Tessl • The package manager for agent skills

The body is an exemplary instruction-only skill: terse, concrete, and fully actionable, with a complete verify-fix-reverify-save loop and explicit handling of revisions. No bundle files exist, and none are needed at this scope.

Dimension	Reasoning	Score
Conciseness	The body is a lean constraint spec — "Create one /workspace/<slug>.json file. JSON is the canonical deck" — with no padding and no explanation of concepts Claude already knows; every line is a rule the deck must satisfy, matching 'every token earns its place'.	5 / 5
Actionability	Fully executable guidance: a complete JSON template, exact field length limits ("Title: 1–200 characters. Front: 1–4,000. Back: 1–12,000."), exact escaping rules, and concrete copy-paste tool calls (verify_artifact(path="/workspace/<slug>.json", format="flashcards") and save_artifact(...)) covering both creation and revision cases.	5 / 5
Workflow Clarity	Clear multi-step sequence with an explicit validation checkpoint ("After verification returns status=\"verified\""), a feedback loop ("Fix all blocking findings together, rewrite the JSON once, and reverify"), a stop condition for persistent blockers, and a complete revision workflow (edit restored JSON from primary_path, write to expected_output_path, verify, save with artifact_id).	5 / 5
Progressive Disclosure	The skill is self-contained with no bundle files; content is organized into two well-signaled sections (## Contract, ## Verify and save) and nothing inlined belongs in a separate file, satisfying the well-organized self-contained case for full credit.	5 / 5
	Total	20 / 20 Passed

Description

53%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 states a single clear, concrete capability in appropriately terse third-person voice, and the flashcard/active-recall domain is largely distinctive. Its main weakness is the complete absence of 'when to use it' trigger guidance, which caps completeness and weakens trigger-term coverage.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for flashcards, a study deck, or memorization aids for active recall, or wants to review material with spaced repetition.'

Include natural synonyms and variations users would actually say — memorize/memorization, quiz cards, spaced repetition — to broaden trigger-term coverage.

Mention additional concrete actions the skill supports (e.g., 'create or revise JSON flashcard decks'), since the body covers revisions but the description only names creation.

Dimension	Reasoning	Score
Specificity	"Create strict JSON flashcard decks" names the domain (flashcards for active-recall study) and one concrete action, but there is no broader action list (create, revise, export, etc.), matching the score-3 anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. It is above a 2 because the action stated is concrete and specific, not generic.	3 / 5
Completeness	The description clearly answers 'what' ("Create strict JSON flashcard decks for active-recall study") but contains no 'when' clause — no 'Use when...' or equivalent trigger guidance — so completeness is capped at 3 per the judging guidelines and matches the score-3 anchor exactly.	3 / 5
Trigger Term Quality	Natural terms present include "flashcard decks", "study", and "active-recall", which users would say, but common variations and synonyms (memorize, memorization, quiz, spaced repetition, test prep) are missing — the score-3 anchor 'Some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	"flashcard decks" and "active-recall study" carve a mostly distinct niche unlikely to trigger the wrong skill, but with no trigger clause there is minor overlap risk with closely related skills (quiz or test-question generation, JSON study-material producers), matching the score-4 anchor.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: MODSetter/SurfSense
Path: docker/sandbox/skills/flashcards/SKILL.md
Revision: 176aed2

Reviewed: 16 days ago

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.

flashcards

Table of Contents

Is this your skill?