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

66%

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/pr-polish/SKILL.md

The canonical home for this skill is pr-polish in OmniNode-ai/omnimarket

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 delivers concrete, executable dispatch guidance with validation and error paths, and it correctly scopes itself as a thin shim. Its weaknesses are redundancy (duplicated contract facts and argument lists) and organization — the generator-owned metadata block interrupts the Arguments section and could live in a reference file.

Suggestions

Delete or shrink the "## Contract" section, which repeats the command name and both topics already stated verbatim in the generated runtime-truth block.

Replace the 14-item payload bullet list with a note that payload field names mirror the argument table, plus one complete example JSON payload (e.g. {"repo": "OmniNode-ai/omnimarket", "pr_number": 123}) to make the dispatch command copy-paste ready.

Move the generated runtime-truth metadata (topics, evidence schema, binding fields) into a reference file such as references/runtime-contract.md so the "## Arguments" heading sits directly above its table.

DimensionReasoningScore

Conciseness

The body is mostly operational, but the "## Contract" section duplicates the command name and both topics already stated in the generated runtime-truth block, and the payload bullet list repeats all 14 argument names from the table — more than minor tightening opportunities.

3 / 5

Actionability

The dispatch command is concrete and nearly copy-paste ready ("env -u PYTHONPATH uv run python scripts/run_codex_runtime_request.py --command-name \"pr_polish\" ... --timeout-ms 300000") with a full argument table, a preflight flag, and explicit error handling; the "<json-payload>" placeholder instead of a worked example payload is the main gap.

4 / 5

Workflow Clarity

The sequence is discernible with most checkpoints present: optional "--compile-only" preflight validation, dispatch, checking "ok"/"output_payloads", and surfacing "error.code" and "error.message" on failure; missing retry/timeout recovery guidance keeps it below a 5.

4 / 5

Progressive Disclosure

The single file has section structure, but the "## Arguments" heading is separated from its table by ~40 lines of generated contract metadata (wire schemas, binding-field enumerations) that belongs in a separate reference file, leaving organization and navigation short of good.

3 / 5

Total

14

/

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 identifies a distinct niche and a clear purpose, but it names only one semi-concrete action and omits any explicit "when to use" trigger guidance. Restating the node's concrete behaviors and adding a "Use when..." clause with natural synonyms would raise specificity, trigger quality, and completeness together.

Suggestions

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

Name the node's concrete behaviors in the description (merge conflict resolution, CI repair, addressing review comments, enabling automerge) instead of the generic "polish a PR".

Include natural user phrasings such as "pull request", "address review comments", and "get the PR green" so the skill triggers on how users actually ask.

DimensionReasoningScore

Specificity

The only capability stated is "polish a PR toward merge readiness" — a single semi-concrete action — while the concrete behaviors the node performs (conflict resolution, CI repair, review-comment handling, automerge) appear only in the body, so coverage is not comprehensive.

3 / 5

Completeness

The "what" is clear ("polish a PR toward merge readiness through the OmniMarket runtime adapter"), but there is no "Use when..." clause or equivalent trigger guidance — "Use to..." restates the what rather than stating when to invoke it, capping completeness at 3.

3 / 5

Trigger Term Quality

"PR", "polish", and "merge readiness" are relevant natural terms, but common variations users would say — "pull request", "review comments", "CI", "get ready to merge" — are missing.

3 / 5

Distinctiveness Conflict Risk

References to "node_pr_polish" and the "OmniMarket runtime adapter" carve out a clear niche with only minor overlap risk against generic PR-review/merge-readiness skills, though the absence of explicit trigger phrases keeps it below a 5.

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

src/omnimarket/adapters/codex/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.