CtrlK
BlogDocsLog inGet started
Tessl Logo

hyperflow-plan

Hyperflow planning phase. Use when a request needs shaping before code — a rough prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. Verbs like plan, design, brainstorm, explore, "should we", "what's the best way to", scope, decompose, "plan out", "break down", "enhance this prompt". Thinking, not building. Writes an optional spec to .hyperflow/specs/<slug>.md and a task file to .hyperflow/tasks/<slug>.md, then hands off to hyperflow-dispatch.

76

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exceptionally lean, well-sequenced planning workflow with concrete thresholds, file artifacts, gates, and mandated verification. Its one gap is a handful of unresolved references — the hyperflow doctrine, AskUserQuestion gates, and the design/Motion/mobile 'standards' are invoked without any pointer to their location, leaving the executor to hunt for them.

Suggestions

Name where the hyperflow doctrine and the 'matching standards' (design system, Motion language, mobile device matrix) live — a path or one-line pointer per item — so the executor doesn't have to discover them.

Show one worked example of a Batches table row (role, files, complexity, acceptance criteria, commit stub) so the task-file format is unambiguous on first use.

Briefly state how the <slug> is derived from the request, since both output paths and the handoff depend on it.

DimensionReasoningScore

Conciseness

Lean and efficient: the 24-line body assumes competence, explains nothing Claude already knows, and packs dense, load-bearing specifics ('role · task · context · constraints · output spec', '>5 files, >500 LOC, 2+ subsystems, or >10-min review'). Every token earns its place — the 5 anchor; not the 4 anchor, which reserves room for trimmable over-explanation.

5 / 5

Actionability

Mostly executable guidance: exact write paths (.hyperflow/specs/<slug>.md, .hyperflow/tasks/<slug>.md), a fully enumerated task-file layout (status table → Goal → Why → ... → commit stub), quantified split thresholds, and a literal output line to print. It falls short of fully copy-paste-ready because a few anchors are named but not resolved — 'ground the design in the matching standards (...the design system, the Motion language...)', 'Follow the hyperflow doctrine', and AskUserQuestion gates give no pointer to where those standards/doctrine live.

4 / 5

Workflow Clarity

A clearly numbered 1–6 sequence with explicit skip conditions, human approval gates ('with approval per section'), per-batch acceptance criteria, and the hard rule 'Always include a concrete verification plan' — explicit checkpoints throughout. No destructive/batch operations exist here (writes are confined to .hyperflow/), so no feedback-loop cap applies; matches the 5 anchor rather than the 4 anchor, whose checkpoints are only 'mostly' present.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), and the body is under 50 lines with no need for external references — well-organized sections (Steps, Rules) suffice. Per the rubric's simple-skill guidance this is the 5 case: everything is appropriately inlined in one navigable, single-level document.

5 / 5

Total

19

/

20

Passed

Description

96%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 description: it states concrete actions with file artifacts, an explicit 'Use when' clause with varied trigger phrases, and clear suite identity. The only weakness is that its broadest trigger verbs (plan, design, brainstorm, explore) overlap with generic planning requests that aren't part of the hyperflow workflow.

DimensionReasoningScore

Specificity

Lists multiple concrete actions with concrete artifacts and paths — 'rewrite it into its strongest form', 'Writes an optional spec to .hyperflow/specs/<slug>.md and a task file to .hyperflow/tasks/<slug>.md', 'hands off to hyperflow-dispatch' — comprehensive coverage of the planning phase's behaviors. Fits the 5 anchor ('lists multiple specific concrete actions') and not the 4 anchor, which expects minor coverage gaps.

5 / 5

Completeness

Explicitly answers both: what ('Writes an optional spec... a task file... then hands off to hyperflow-dispatch') and when ('Use when a request needs shaping before code — a rough prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose'). This mirrors the 5 anchor's example structure exactly; the 4 anchor requires the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms and quoted user phrasings: 'plan, design, brainstorm, explore, "should we", "what's the best way to", scope, decompose, "plan out", "break down", "enhance this prompt"'. Matches the 5 anchor's standard of natural terms plus variations; no common phrasing for this intent is obviously missing.

5 / 5

Distinctiveness Conflict Risk

The 'Hyperflow' framing and the handoff to hyperflow-dispatch carve a clear niche, but the trigger verbs ('plan, design, brainstorm, explore') are extremely common words that overlap with generic planning/design skills, creating minor conflict risk. Mostly distinct per the 4 anchor; not 5 because the broad verb list could fire for other planning skills outside the hyperflow suite.

4 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jeremylongshore/tons-of-skills-marketplace
Reviewed

Table of Contents

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.