CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

align

Presents a proposed approach in progressive confirmable chunks with recommended decisions and alternatives. Use when aligning on a design, plan, or technical approach before implementation.

Quality

89%

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

92%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 instruction-only skill: a clear multi-step flow with explicit confirmation checkpoints and a redirect feedback loop, concrete presentation conventions, and tight anti-patterns. The only notable gap is the absence of a positive worked example of a well-formed chunk.

DimensionReasoningScore

Conciseness

The body is lean behavioral guidance Claude does not already know ("Propose, don't ask.", "Scannable in one read. If it needs scrolling, split it.", the redirect rule) with zero padding or explanation of known concepts. Every line instructs the specific protocol; nothing can be trimmed without losing guidance, matching the top anchor.

5 / 5

Actionability

Concrete, executable direction throughout: specific markers ("⭐ Recommended approach", "❌ Alternatives"), a named tool ("Confirm each chunk with AskUserQuestion"), and a concrete grouping anti-example ("framework choice, state management choice, and styling choice ... belong in one chunk"). Not 5 because there is no positive worked example showing what a well-formed chunk actually looks like; not 3 because the guidance is specific and executable, not pseudocode-level.

4 / 5

Workflow Clarity

The Flow section gives a clear sequence with an explicit checkpoint ("Confirm each chunk with AskUserQuestion before moving to the next") and an explicit feedback loop ("When the user rejects a chunk ... Rethink from the redirect point forward"), reinforced by the anti-patterns "Moving to the next chunk without explicit confirmation" and "Continuing with pre-planned chunks after a redirect". No destructive or batch operations are involved, so no cap applies.

5 / 5

Progressive Disclosure

This is a simple, single-purpose skill (~40 content lines) with no bundle files (references/, scripts/, assets/ do not exist) and no need for external references; the body references no files, which is consistent. Per the rubric's simple-skill guideline, well-organized sections (Core Principle, Flow, Presenting Chunks, Handling Redirects, Anti-patterns) earn the top score.

5 / 5

Total

19

/

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 in third-person voice that clearly states both capability and an explicit 'Use when' trigger clause. Trigger terms are natural and the distinctiveness is good, though the trigger vocabulary could be broadened and the capability list is not fully comprehensive.

Suggestions

Add natural trigger synonyms such as 'agree on an approach', 'review the plan', or 'discuss the architecture' so users phrasing the need differently still hit the skill.

Mention the confirmation interaction (e.g., 'confirming each chunk with the user before proceeding') in the capability clause to make the what more comprehensive and further distinguish it from plain planning skills.

DimensionReasoningScore

Specificity

"Presents a proposed approach in progressive confirmable chunks" plus "with recommended decisions and alternatives" names three specific actions, matching the anchor for several specific actions with minor gaps. Not 5 because coverage is not comprehensive (e.g., the confirmation interaction and redirect handling are absent); not 3 because it goes beyond 1-2 actions with concrete presentation mechanics.

4 / 5

Completeness

The description explicitly answers what ("Presents a proposed approach in progressive confirmable chunks with recommended decisions and alternatives") and when ("Use when aligning on a design, plan, or technical approach before implementation") with concrete trigger phrases, matching the top anchor and the good-overall-example pattern. Score 4 would apply only if the 'when' were vague or implicit, which it is not.

5 / 5

Trigger Term Quality

"Use when aligning on a design, plan, or technical approach before implementation" supplies natural phrases a user would say ("aligning on", "design", "plan", "before implementation"). Not 5 because common synonyms and variations ("agree on an approach", "review the plan", "architecture") are missing; not 3 because coverage is clearly better than a few scattered keywords.

4 / 5

Distinctiveness Conflict Risk

The mechanism ("progressive confirmable chunks with recommended decisions and alternatives") carves a distinct niche, but the trigger domain "design, plan, or technical approach" is broad and could overlap with general planning or brainstorming skills. Not 5 due to that overlap risk with closely related skills; not 3 because the trigger and mechanism are considerably more specific than generic overlap examples.

4 / 5

Total

17

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

saski/arnesto

Path

.agents/skills/align/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.