plan

Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. One chain-starter that amplifies the prompt, designs the approach, and decomposes it into a batched task file, skipping whichever phases the request doesn't need, then STOPS at a build-location gate (build here, hand off to another session, or just keep the plan). Plan never implements. Trigger with /hyperflow:plan, "design this", "plan this", "decompose this", "how should we", "what's the best way to", "break this down", "enhance this prompt".

Quality

88%

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.

The content is a thorough, highly actionable planning procedure with explicit sequencing, validation checkpoints, and feedback loops, and it uses real one-level references. Its weakness is conciseness: the body is long and dense with internal jargon that could be tightened or offloaded to referenced files.

Suggestions

Tighten the densest procedural sections (the Per-Step Agent Map and Step 7/9 narrative) by moving rule citations (DOCTRINE rule numbers, §12.x) and low-frequency edge-case detail into a referenced file, keeping only the load-bearing sequence inline.

Define or link the P1–P5 / layer-numbering shorthand once up front (or via the latency-patterns.md reference) so the body can refer to it without repeating the definitions inline.

Collapse the Approval Gates table and the Step 12 gate-text blocks into a single referenced 'gates.md' file, leaving a one-line summary per gate in the body to reduce token weight.

Dimension	Reasoning	Score
Conciseness	The body avoids padding with concepts Claude already knows, but it is a very long, procedurally dense ~260-line document heavy with internal jargon (P1–P5, DOCTRINE rule numbers, §12.2.8) that could be tightened; it is mostly efficient but carries notable length that could be reduced.	3 / 5
Actionability	Highly executable: exact dispatch strings, concrete file paths, literal AskUserQuestion gate text blocks, a runnable python3 resolve-mode.py command, exact mv renames, and Skill invocation args give copy-paste-ready guidance covering the common cases.	5 / 5
Workflow Clarity	Steps 0–12 are clearly sequenced with a per-step agent map, an approval-gates table, per-sub-phase Reviewer checkpoints, NEEDS_FIX/retry→escalate→abort feedback loops, and a dedicated error-handling table, satisfying the explicit-checkpoint top anchor.	5 / 5
Progressive Disclosure	Real, well-signaled one-level-deep references (references/prompt-rubric.md and references/examples.md both exist and are linked, plus a Resources section of ../hyperflow/*.md pointers) with good sectioning, but a large amount of procedural detail is inlined in the main body rather than split into separate files.	4 / 5
	Total	17 / 20 Passed

Description

95%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 strong: it concisely states a distinct planning niche, names concrete actions, and pairs them with an explicit 'Use when' clause and a rich set of natural trigger phrases. The only minor gap is that the capability verbs lean slightly abstract rather than enumerating every concrete output.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("amplifies the prompt, designs the approach, and decomposes it into a batched task file", "STOPS at a build-location gate") but the verbs stay somewhat abstract rather than enumerating fully concrete outputs, sitting just below the comprehensive 5 anchor.	4 / 5
Completeness	Explicitly answers both what (amplify → design → decompose into a batched task file, then stop at a build gate) and when ("Use when a request needs shaping before any code is written" plus concrete trigger phrases), matching the top anchor.	5 / 5
Trigger Term Quality	A dedicated "Trigger with" line gives comprehensive natural phrases users would say ("design this", "plan this", "break this down", "how should we", "what's the best way to", "enhance this prompt") plus the slash command, covering synonyms.	5 / 5
Distinctiveness Conflict Risk	A clear niche — pre-code planning/decomposition that explicitly "never implements" and stops at a build-location gate — with distinct triggers and minimal overlap with build or execute skills.	5 / 5
	Total	19 / 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: 40 suspicious	Warning

	Total	13 / 16 Passed

Repository: jeremylongshore/tons-of-skills-marketplace
Path: plugins/ai-agency/hyperflow/skills/plan/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.