Tessl • The management layer for AI agent skills

A tightly written behavioral skill with an explicit round-based workflow, validation checkpoints, and a concrete output format. The only gaps are minor: slight redundancy in framing and the absence of a worked example of a completed round.

Suggestions

Add one short worked example of a filled-in round (a real Q1 with its recommended answer) to make the format unambiguous in practice.

Trim the opening sentence and the second explanation of the frontier, which partially restate rules already given, to push conciseness to fully lean.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no explanation of sub-agents or decision trees), but the opening sentence and the twice-explained frontier concept are minor instances of over-explanation that could be trimmed, matching anchor 4 rather than the every-token-earns-its-place of anchor 5.	4 / 5
Actionability	A copy-paste-ready round format template plus crisp directives ("Word each question so 'yes' accepts your recommended answer") make the guidance mostly executable, but no worked example of a filled-in round is provided, which keeps it just below anchor 5's "specific examples cover the common cases".	4 / 5
Workflow Clarity	The sequence is explicit (compute frontier → ask the whole frontier in one round → wait for answers → recompute → repeat) with validation checkpoints (waiting each round, user confirmation before acting), an explicit feedback loop (answers reshape the tree and push the frontier outward), and a crisp termination condition (frontier empty), matching anchor 5.	5 / 5
Progressive Disclosure	This is a single-file skill under 50 lines with no bundle files and no need for external references; the content is clear and logically ordered (setup → format → dynamics → completion), so the simple-skill exception applies and it scores 5.	5 / 5
	Total	18 / 20 Passed

Description

82%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 terse, distinctive description that explicitly answers both what the skill does and when to trigger it, using natural trigger phrases. Its only weakness is thin capability coverage — a single action verb rather than a list of concrete behaviors.

Suggestions

Enumerate one or two more concrete behaviors in the description (e.g., "map decisions as a tree and interview the user in rounds, asking only unblocked questions") to raise specificity beyond a single action.

Add a common trigger synonym such as "devil's advocate" or "challenge my assumptions" to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	The phrase "Grill the user relentlessly about a plan or decision" names the domain and one concrete action with its manner, matching anchor 3 ("Processes PDF files and extracts content") rather than anchor 2's bare generic action or anchor 4's list of several specific actions.	3 / 5
Completeness	It explicitly answers both "what" ("Grill the user relentlessly about a plan or decision") and "when" with a concrete trigger clause ("Trigger: stress-test my thinking, grill"), satisfying the explicit-trigger requirement that would otherwise cap completeness at 3.	5 / 5
Trigger Term Quality	"Trigger: stress-test my thinking, grill" provides two natural phrases a user would actually say, giving good coverage, but common variations like "devil's advocate", "challenge my assumptions", or "poke holes in my plan" are missing, so it falls between anchors 3 and 4 — noticeably above the midpoint of keyword coverage.	4 / 5
Distinctiveness Conflict Risk	The skill occupies a clear niche — adversarial interrogation of the user's own plan or decision — with distinctive triggers ("grill", "stress-test my thinking") that are unlikely to fire for unrelated skills, matching anchor 5 rather than anchor 4's minor-overlap case.	5 / 5
	Total	17 / 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: YoizenSA/dev-ai-workflow
Path: ywai/skills/grilling/SKILL.md
Revision: 98f360e

Reviewed: 22 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.

grilling

Table of Contents

Is this your skill?