CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

session-orchestrator

Thin Codex skill shim for node_session_orchestrator. Use to run the session health gate, queue scoring, and dispatch planning loop.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/onex/skills/session-orchestrator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 highly actionable for its narrow runtime-adapter purpose, with an executable dispatch command, a full argument table, and preflight/error checkpoints. Its main weaknesses are duplicated transport metadata across two sections and a monolithic inline generated block that should be split into a reference file, plus the lack of a worked example payload.

Suggestions

Deduplicate the transport metadata: the command name and both topics appear verbatim in both the 'Runtime truth' block and the 'Contract' section — keep one authoritative location and reference it.

Add a complete example JSON payload (with a sample correlation_id and typical arguments) so the dispatch command is copy-paste ready instead of a '<json-payload>' placeholder.

Move the generated 'Runtime truth' transport/binding metadata into a references/ file (e.g., references/runtime-truth.md) and keep a brief pointer in SKILL.md, trimming the inline payload-field bullet list that duplicates the argument table.

DimensionReasoningScore

Conciseness

The body is dense operational detail rather than explanation of known concepts, but the command name and both topics are repeated verbatim between the "Runtime truth" block and the "Contract" section, and payload field names are listed twice (table plus bullet list), so it could be tightened.

3 / 5

Actionability

Provides a concrete executable dispatch command, a complete argument table with defaults, explicit payload-field mapping, and error-handling direction ("surface error.code and error.message directly"), but the '--payload <json-payload>' placeholder and absence of a complete example payload keep it from copy-paste readiness.

4 / 5

Workflow Clarity

The input-mapping, dispatch, compile-only preflight, and result/error interpretation flow is clear with checkpoints (--compile-only validates before publishing; ok:false handling is specified), though steps are not explicitly numbered and there is no validate-fix-retry loop.

4 / 5

Progressive Disclosure

The body is well-sectioned but no bundle files exist, and the ~40-line generated runtime-truth block with transport metadata is inlined in a 115-line body where a clearly signaled reference file would be more appropriate.

3 / 5

Total

14

/

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 clearly states what the skill does by naming the node's three functions, and its unique node anchor makes conflict risk low. However, it lacks any "Use when..." trigger guidance and relies on internal jargon rather than natural user phrases, which limits completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause naming the situations or user requests that should trigger this skill (e.g., 'Use when asked to run or check session health, score the dispatch queue, or plan worker dispatch').

Replace the uniform verb 'run' with concrete third-person verbs per function (e.g., 'Gates session health, scores the dispatch queue, and plans worker dispatch') so each capability is described concretely.

Include natural synonyms or phrasings a user would actually say (e.g., 'health check', 'dispatch queue', 'session run') alongside the internal terminology to broaden trigger coverage.

DimensionReasoningScore

Specificity

Enumerates the node's three specific functions ("session health gate, queue scoring, and dispatch planning loop"), which covers the full scope, but the uniform verb "run" applied to jargon objects falls short of anchor 5's concretely described actions.

4 / 5

Completeness

"Use to run the session health gate, queue scoring, and dispatch planning loop" gives a clear "what", but there is no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 3.

3 / 5

Trigger Term Quality

Keywords like "session health gate", "queue scoring", and "dispatch planning" are what users of this system would say, but the description leans on internal jargon ("Thin Codex skill shim for node_session_orchestrator") and offers no natural synonyms or variations.

3 / 5

Distinctiveness Conflict Risk

Anchoring to the unique node name "node_session_orchestrator" gives a clear niche with minimal wrong-skill risk, but "session" and "dispatch" are common terms and no distinct trigger phrases are provided.

4 / 5

Total

14

/

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

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

15

/

16

Passed

Repository

OmniNode-ai/omnimarket

Path

plugins/onex/skills/session-orchestrator/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.