CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ticket-pipeline

Thin Codex skill shim for node_ticket_pipeline. Use to run the bounded per-ticket pipeline slice through the OmniMarket runtime adapter.

Quality

72%

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 ./src/omnimarket/adapters/codex/skills/ticket-pipeline/SKILL.md

The canonical home for this skill is ticket-pipeline in OmniNode-ai/omnimarket

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 lean, concrete, and immediately executable: a copy-paste dispatch command, a tabulated argument contract, and explicit output/error handling. Its main weaknesses are the redundant Contract section duplicating the generated runtime-truth block and a dispatch sequence that is implied by section order rather than explicitly enumerated.

Suggestions

Collapse the Contract section or replace it with a one-line pointer to the generated Runtime truth block, since all four facts there are already stated verbatim above.

Present the dispatch as an explicit short sequence (1. build payload, 2. optionally compile-only preflight, 3. dispatch, 4. interpret output) and include one worked example with a real ticket_id and filled payload.

DimensionReasoningScore

Conciseness

The body is dense and operational (argument table, dispatch command, payload shape, output handling) with no explanation of concepts Claude already knows; the only trim opportunity is the Contract section, which repeats the command name, wrapper, and both topics already stated verbatim in the generated Runtime truth block.

4 / 5

Actionability

The dispatch command is concrete and executable ("env -u PYTHONPATH uv run python scripts/run_codex_runtime_request.py --command-name \"ticket_pipeline\" --payload '<json-payload>' --timeout-ms 600000") with a tabulated argument list and an explicit JSON payload shape; the minor gap is that no worked example combines the command with a filled-in payload.

4 / 5

Workflow Clarity

The flow — assemble arguments, build the payload, dispatch via the wrapper, interpret output_payloads[0] or surface error.code — is unambiguous, with --compile-only offered as a preflight checkpoint and explicit failure handling; the sequence is implied by section order rather than enumerated, and the preflight is not positioned as an explicit first step.

4 / 5

Progressive Disclosure

This is a single-file skill with no bundle files (no references/, scripts/, or assets/ exist) and clear section headers (Arguments, Dispatch, Contract, Output) plus one-level-deep repo paths, making navigation easy; the ~38-line generated metadata block and its duplication in the Contract section are minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

57%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 highly distinctive and names a concrete action, but it is written in internal jargon, covers only a single capability, and lacks any explicit "when to use" trigger guidance. Adding a plain-language "Use when..." clause with natural user phrases would materially improve it.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to run, resume, or dry-run the ticket pipeline for a Linear ticket in the omnimarket repo."

Include natural synonyms users would actually say ("ticket pipeline", "run the ticket", "Linear ticket", "process a ticket") alongside the node name.

Expand the single action into 2-3 concrete capabilities (e.g. dispatching with dry-run, skipping TEST_ITERATE, resuming from a phase via skip_to) for fuller coverage.

DimensionReasoningScore

Specificity

The description names a specific domain (node_ticket_pipeline via the OmniMarket runtime adapter) and one concrete action ("run the bounded per-ticket pipeline slice"), but lists no further capabilities, matching the anchor for domain plus 1-2 concrete actions without comprehensive coverage.

3 / 5

Completeness

"Use to run the bounded per-ticket pipeline slice through the OmniMarket runtime adapter" states the what, but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

"ticket pipeline" and "run" are semi-natural trigger terms, but the description is dominated by internal jargon ("Thin Codex skill shim", "bounded per-ticket pipeline slice", "runtime adapter") and omits natural variations a user would say, such as "Linear ticket" or "process a ticket".

3 / 5

Distinctiveness Conflict Risk

The description names a specific backing node, adapter, and transport ("node_ticket_pipeline", "OmniMarket runtime adapter"), giving it a clear niche with distinct triggers and minimal risk of firing for the wrong skill.

5 / 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

src/omnimarket/adapters/codex/skills/ticket-pipeline/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.