clear sequence, most checkpoints present, minor validation gaps). Not 5 because there is no failure-recovery guidance and the actual execution step between prepare and receipt is left implicit; not 3 because validation is explicit in the sequence rather than missing or only implied.

4 / 5

Progressive Disclosure

The body is a stub that delegates the entire protocol to "See [hephaestus-network](hephaestus-network/SKILL.md) for full execution protocol", but that file does not exist anywhere in the bundle (no references/, scripts/, or assets/ directories, no hephaestus-network/ directory). The one reference is clearly signaled but unresolvable, so navigation to the detail content fails — closer to anchor 2 (references effectively unusable) than anchor 3's 'references present but not clearly signaled'.

2 / 5

Total

14

/

20

Passed

Description

70%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 has an explicit and concrete 'Use when' trigger clause with multiple alias variants, and states a specific (if jargon-heavy) capability. Its main weaknesses are a single-action 'what' expressed in domain-specific vocabulary and missing natural-language trigger phrases beyond typed commands.

Suggestions

State the capability in plainer terms alongside the jargon, e.g. 'staff a durable goal by finding, validating, and dispatching registered agents', and list the concrete actions (search, validate, prepare, execute) rather than the single verb 'staff'.

Add one or two natural-language trigger phrases users might say without typing a command (e.g. 'or when the user asks to staff an agent team or find workforce agents').

DimensionReasoningScore

Specificity

"staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams" names the domain and one concrete action, but no further actions are listed — matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor. Not 2 because the action is concrete rather than generic; not 4/5 because only a single action is described.

3 / 5

Completeness

Both parts are explicit: what = "staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams", and a clear "Use when the user types ..." trigger clause. Not 5 because the 'what' leans on opaque jargon ("durable goal", "owner Cloud") that obscures the concrete capability, keeping it at anchor 4.

4 / 5

Trigger Term Quality

Four explicit trigger variants are given ("/agentlas-network", "/agentlas network", "$hephaestus-network", "/hep-network") with good alias coverage, but natural phrases a user might say without typing a command (e.g. "staff a team", "find agents", "workforce") are missing. Fits anchor 4 (good coverage, a few natural terms missing) rather than 5's comprehensive synonyms/extensions.

4 / 5

Distinctiveness Conflict Risk

Distinctive typed-command triggers ("/agentlas-network", "/hep-network") make false triggering unlikely, but the description explicitly aliases the sibling skill "hephaestus-network" and includes a likely-typo variant ("$hephaestus-network"), giving minor overlap risk with that closely related skill — anchor 4.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

agentlas-ai/Agentlas-OS

Path

codex/plugins/agentlas-core-engine-meta-agent/skills/agentlas-network/SKILL.md

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.