publish

Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its artifacts. Ship-only: never runs pre-publish-review or re-reviews merged code unless the user explicitly asks. Argument: <patch|minor|major|explicit-semver>. Triggers: publish, release, deploy, npm publish.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/publish/SKILL.md

Quality

Content

77%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 exceptionally executable and rigorously sequenced with validation and fail-closed loops appropriate to a batch release operation, scoring top marks on actionability and workflow clarity. Its weaknesses are token efficiency (heavy repetition of the same mandates across CRITICAL sections) and progressive disclosure (a monolithic single file with no bundle references).

Suggestions

Consolidate the four 'CRITICAL' preamble sections into a single completion-contract block; the ship-only, three-surfaces, Discord, and no-early-turn-end mandates repeat the same STOP-and-report rules multiple times and can be deduplicated to recover token budget.

Move the release-note style guide (Step 6 rules/examples) and the Discord message template (Step 7.5) into references/ files (e.g. references/release-notes.md, references/discord-announce.md) and link one level deep, keeping SKILL.md an overview.

Drop the dated incident narrative ('A prior session forgot this... That mistake is why this section exists') or relocate it to a deprecation/old-patterns note; time-sensitive rationale text competes with evergreen instructions for context.

Dimension	Reasoning	Score
Conciseness	The body is highly actionable and padded with strong assertions, but it repeats the completion/ship-only contract across multiple 'CRITICAL' sections, restates the same Discord and summary mandates several times, and includes a dated narrative ('A prior session forgot this'), which is mostly efficient yet noticeably over-emphasized for token budget.	3 / 5
Actionability	Every step ships copy-paste-ready, executable bash (gh workflow run, gh run view --json, npm view, gh release edit --notes-file) with concrete IDs, channel numbers, bot IDs, and a fully templated Discord message, covering the common release cases completely.	5 / 5
Workflow Clarity	A clearly sequenced Step 0-9 process with explicit validation checkpoints (run conclusion == success, gh release view resolves, npm view matches version), a five-item completion contract, and fail-closed feedback loops (re-validate, --log-failed on failure, stop-and-report) for this batch/destructive release operation.	5 / 5
Progressive Disclosure	All guidance lives inline in one ~470-line SKILL.md with no references/, scripts/, or assets/ bundle files and no section pointing to deeper materials; it is well-headed and navigable but content that could be split (release-note style guide, Discord template, stage table) is inlined rather than one level deep.	3 / 5
	Total	16 / 20 Passed

Description

78%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 strong on completeness and trigger quality, clearly stating what the skill does and when to invoke it with natural keywords and a scope guard. Specificity and distinctiveness are solid but not maximally comprehensive, as the action list is brief and the npm-release niche still brushes generic deploy/release skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('Publish oh-my-opencode to npm') and 1-2 concrete actions ('triggering the GitHub Actions publish workflow and verifying its artifacts') but stops short of listing the broader action set, matching the 'Names domain and 1-2 concrete actions' anchor rather than the more comprehensive score 4.	3 / 5
Completeness	Explicitly answers both what (publish to npm via the GitHub Actions workflow and verify artifacts) and when ('Triggers: publish, release, deploy, npm publish'), and clarifies scope ('Ship-only: never runs pre-publish-review... unless the user explicitly asks') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user-facing keywords ('publish, release, deploy, npm publish') plus the argument vocabulary (patch\|minor\|major); falls just short of the comprehensive synonym-and-extension coverage of score 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to a distinct npm/GitHub-Actions publish niche with explicit non-overlap guard ('Ship-only: never runs pre-publish-review'), with only minor overlap risk against generic release-related skills rather than the clear-niche minimal-conflict of score 5.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: code-yeongyu/oh-my-openagent
Path: .agents/skills/publish/SKILL.md
Commit: 6108673

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.