overnight-development

Automates software development overnight using git hooks to enforce test-driven Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Quality

28%

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 ./plugins/productivity/overnight-dev/skills/overnight-development/SKILL.md

Quality

Content

22%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a generic template filled with placeholder steps and outputs rather than skill-specific guidance; it provides no concrete commands and does not describe the actual overnight-development/TDD workflow it claims to automate. Bundle references exist but are poorly wired into the body.

Suggestions

Replace the generic six-step Instructions with the real workflow: how the git hooks are installed, what TDD checks they run, and how failures are handled (or point to references/workflow.md).

Add concrete, executable guidance — actual hook scripts or commands (e.g. the pre-commit/pre-push test command) — so the skill is actionable rather than descriptive.

Link the existing workflow.md from the body (it is currently unlinked) and clearly signal each reference's purpose, since workflow.md is the core reference but is not mentioned.

Dimension	Reasoning	Score
Conciseness	The body is short and does not pad with concepts Claude already knows, but it is hollow boilerplate ("Execute skill workflow systematically", "Validate outputs meet requirements") so most tokens do not earn their place, placing it between lean (3) and padded (1) at 2.	2 / 3
Actionability	Instructions are entirely abstract ("Gather required inputs and parameters", "Execute skill workflow systematically") with no concrete code, commands, or specifics, matching the vague/describes-rather-than-instructs anchor at 1.	1 / 3
Workflow Clarity	The six-step list is generic and does not describe the actual claimed workflow (overnight TDD via git hooks); there is no real sequence and no validation checkpoints for the destructive/batch operations git hooks imply, matching the unclear/missing-sequence anchor at 1.	1 / 3
Progressive Disclosure	One-level-deep references to errors.md and examples.md exist and are real files, but they are weakly signaled and the key workflow.md file is never referenced from the body despite existing, so it is structured but not well-organized enough for 3.	2 / 3
	Total	6 / 12 Passed

Description

35%

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 names a real niche (overnight TDD via git hooks) but is malformed: the capability sentence is cut off and the trigger clause is generic placeholder text rather than natural user keywords. It conveys intent but fails to give a usable trigger.

Suggestions

Complete the truncated capability sentence (e.g. "enforce test-driven development") and list concrete actions rather than leaving the thought unfinished.

Replace the placeholder trigger ("Use when appropriate context detected...") with natural phrases users would say, such as "Use when running unattended overnight builds, setting up pre-commit/pre-push hooks, or enforcing TDD before commits".

Tighten the broad opening ("Automates software development") to the specific niche so the skill is clearly distinguishable from general development skills.

Dimension	Reasoning	Score
Specificity	The description names a domain and some actions ("Automates software development overnight using git hooks to enforce test-driven"), but the action list is truncated mid-sentence and not comprehensive, so it does not reach the multiple-concrete-actions anchor at 3.	2 / 3
Completeness	It states a partial "what" but the "when" is only implied via a placeholder rather than an explicit trigger, so it sits at the has-what-but-when-implied anchor (2) rather than the explicit-trigger anchor (3).	2 / 3
Trigger Term Quality	The trigger clause is generic boilerplate ("Use when appropriate context detected. Trigger with relevant phrases based on skill purpose") with no natural keywords a user would actually say, matching the no-natural-keywords anchor at 1.	1 / 3
Distinctiveness Conflict Risk	"software development overnight using git hooks" is somewhat specific, but "automates software development" is broad and could overlap with general dev skills, matching the somewhat-specific-but-could-overlap anchor at 2.	2 / 3
	Total	7 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/productivity/overnight-dev/skills/overnight-development/SKILL.md
Commit: 15940c5

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.