background

Use when the user wants to see, inspect, cancel, or prune background agents fired during prior chain runs. Read/manage `.hyperflow/background/registry.json` and the per-agent output buffers at `.hyperflow/background/<id>.md`. Standalone — never auto-invoked. Trigger with /hyperflow:background, "list background agents", "what's running in background", "cancel background agent", "show background result".

Quality

80%

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

61%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 highly actionable and well-structured with externalized doctrine, but loses points for redundant overview/flow/instructions sections and missing validation checkpoints on its destructive batch operations.

Suggestions

Collapse the redundant "Flow" and "Instructions" sections into a single sequenced procedure, and remove the "Output" section since it duplicates the Examples.

Add an explicit validation checkpoint before destructive batch operations — e.g. have `prune` list candidate buffers and a count for confirmation before running `find ... -delete`, and have `cancel --all` print the in-flight IDs before cancelling.

Replace the prose description of registry JSON mutation in `cancel`/`prune` with a concrete literal JSON edit example so the guidance is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tables and commands rather than concept explanations, but contains notable structural redundancy — the "Flow" and "Instructions" sections give near-identical 4-step summaries, "Overview" restates the intro, and "Output" restates the Examples — so it could be tightened.	3 / 5
Actionability	Provides concrete executable commands (e.g. `find .hyperflow/background/ -name "bg-*.md" -mtime +7 -delete`), exact output strings, and worked examples, with only minor gaps where registry JSON mutation and provider cancellation are described in prose rather than literal code.	4 / 5
Workflow Clarity	The Flow is clearly sequenced with a thorough error-handling table providing recovery (e.g. malformed registry → backup + recreate + continue), but the batch/destructive operations (`prune`, `cancel --all`) lack explicit pre-execution validation checkpoints, which caps this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	SKILL.md serves as an overview with one-level-deep, clearly signaled references ("Full doctrine: background-agents.md" and a Resources section), and the bulk doctrine is externalized; minor organization gaps remain from the inlined duplicate sections.	4 / 5
	Total	14 / 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.

The description is specific, trigger-rich, and clearly answers both what and when, with a distinct niche and minimal conflict risk. It is among the strongest examples on the rubric.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "see, inspect, cancel, or prune background agents" plus "Read/manage `.hyperflow/background/registry.json` and the per-agent output buffers" — covering the full lifecycle comprehensively, matching the anchor for multiple specific concrete actions.	5 / 5
Completeness	Explicitly answers both what ("Read/manage registry.json and output buffers") and when ("Use when the user wants to see, inspect, cancel, or prune background agents") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides natural user phrases ("list background agents", "what's running in background", "cancel background agent", "show background result") plus the /hyperflow:background command, giving comprehensive coverage of terms users would actually say.	5 / 5
Distinctiveness Conflict Risk	Targets a narrow niche (background agents from prior hyperflow chain runs) with specific file paths and distinct trigger phrases, making conflict with other skills minimal.	5 / 5
	Total	20 / 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
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
relative_links	Relative link issues: 4 suspicious	Warning

	Total	13 / 16 Passed

Repository: jeremylongshore/tons-of-skills-marketplace
Path: plugins/ai-agency/hyperflow/skills/background/SKILL.md
Commit: 88dcf65

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.