CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

adversarial-pipeline

Thin Codex skill shim for node_adversarial_pipeline_orchestrator. Use when running the adversarial plan-to-ticket pipeline through runtime truth.

Quality

70%

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/adversarial-pipeline/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 a well-structured, actionable dispatch guide with exact commands, argument defaults, and explicit success/error handling. Its main costs are a fully redundant Contract section and a missing concrete example payload; moving the generated contract metadata into a reference file would tighten it further.

Suggestions

Delete or collapse the "Contract" section — all four facts (backing node, wrapper path, command name, both topics) already appear in the generated runtime-truth block.

Add one concrete example payload, e.g. --payload '{"topic": "...", "min_findings_gate": 3, "dry_run": true}', so the dispatch command is fully copy-paste executable.

Recommend a validation sequence for ticket-creating runs (e.g. run with --compile-only or dry_run first, then dispatch), which would also raise workflow clarity to anchor 5.

DimensionReasoningScore

Conciseness

The body is dense and project-specific with no padding, but the "Contract" section repeats the command name, both contract topics, and the wrapper path already stated verbatim in the generated runtime-truth block, and the intro paragraph restates the frontmatter description — clear tightening opportunities that fit 'mostly efficient but could be tightened'.

3 / 5

Actionability

Gives a copy-paste-ready dispatch command with flags, a complete argument table with defaults, explicit payload field names, and concrete ok/error handling; the only gap is that the payload is shown as a '<json-payload>' placeholder with no worked example payload, keeping it just below fully-executable anchor 5.

4 / 5

Workflow Clarity

The single dispatch flow is unambiguous (run wrapper → check ok → render output_payloads[0] / surface error.code), with a compile-only preflight option, a documented dry_run flag, and an explicit stop state for node_not_implemented; it stops short of anchor 5 because there is no explicit preflight-then-dispatch sequencing or dry-run-first guidance for ticket-creating runs.

4 / 5

Progressive Disclosure

No bundle files exist and the body is well-sectioned (Arguments, Dispatch, Contract, Output) with clearly marked generated content, but at ~110 lines everything is inline — the 38-line contract metadata block is never offloaded to a reference file, fitting 'good structure; minor organization gaps' rather than a clean overview-plus-references split.

4 / 5

Total

15

/

20

Passed

Description

61%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 'Use when' trigger and a distinct, conflict-free niche, but the 'what' is jargon-heavy and vague about concrete capabilities. Listing the skill's actual actions (dispatch runtime requests, gate on hostile-review findings, create tickets) would lift specificity and trigger coverage.

Suggestions

Replace "Thin Codex skill shim for node_adversarial_pipeline_orchestrator" with the concrete actions the skill performs, e.g. "Dispatches adversarial plan-to-ticket pipeline runs (design-to-plan, hostile-review gating, ticket creation) via the runtime request wrapper".

Add natural trigger synonyms to the 'Use when' clause, such as "hostile review", "plan-to-ticket", or "create tickets from a design/plan", and drop the internal jargon "runtime truth" from the trigger.

Keep the node name as a secondary identifier rather than the main capability statement, so the description reads as what the skill does rather than what it wraps.

DimensionReasoningScore

Specificity

"Thin Codex skill shim for node_adversarial_pipeline_orchestrator" names the domain but states no concrete actions the skill itself performs; the actual capabilities (dispatching runtime requests, hostile-review gating, ticket creation) appear only in the body, matching the 'names the domain but actions are minimal or generic' anchor.

2 / 5

Completeness

An explicit "Use when running the adversarial plan-to-ticket pipeline" trigger answers 'when', and "thin Codex skill shim for node_adversarial_pipeline_orchestrator" answers 'what', but the 'what' is thin on capabilities so it falls short of the clearly-explicit-both anchor 5.

4 / 5

Trigger Term Quality

"running the adversarial plan-to-ticket pipeline" is a phrase a user of this system would plausibly say, but it is surrounded by pure jargon ("runtime truth", "Codex skill shim", the raw node name) and misses natural synonyms such as "hostile review" or "create tickets from a design", fitting 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

The trigger "adversarial plan-to-ticket pipeline" carves out a clear niche tied to one named orchestrator node, making accidental triggering of another skill very unlikely.

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

plugins/onex/skills/adversarial-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.