CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pr-polish

Thin Codex skill shim for node_pr_polish. Use to polish a PR toward merge readiness through the OmniMarket runtime adapter.

Quality

67%

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 ./plugins/onex/skills/pr-polish/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 content is a focused, actionable dispatch guide: it gives an executable command, an explicit argument-to-payload mapping, preflight and error-handling guidance, and clear output interpretation rules, with no filler or over-explanation. Its main weakness is redundancy — transport metadata is restated across the generated "Runtime truth" and "Contract" sections. Overall it scores above the midpoint.

Suggestions

Consolidate the command name and topic strings that currently appear in both the generated "Runtime truth" section and the "Contract" section into a single source of truth to cut duplicated tokens.

Replace the `'<json-payload>'` placeholder with one small copy-paste-ready example JSON payload (e.g. `{"repo": "OmniNode-ai/omnimarket", "pr_number": 123}`) to make dispatch fully executable.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence and explains no known concepts, but the command name `pr_polish` and the command/terminal topics are repeated three to four times across the generated "Runtime truth" section, the "Contract" section, and the dispatch prose. Mostly efficient but could be tightened by consolidating the duplicated metadata.

3 / 5

Actionability

The dispatch section gives a concrete, runnable command with exact flags (`env -u PYTHONPATH uv run python scripts/run_codex_runtime_request.py --command-name "pr_polish" ... --timeout-ms 300000`) plus an explicit payload field list and error-handling rules. Not 5 because `--payload '<json-payload>'` is a placeholder rather than a copy-paste-ready example payload.

4 / 5

Workflow Clarity

The sequence is clear: map user inputs to payload fields, optionally preflight with `--compile-only`, dispatch via the wrapper, then branch on `ok`/`output_payloads` vs `error.code`/`error.message`. Checkpoints (compile-only preflight, explicit error surfacing) are present; not 5 because there is no recovery guidance beyond surfacing the error.

4 / 5

Progressive Disclosure

No bundle files exist and none are needed; the body is organized into clear sections (Arguments, Dispatch, Contract, Output) with content mostly appropriately placed. Not 5 because the ~40-line generator-owned transport/binding metadata block is inlined in SKILL.md where a one-level-deep reference file would keep the overview leaner.

4 / 5

Total

15

/

20

Passed

Description

53%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 short, honest, and appropriately specific about its niche as a runtime adapter shim, but it under-communicates what the skill actually does and lacks an explicit 'Use when...' trigger clause. It reads more like internal architecture documentation than a trigger-facing description. Overall it sits just above the midpoint of the scale.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to polish, finalize, or get a pull request ready to merge in the OmniMarket repo."

Enumerate the concrete capabilities the node provides (conflict resolution, CI repair, review-comment handling, local review, automerge) so the 'what' is comprehensive rather than a single summarizing verb.

Include natural synonyms such as "pull request", "fix CI", and "address review comments" to improve trigger-term coverage.

DimensionReasoningScore

Specificity

"Use to polish a PR toward merge readiness" names the domain and one moderately concrete action, but the actual capabilities (conflict resolution, CI repair, review-comment handling, automerge) are absent. Not 4 because it does not list several specific actions; not 2 because a real action is stated rather than generic processing.

3 / 5

Completeness

The 'what' is clear (polish a PR toward merge readiness via the runtime adapter), but "Use to polish a PR" restates the what rather than providing trigger guidance; there is no "Use when..." clause or equivalent, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"polish a PR" and "merge readiness" are natural phrases a user might say, but common variations like "pull request", "fix CI", or "address review comments" are missing. Fits the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"node_pr_polish" and "OmniMarket runtime adapter" carve a specific niche with minimal conflict risk, and "polish a PR" is a distinctive trigger. Not 5 because the description would still mildly overlap with generic PR-preparation or merge skills.

4 / 5

Total

13

/

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/pr-polish/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.