oss-maintainer

Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/oss-maintainer/SKILL.md

Quality

Content

78%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 an exceptionally lean, well-structured set of maintainer rules with strong validation gates in the merge and release workflows. Its main weakness is actionability: much of the guidance is stated as principles rather than concrete, copy-paste commands or complete examples.

Suggestions

Add a few concrete command examples for the most common actions (e.g. a sample `gh pr list --search` invocation, a merge-gate shell snippet that captures `$?`).

Provide one short fail-before/pass-after regression-test template to make the 'every fix carries a test' rule immediately executable.

Consider a minimal close-with-reopen-door message template so the communication guidance is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Lean throughout: every line is a distilled failure-lesson with no padding, no explanation of concepts Claude already knows, and no tutorial fluff about what an issue or PR is.	5 / 5
Actionability	Guidance is concrete and executable in places (gh pr list, Co-authored-by, pytest \| tail, capture $?) but most of it is principle-level directive prose rather than copy-paste commands or complete examples covering common cases.	3 / 5
Workflow Clarity	Sequenced workflows with explicit validation gates are present (run full gates before bumping versions; merge only on structural check; validate built release like a skeptic), with only minor checkpoint gaps in the triage/close flow.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no bundle files to over-split; the body is a single self-contained overview that navigates cleanly by section, appropriate for a guidance skill needing no external references.	5 / 5
	Total	17 / 20 Passed

Description

50%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 vividly conveys the maintainer persona and concrete duties but omits any explicit 'Use when...' trigger guidance, which is the rubric's most weighted completeness requirement. Trigger-term naturalness is also moderate rather than comprehensive.

Suggestions

Add an explicit trigger clause such as 'Use when maintaining an open-source project — triaging issues, reviewing community PRs, cutting releases, or handling CI.'

Surface natural user phrases ('maintain a repo', 'review pull requests', 'cut a release', 'handle stale issues') so the skill triggers on how users actually ask.

Tighten the persona-flavored language slightly to free room for concrete trigger keywords and file/extension cues.

Dimension	Reasoning	Score
Specificity	Lists several concrete maintainer actions (triage to root cause, absorb community PRs, gate merges, ship releases, thank contributors), with minor coverage gaps around specific artifacts like changelog formats or CI tooling names.	4 / 5
Completeness	The 'what' is richly described but there is no 'Use when...' clause or equivalent trigger guidance telling Claude when to invoke this skill, which caps completeness well below the explicit-when anchors.	2 / 5
Trigger Term Quality	Contains relevant domain terms (issues, PRs, releases, CI, triage) but lacks the natural trigger phrases a user would actually say (e.g. 'maintain', 'open-source project', 'review PRs') and misses common synonyms.	3 / 5
Distinctiveness Conflict Risk	The open-source maintainer-loop framing is a clear niche with distinct triggers, with only minor overlap risk against general git/code-review skills.	4 / 5
	Total	13 / 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: debpalash/OmniVoice-Studio
Path: skills/oss-maintainer/SKILL.md
Commit: 98c9e68

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.