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

73%

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 ./src/omnimarket/adapters/codex/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 body is a highly actionable adapter shim: concrete commands, full argument reference, preflight validation, and explicit result handling. Its weaknesses are redundancy between the generated runtime-truth block and the Contract section, a missing worked payload example, and inlining generator-owned contract metadata that would fit better in a separate reference file.

Suggestions

Deduplicate the Contract section against the generated Runtime truth block (command name and both topics appear in both) — keep one authoritative location and reference it.

Add one complete example JSON payload showing typical field values so the '<json-payload>' placeholder is directly fillable.

Move the generator-owned adapter/evidence contract metadata into a reference file (e.g. references/runtime-contract.md) and keep only the dispatch-relevant lines in SKILL.md.

DimensionReasoningScore

Conciseness

The body avoids concept explanations and stays operational, but the command name and both topics are restated across the "Runtime truth" and "Contract" sections, and the ~40-line generator block carries evidence-wire-schema detail that could be trimmed. This matches anchor 3 (mostly efficient, could be tightened) rather than anchor 4's minor trims.

3 / 5

Actionability

An executable dispatch command, a complete argument table with defaults, an explicit payload field list, and concrete ok/error/output handling give mostly copy-paste-ready guidance. The '<json-payload>' placeholder with no worked example payload is the minor gap keeping it from anchor 5.

4 / 5

Workflow Clarity

The flow is clear and ordered: run location, payload mapping, dispatch command, `--compile-only` preflight validation, ok/false branches, and output rendering. It matches anchor 4; not anchor 5 because error handling stops at "surface error.code and error.message" with no fix/retry guidance.

4 / 5

Progressive Disclosure

The skill is a single file with no bundle directories; `scripts/run_codex_runtime_request.py` points into the target repo rather than the skill bundle, and the ~40-line generated contract metadata is inlined content that could live in a reference file. This matches anchor 3 (content that should be separate is inline).

3 / 5

Total

14

/

20

Passed

Description

71%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 is specific, third-person, and tightly scoped to a single backing node, with explicit purpose-based trigger guidance. Its main weakness is narrow trigger vocabulary: only exact internal operation names appear, with no synonyms or user-side phrasings that would broaden natural invocation.

Suggestions

Add natural trigger phrases users would actually say, e.g. "Use when asked to run a session health check, score the dispatch queue, or plan worker dispatch".

Include a synonym or two for the core operations (e.g. "health check" alongside "health gate") so the description matches varied user phrasing.

DimensionReasoningScore

Specificity

"run the session health gate, queue scoring, and dispatch planning loop" names three concrete actions over a clearly identified node. It lists several specific actions with minor gaps (preflight/dry-run capabilities are absent), matching anchor 4 rather than anchor 5's comprehensive coverage.

4 / 5

Completeness

The "what" is explicit (health gate, queue scoring, dispatch planning loop) and "Use to run..." provides explicit trigger guidance, but the "when" lacks concrete varied trigger phrases, matching anchor 4 rather than anchor 5.

4 / 5

Trigger Term Quality

"session health gate", "queue scoring", and "dispatch planning" are relevant keywords, but coverage is limited to exact internal phrases with no common variations or synonyms, matching anchor 3 rather than anchor 4's good coverage.

3 / 5

Distinctiveness Conflict Risk

"Thin Codex skill shim for node_session_orchestrator" carves out a clear niche tied to one specific node with distinct operations, giving minimal conflict risk with other skills.

5 / 5

Total

16

/

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

src/omnimarket/adapters/codex/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.