CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ipollowork-design-studio

Route iPolloWork Design sessions by category and author other designs.

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./examples/plugin-packages/design-agent/skills/ipollowork-design-studio/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 an exemplary lean router with well-signaled, verified one-level-deep references and disciplined token efficiency. Its weakness is over-compression: key 'Other' workflow steps and validation checkpoints are named in telegraphic prose rather than given as an executable sequence, so following them depends on interpreting references rather than acting directly.

Suggestions

Unpack the telegraphic 'Other' section into a short numbered sequence (read source and tokens, locate stale selection, apply Other rules, run acceptance/export checks, disclose unverified results) so the order and checkpoints are explicit.

State in one line each what 'Other acceptance' and 'affected editing/interaction checks' concretely involve, or point to the exact section in design-other.md that defines them instead of naming them abstractly.

Clarify compressed clauses like 'No replacement project, preview host or application-source edits' and 'assets follow shared media plan/check' — either spell out the prohibited actions or link the specific guideline section being invoked.

DimensionReasoningScore

Conciseness

The ~25-line body contains zero padding and zero explanation of concepts Claude already knows — every sentence is a directive ('Preserve --ipw-* tokens/variable bindings', 'No replacement project, preview host or application-source edits'). This matches anchor 5 ('lean and efficient; assumes Claude's competence; every token earns its place'); there are no unnecessary explanations that would pull it to anchor 4.

5 / 5

Actionability

There are concrete elements — the routing table with real links, exact paths ('design/<session-id>/', 'design-tokens.css'), and specific invariants ('--ipw-* tokens', 'component IDs, editable/locked markers'). But much of the 'Other' section is compressed to near-opacity ('Apply Other acceptance, affected editing/interaction and requested supported export checks'; 'assets follow shared media plan/check') — pointers whose execution requires chasing multiple referenced files, matching anchor 3 ('some concrete guidance but incomplete; missing key details') rather than anchor 4's mostly-executable guidance.

3 / 5

Workflow Clarity

An implicit sequence exists (hand off before reads/edits, then read the injected source, then apply rules and acceptance checks, and 'disclose unverified results' acts as a validation/disclosure checkpoint), and 'Stale selection requires a new locator before edits' is a conditional guard. But the steps are embedded in prose rather than sequenced, and checkpoints like 'Apply Other acceptance ... checks' are named, not specified — anchor 3 ('steps present but checkpoints missing or implicit'), not anchor 4's clear sequence with most checkpoints explicit.

3 / 5

Progressive Disclosure

The body is a true overview/router: it keeps only the routing table and the 'Other' summary inline, and points to verified, one-level-deep bundle files with clearly signaled purpose ('Read only affected [Other rules](references/design-other.md) for targeted/theme edits', 'Creation/structural work uses applicable [Design authoring](references/design.md) and [Shared guidance](references/shared-guidelines.md) sections'). All three referenced files exist in references/ with matching sections, and 'Resolve installed links once; report missing references' handles link failures — matching anchor 5.

5 / 5

Total

16

/

20

Passed

Description

46%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 concise and names its domain plus two functions, but it omits any 'use when' trigger guidance and contains almost no natural keywords — users asking for a poster, slides, or a website would not match this text. The distinctive product name offsets conflict risk with unrelated skills, though overlap with its own sibling skills remains.

Suggestions

Add an explicit 'Use when...' clause listing the natural category terms users actually say (e.g., 'Use when the user asks to create or edit websites, apps, posters, cards, articles, reports, slides, or videos').

Replace internal jargon like 'Route iPolloWork Design sessions by category' with user-facing verbs and nouns (e.g., 'Routes design work by type: websites, posters, reports, slides, video').

Briefly demarcate the boundary from sibling design skills (e.g., note that this skill routes to specialized design skills and directly handles other/miscellaneous design work).

DimensionReasoningScore

Specificity

The description names its domain ("iPolloWork Design sessions") and two actions — "Route ... sessions by category" (concrete) and "author other designs" (generic). It matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive): it is above anchor 2 because routing-by-category is a real action, not purely generic processing, but below anchor 4 because "author other designs" names no specific actions and coverage of what authoring involves is absent.

3 / 5

Completeness

The 'what' is stated clearly enough (route sessions by category; author other designs), but there is no 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 3 per the judging guidelines. It is not 2 because the 'what' is not vague — two distinct functions are named — and not 4 because 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

The only natural user-facing term is "design/designs"; "Route ... sessions by category", "manifest category", and "author" are internal jargon a user would never say. All natural trigger phrases for the routed categories (poster, cards, website, app, article, report, slides, video) are missing, which fits anchor 2 ('one or two generic keywords; missing the natural phrases users say') better than anchor 3, which expects a domain keyword like 'PDF' — here even the domain term is diluted by jargon.

2 / 5

Distinctiveness Conflict Risk

The product-specific name "iPolloWork" establishes a clear niche with minimal conflict against unrelated skills, matching anchor 4. It is not 5 because the bare word "design/designs" still overlaps with the several closely related sibling design skills this router hands off to (web, graphics, editorial, presentations), and the description does not demarcate which design requests belong here.

4 / 5

Total

12

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 suspicious

Warning

Total

15

/

16

Passed

Repository

Devin-AXIS/iPolloWork

Path

examples/plugin-packages/design-agent/skills/ipollowork-design-studio/SKILL.md

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.