blackbox

Delegate coding tasks to the Blackbox AI multi-model CLI.

Quality

64%

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 ./optional-skills/autonomous-ai-agents/blackbox/SKILL.md

Quality

Content

76%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 highly actionable with concrete, copy-paste-ready commands and well-organized sections, but it lacks explicit verification checkpoints for destructive code-modifying workflows, which limits workflow clarity.

Suggestions

Add a verification step to long-running/destructive workflows, e.g. after task completion run 'git diff' and the project's test suite before reporting success.

Tighten the intro and Multi-Model Mode paragraphs to remove explanatory prose Claude can infer, improving token efficiency.

Consider splitting the full Key Flags / Session Commands tables into a reference file to keep SKILL.md a leaner overview.

Dimension	Reasoning	Score
Conciseness	The body is largely lean command/flag examples with little padding, though the intro paragraph and Multi-Model Mode prose could be trimmed slightly; it is efficient with minor over-explanation rather than fully lean (5).	4 / 5
Actionability	It provides copy-paste-ready terminal/process invocations covering one-shot, background, checkpoint-resume, PR review, and parallel-work cases, with concrete flags and settings examples matching the fully-executable anchor.	5 / 5
Workflow Clarity	Sequences (background start→monitor→submit→kill, checkpoint resume) are clearly listed, but coding tasks modify code destructively and there is no explicit validation/verification checkpoint (e.g. run tests, review git diff), which caps this at 3.	3 / 5
Progressive Disclosure	No bundle files exist and all content lives inline under clear section headers with easy navigation; because the body exceeds ~50 lines it is good structure rather than the minimal-file 5.	4 / 5
	Total	16 / 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 clearly states what the skill does and names a specific product, giving it reasonable distinctiveness, but it omits any explicit "Use when..." trigger guidance and offers only one concrete action with limited keyword variation.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when delegating coding tasks to a multi-model CLI or when you want multiple LLMs to compete on an implementation.'

Expand the action list beyond 'Delegate' to mention specific capabilities like one-shot tasks, background long-running tasks, checkpoint resume, and multi-model judged runs.

Include natural user-facing synonyms (e.g. 'coding tasks', 'code generation', 'implementation', 'code review') to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("coding tasks", "Blackbox AI multi-model CLI") with one concrete action ("Delegate coding tasks"), matching the 1-2-actions anchor; it does not list several specific actions, so it is not a 4.	3 / 5
Completeness	It gives a clear "what" (delegate coding tasks to Blackbox AI) but has no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Includes relevant keywords ("coding tasks", "Blackbox AI") but misses common variations or synonyms a user might naturally say, fitting the some-relevant-keywords anchor rather than good coverage.	3 / 5
Distinctiveness Conflict Risk	Naming the specific Blackbox AI product gives it a clear niche, but the metadata lists related coding-agent skills (claude-code, codex) creating minor overlap risk, so it is mostly distinct rather than minimal-conflict (5).	4 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/autonomous-ai-agents/blackbox/SKILL.md
Commit: 6680afb

Reviewed: about 3 hours 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.