CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hephaestus-network

Use when the user types $hephaestus-network, /hep-network, or /agentlas-network, mentions @Hephaestus, or asks Agentlas to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM staffs each turn; the exact roster remains goal-bound until explicit completion.

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/hephaestus-network/SKILL.md

The canonical home for this skill is hephaestus-network in agentlas-ai/Agentlas-OS

SKILL.md
Quality
Evals
Security

Quality

Content

62%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 delivers an unusually well-validated, unambiguous workflow with exact tool names, fields, and failure paths — sequencing and checkpoints are excellent. Its costs are token efficiency and structure: dense, repetitive policy prose with inline dated/versioned detail, and no progressive disclosure of reference material that would keep the main file lean.

Suggestions

Move stable detail into one-level-deep reference files (e.g. receipts.md for the section-7 field inventory, digest-rules.md for canonicalization/validation rules, model-policy.md for role mappings and allocation policy) and keep SKILL.md as a lean overview with clearly signaled links.

Deduplicate the truthfulness/receipt caveats repeated across sections 4, 6, and 7 into a single authoritative statement, and convert the 'Measured 2026-09-24' incident into a short bullet in an 'old patterns / known pitfalls' section.

Add one compact worked example — a sample compact decision with one assignments row and reason codes — so the core payload shape is shown, not only described in prose.

DimensionReasoningScore

Conciseness

The ~440-line body is noticeably verbose: truthfulness caveats are restated across sections 4, 6, and 7, 'Do not call / Never fabricate' rules repeat, and an inline dated incident report ('Measured 2026-09-24: a Codex session probed the invented mcp__agentlas__workforce__goal_context...') plus inline version pins (protocol '2026-08-20.1', 'runtime 1.2.49', digest schema 'v4') add time-sensitive padding outside any deprecated/old-patterns section. It avoids anchor 1 only because it never explains concepts Claude already knows — the padding is redundant domain policy, not basic-concept teaching.

2 / 5

Actionability

Concrete, executable artifacts dominate: a copy-paste bash runner-resolution block, the ordered typed MCP sequence (workforce.preflight_work_order through workforce.validate_execution_receipt), an executable 'workforce execute' command, exact schema names, exact reason codes (reason:best-content-fit, reason:host-semantic-judgment), and exact turn postures. It stops short of anchor 5 because the MCP calls use '...' parameter elision and no complete worked example of a decision, assignments row, or role entry is ever shown — a minor but real gap.

4 / 5

Workflow Clarity

The process is clearly sequenced (runner/sign-in, protocol check, then numbered steps 1-7: job analysis, menu retrieval and decision, validation and pinning, goal binding, model policy, execution, receipts) with explicit validation at every phase (preflight boundary, validate_selection, digest recompute, validate_execution_receipt) and genuine feedback loops ('Re-plan on rejection', at-most-two refinements, the upgrade-required reload path). This matches the anchor-5 pattern of explicit validation steps with error-recovery loops for a complex process.

5 / 5

Progressive Disclosure

The body has real section structure in workflow order, but it is a 440-line monolith with zero reference files: content that clearly belongs in separate references — the section-7 receipt field inventory, the digest canonicalization rules ('__proto__/prototype/constructor fail closed'), the model-role vocabulary mapping, the host-adapter transport contract — is all inlined. This fits anchor 3 ('content that should be separate is inline') rather than anchor 2, since structure is present and navigable, not minimal; with no bundle files provided, nothing can be scored against an actual reference layout.

3 / 5

Total

14

/

20

Passed

Description

73%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 excellent, explicit trigger guidance built on unique command aliases and an @-mention, making misfiring very unlikely. Its main weakness is that the capability statement is wrapped in proprietary jargon ('staff a durable goal', 'goal-bound') that obscures what the skill concretely does for an unfamiliar reader.

Suggestions

Restate the core capability in plain verbs, e.g. 'Selects and runs a roster of registered Local, owner Cloud, and public Hub agents/teams for a long-running goal: searches candidate menus, validates the selection, and executes workers through the host runtime.'

Add one or two natural-language synonyms users might say without knowing the command, such as 'agent workforce', 'build a team of agents', or 'recruit agents for a goal'.

DimensionReasoningScore

Specificity

Phrases like "staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams" and "The active host LLM staffs each turn" name the domain plus 1-2 concrete behaviors, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor. It is below anchor 4 because the concrete mechanics (candidate search, selection validation, execution receipts) are absent, and above anchor 2 because the actions named are specific rather than generic.

3 / 5

Completeness

Both parts are present: an explicit 'Use when' clause with concrete triggers, and a what-statement ("staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams... roster remains goal-bound until explicit completion"). It is not anchor 5 because the 'what' is stated in opaque system jargon ('durable goal', 'goal-bound') that a reader unfamiliar with Agentlas cannot fully decode, and it is above anchor 4's baseline since the 'when' is explicit and specific rather than weakly implied.

4 / 5

Trigger Term Quality

The description covers multiple invocation variants users would naturally produce: "$hephaestus-network, /hep-network, or /agentlas-network, mentions @Hephaestus, or asks Agentlas to staff a durable goal", giving good keyword coverage across command aliases and a semantic phrase. It falls short of anchor 5 because common natural synonyms such as 'agent workforce', 'build a team', or 'recruit agents' are missing.

4 / 5

Distinctiveness Conflict Risk

Triggers are exact, unique proper nouns and commands ($hephaestus-network, /hep-network, /agentlas-network, @Hephaestus, "asks Agentlas to staff a durable goal"), giving a clear niche with minimal overlap risk with any other skill. This clearly matches the anchor-5 example pattern of distinct, proprietary trigger phrases.

5 / 5

Total

16

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

agentlas-ai/Agentlas-OS

Path

codex/plugins/agentlas-core-engine-meta-agent/skills/hephaestus-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.