hyperflow

Use when applying Hyperflow's orchestration doctrine in Codex, Antigravity, Grok, or another single-agent surface. Auto-invoke for non-trivial engineering work: build, implement, add, refactor, debug, fix, review, audit, plan, scope, design, brainstorm, ship, or deploy. Trigger with /hyperflow:hyperflow, "use hyperflow", "apply the doctrine", or automatically on any task-shaped message.

Quality

75%

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/ai-agency/hyperflow/skills/hyperflow/SKILL.md

Quality

Content

63%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 routing doctrine with concrete mappings and templates, undermined by repeated model/effort-policy passages and broken external references. The content is genuinely useful but could be tightened and properly split across the referenced files.

Suggestions

State the 'current session model, no per-role model selection' and reasoning-effort (low/medium/high) rules once in the Reasoning Policy section and remove the duplicate mentions in the Codex and Grok sections.

Create the referenced 'DOCTRINE.md' and 'security.md' (or remove the references), and consolidate the host-specific subagent mapping tables into a clearly signaled one-level-deep reference file.

Add an explicit validation/feedback step (e.g., self-review -> fix -> re-review) to the dispatch and audit auto-chain sequence so the workflow checkpoints are concrete rather than implicit.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence with no basic-concept padding, but the 'current session model / no per-role model selection' rule and the low/medium/high reasoning-effort guidance are each repeated ~3 times across the Codex, Grok, and Reasoning Policy sections, which is more than minor redundancy.	3 / 5
Actionability	Provides concrete routing tables (user-says to run), role-to-subagent_type mappings, specific tool names ('multi_agent_v1.spawn_agent', 'spawn_subagent'), and a copy-ready chat-block fallback template, with only minor gaps where routed sub-skill workflows are referenced but not shown.	4 / 5
Workflow Clarity	The auto-chain section gives a clear sequenced flow (plan -> build-location gate -> dispatch -> audit/deploy gates) with explicit structural gates as checkpoints; validation is implicit via the audit step rather than a validate-fix-retry loop, leaving minor gaps.	4 / 5
Progressive Disclosure	Section and table structure is present, but the referenced 'DOCTRINE.md' and 'security.md' do not exist in the bundle, the references are inline rather than a clearly signaled navigation block, and the large host-specific mapping tables could reasonably live in separate reference files.	3 / 5
	Total	14 / 20 Passed

Description

87%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, trigger-rich description that clearly states what the skill does and when to use it, with broad natural-language keywords. Its main weakness is conflict risk: the catch-all 'any task-shaped message' and generic engineering verbs make it likely to compete with other general-purpose skills.

Suggestions

Tighten the trigger scope by narrowing 'automatically on any task-shaped message' to contexts where orchestration doctrine is actually needed, to reduce overlap with general coding skills.

Replace some generic verbs with doctrine-specific capabilities (e.g., 'route multi-step work through plan/dispatch/audit workflows') to sharpen specificity beyond common engineering verbs.

Add a one-line differentiator that distinguishes Hyperflow orchestration from a host's built-in multi-agent runtime so it is less likely to fire when native tooling already applies.

Dimension	Reasoning	Score
Specificity	Lists many concrete action verbs ('build, implement, add, refactor, debug, fix, review, audit, plan, scope, design, brainstorm, ship, or deploy'), but they are generic engineering verbs rather than domain-specific capabilities of the orchestration doctrine, leaving minor gaps versus a fully comprehensive anchor.	4 / 5
Completeness	Explicitly answers both 'what' ('applying Hyperflow's orchestration doctrine') and 'when' ('Use when applying...', 'Auto-invoke for non-trivial engineering work') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms and the slash command ('/hyperflow:hyperflow, use hyperflow, apply the doctrine') alongside the full verb vocabulary users would naturally say.	5 / 5
Distinctiveness Conflict Risk	The Hyperflow brand and named surfaces (Codex, Antigravity, Grok) carve a niche, but 'automatically on any task-shaped message' plus generic engineering verbs create real overlap with many general coding skills.	3 / 5
	Total	17 / 20 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/tons-of-skills-marketplace
Path: plugins/ai-agency/hyperflow/skills/hyperflow/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.