clonedeps

Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug library implementation details, or make core dependency repos locally readable. Do not use for ordinary API/docs questions where @librarian is enough.

Quality

90%

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

Quality

Content

81%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.

A well-structured, actionable workflow skill with explicit verification gates and error-recovery loops. Its main weaknesses are minor: the core git clone commands are described rather than given as exact copy-paste commands, and the long inline librarian prompt plus a hardcoded date in the JSON example add token weight that could be trimmed or moved to a reference file.

Suggestions

Replace the procedural clone description with exact copy-paste git commands (e.g., `git clone --depth 1 <repoUrl> <tmpDir>` and `git fetch --depth 1 origin <ref>`) so the central action is fully executable.

Trim the explanatory prose around the ignore-file blocks and use placeholders (e.g., `<timestamp>`, `<version>`) instead of the hardcoded `2026-05-12T00:00:00.000Z` date and `1.3.17` version numbers in the JSON example to remove time-sensitive clutter.

Consider extracting the long Step 2 librarian prompt and/or the full JSON manifest example into a `references/` file linked from the main body, shortening the SKILL.md overview while keeping the workflow navigable.

Dimension	Reasoning	Score
Conciseness	Largely lean operational guidance (exact ignore blocks, safe-name rules, git sequence, JSON manifest) rather than concept padding, but the inline librarian prompt is long and the JSON example hardcodes a specific date ('2026-05-12T00:00:00.000Z') and version numbers, which is minor time-sensitive clutter. Not 5 because of these trims; not 3 because there is little conceptual fluff.	4 / 5
Actionability	Provides copy-paste-ready artifacts (managed `.gitignore`/`.ignore` blocks, full JSON manifest example, AGENTS.md template, safe-name derivation with a worked example), but the core clone step is described procedurally ('Clone without submodules/recursive behavior', 'Prefer shallow fetch/clone where practical') rather than as exact commands. Not 5 because the central git clone commands are not copy-paste ready.	4 / 5
Workflow Clarity	Seven clearly numbered steps plus a Cleanup section, with explicit validation gates (Step 3 'Verify and Confirm the Plan' using `git ls-remote` and user confirmation; Step 5 remote-URL mismatch → 'stop and ask whether to clean/reclone') and feedback loops (clone into temp dir then move on success, remove failed temp clones, write state for partial successes).	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections (Workflow → Steps 1–7, Cleanup) with no nested or broken references, and the only paths mentioned are project files the skill manages. Not 5 because at ~240 lines it is a single monolithic file where the long inline librarian prompt and full manifest example could be split into a reference, and the under-50-lines exception does not apply.	4 / 5
	Total	17 / 20 Passed

Description

100%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.

A strong description that clearly states what the skill does, gives multiple natural trigger phrases for when to use it, and draws an explicit negative boundary against the overlapping @librarian skill. It uses the expected imperative/third-person voice with no first- or second-person phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Clone important project dependency source code into an ignored local workspace', 'inspect library internals', 'understand SDK/framework behavior from source', 'debug library implementation details', 'make core dependency repos locally readable' — giving comprehensive coverage comparable to the score-5 anchor.	5 / 5
Completeness	Explicitly answers what ('Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals') and when ('Use when the user asks to clone dependencies...') with concrete trigger phrases, plus a negative boundary ('Do not use for ordinary API/docs questions where @librarian is enough').	5 / 5
Trigger Term Quality	Natural phrases a developer would actually say are well covered with synonyms — 'clone dependencies', 'inspect dependency/source internals', 'understand SDK/framework behavior from source', 'debug library implementation details', 'make core dependency repos locally readable' — matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche (cloning dependency source into a local ignored workspace for inspection) and explicitly distinguishes itself from @librarian via 'Do not use for ordinary API/docs questions where @librarian is enough', minimizing conflict risk.	5 / 5
	Total	20 / 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: alvinunreal/oh-my-opencode-slim
Path: src/skills/clonedeps/SKILL.md
Commit: 3222930

Reviewed: 1 day 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.