CtrlK
BlogDocsLog inGet started
Tessl Logo

agenta-apps

How to give the person a small interactive page in the drive: a board, checklist, queue, form, table or dashboard. Read it when the ask is for something to look at and touch rather than a reply. Covers picking a starter with create_app, the app folder layout, and the window.agenta bridge for hand-written apps.

70

Quality

88%

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

88%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.

Excellent instruction-only skill body: dense, assumption of competence, exact commands and schemas, explicit error-recovery loops, and a well-organized single-file structure. The only refinements are a worked example for the hand-written app path and possibly splitting the bridge API / registry conventions into reference files.

DimensionReasoningScore

Conciseness

Lean and dense throughout: 'Paths are relative to index.html and cannot leave the folder', 'Writes carry If-Match automatically'. No padding, no explanation of concepts Claude already knows (no 'what is a kanban' or library tutorials); every token earns its place.

5 / 5

Actionability

Highly concrete: exact command 'create_app(starter, "apps/<slug>")', exact manifest keys, fully enumerated bridge API (agenta.fs read/readJSON/write/writeJSON/list/exists/stat/remove), exact kit class names, error codes and a conflict-recovery protocol. Minor gap: no worked app.json/index.html example for the hand-written fallback path, keeping it below fully copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

Clear numbered sequence (check existing apps -> pick starter -> custom fallback -> reply with card), explicit feedback loops ('on conflict, re-read the file and reapply the change once'), a pre-creation registry merge check, and checklist rules with stop conditions ('If the file already exists with a different version, stop and say so'). Validation and recovery are explicit throughout.

5 / 5

Progressive Disclosure

No bundle files exist; the skill is a single ~85-line file with well-labeled sections (When, First, Folder, Bridge, Custom app rules, Starters, After, Agent-level layout) and no nested or buried references. It exceeds the under-50-lines bar for an unconditional 5, and the bridge API details and agent-level registry rules could plausibly live in separate reference files, so anchor 4 fits.

4 / 5

Total

18

/

20

Passed

Description

83%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 that states a concrete what, an explicit when with natural trigger terms, and a distinct technical niche. It is specific and unpaddinged; only minor coverage gaps in capability enumeration and a few missing synonym terms keep individual dimensions at 4.

DimensionReasoningScore

Specificity

Names the domain ('small interactive page in the drive') and several concrete capabilities: 'a board, checklist, queue, form, table or dashboard', 'picking a starter with create_app', 'the app folder layout', 'the window.agenta bridge'. Falls short of 5 only because coverage has minor gaps (app updates, registry, access modes are unmentioned).

4 / 5

Completeness

Explicitly answers both: what ('give the person a small interactive page... Covers picking a starter with create_app, the app folder layout, and the window.agenta bridge') and when ('Read it when the ask is for something to look at and touch rather than a reply'), with concrete trigger artifacts named. Both are clear and concrete, matching anchor 5.

5 / 5

Trigger Term Quality

Good natural-term coverage — 'board', 'checklist', 'queue', 'form', 'table', 'dashboard' — plus an explicit trigger clause ('Read it when the ask is for something to look at and touch rather than a reply'). A few common variations ('app', 'to-do') are missing, keeping it below the comprehensive synonym-level anchor 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche — drive-hosted interactive apps built via create_app and the window.agenta bridge — with distinct technical triggers. Generic artifact words ('form', 'table') create minor overlap risk with document or dataviz skills, so it sits at anchor 4 rather than 5.

4 / 5

Total

17

/

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
Agenta-AI/agenta
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.