← The Index  /  devtools
Scored by model · 3 samples, median · No human review
Rank 168 of 173 · clearer than 2% of the index, 0% of devtools · Reviewed 2026-11-02 · contested

Skepagent

skepagent.com  ·  devtools
49
GRADE D
BAND 38–60

What their homepage claims

“Skep — Cross-device collaboration for AI coding agents”

What that means

Skep provides a way to coordinate AI coding agents across devices in live sessions.

Verdict

The headline gives a vague sense of product scope and lacks a plainly named product category; overall clarity is moderate but the page offers little measurable proof or strong CTAs.

What to fix first

Ranked by what each change is worth on the composite — the gap to the next rung of the ladder times the dimension’s weight. Computed from the scores, not written by the model; the model’s sentence under each is the action.

  1. 1Clarity quick win 50 → 65+4.5

    Use a concrete product noun in the headline that names a product category Skep offers, e.g., 'Skep Live Coding Sessions'.

  2. 2Specificity needs a fact 65 → 80+3

    Add a concrete, verifiable metric tied to a user outcome (e.g., time saved, sessions completed) to reach a higher score.

  3. 3Jargon-free quick win 65 → 80+3

    Simplify or remove multiple buzzwords and define actions in plain language.

All three together: 49 → 60. Every dimension one rung up: 64 (grade C). Ceiling is 95.

A plainer headline

Theirs
“Skep — Cross-device collaboration for AI coding agents”
Index’s suggestion
“Skep coordinates AI coding agents across devices in live sessions.”

Built only from facts already on the page — not the company’s words. Shown so the gap between what was written and what could have been written is concrete rather than a number.

Where the score comes from

Five dimensions on one ladder — 5 · 20 · 35 · 50 · 65 · 80 · 95 — weighted clarity 30%, specificity 20%, jargon 20%, proof 15%, call to action 15%. For each: the rung the page matched, the words that drove it, and what would reach the next rung. Full rubric →

Clarity30% 50

The headline mentions collaboration across devices but does not name a concrete product category; it remains abstract.

Skep — Cross-device collaboration for AI coding agents

Next rungUse a concrete product noun in the headline that names a product category Skep offers, e.g., 'Skep Live Coding Sessions'.

Specificity20% 65

No measurable outcomes or numbers tied to an outcome appear on the page.

Scored from the page as a whole; no single line was cited.

Next rungAdd a concrete, verifiable metric tied to a user outcome (e.g., time saved, sessions completed) to reach a higher score.

Jargon-free20% 65

Uses multiple technical terms (orchestrator, TUI, briefs, roles, skill, protocol) that raise the abstraction level.

Orchestrator /orchestrate auto|confirm|off|new . Default is auto.

Next rungSimplify or remove multiple buzzwords and define actions in plain language.

Proof15% 5

No named customers, no verifiable numbers tied to outcomes; only generic claims.

Illustrative session. Repo names, devices and output are examples, not measurements.

Next rungShow a named user case or a measurable result.

Call to action15% 50

No strong, explicit next-step CTA aligned to a clear product promise; the page uses commands rather than standard CTAs.

Join from another device

Next rungProvide a clear, low-friction action like Start or Try now under a concrete promise.

Evidence

Skep — Cross-device collaboration for AI coding agentsInitial headline used to determine clarity and product scope.
One master, many peersShows a concrete workflow element but not a product noun.
What the scorer was given first 1,500 characters of the homepage text — check the quotes yourself
Skep — Cross-device collaboration for AI coding agents
Skip to content
@skepagent/skep v0.2.0
Your agents, on every device, in one live session.
Cross-device collaboration for AI coding agents via live join-code sessions. Each peer runs its own agent — Claude Code, Codex, Pi, and more.
$ npm install -g @skepagent/ [email protected]
Copy
Start in 3 steps
View on npm
Apache-2.0 · Node.js ≥ 22.12 · macOS & Linux · bin: skep
One master, many peers
Start a session, peers join with a code, and work flows between devices. Each peer runs an AI coding agent in its own repo.
/orchestrate
auto
confirm
off
↻ Replay
$ skep
> /start
join code 7391-4820-1940 · 192.168.1.20:7419
+ device, server, ios, android, h5 joined
> /orchestrate auto
→ split into briefs, dispatched to peers
> /orchestrate confirm
? proposed briefs, waiting for your confirm
> /orchestrate off
→ no auto-split, you route work yourself
✓ 5 peers reported back
✓ summary received · changed files listed
Illustrative session. Repo names, devices and output are examples, not measurements.
Up in three steps
Run Skep inside any git repository on each device.
Start a session
On the master device, run skep and start a session. You get a join code and an address.
/start Copy
Join from another device
In the peer TUI, /join with the code and address. Any repo checkout works. Optional --role if using a skill.
/join 7391-4820-1940 192.168.1.20:7419 Copy
Hand out the work
Let the orchestrator split work ( auto / confirm / off ), or send 

How this compares

2%of the index scores lower
-19vs index mean (68)
-18vs devtools mean (67)
-20vs median (69)
100%of headline words survive
3×independently scored

Strongest: Specificity 65. Weakest: Proof 5. The 3 passes disagreed by 21 points, so treat this score as contested. The band 38–60 is where a re-score of this unchanged page would most likely land: on 42 dry re-scores (12 Oct 2026) the median move was 6 points and one in four moved more than 10. A grade only changes when a new score clears the boundary by 5.

Nothing struck

No word in the headline itself was judged empty, yet jargon-free scores 65: the scorer found generic phrasing further down the page. Uses multiple technical terms (orchestrator, TUI, briefs, roles, skill, protocol) that raise the abstraction level.

Share this rating

Badges are issued to grades A and B. The share card for this page shows the headline with its jargon struck through; paste the URL anywhere that unfurls links.

Provenance

Scored from the live homepage on 2026-11-02 by gpt-5-nano, 3 independent passes, median taken. Page snapshot d03032027efc. Rubric 7329c240 (current; what it says). No person reviewed or edited this score. If the rubric and the score disagree, the rubric wins and the page is re-scored — not hand-corrected. Re-scored when the homepage text changes.