CtrlK
BlogDocsLog inGet started
Tessl Logo

wayfinding

Audit whether someone dropped into an arbitrary file can tell where they are and where to go next. Use when the user says "onboarding is painful", "agents get lost in this repo", "nobody can find their way around", "add breadcrumbs", or when an /ia pass fixed the structure but readers still stall.

72

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

86%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 effective, actionable audit methodology: concrete procedure, explicit scoring, and a clean output template, with theory correctly offloaded to a single well-signaled reference. It could shave a little inline theory prose to tighten conciseness and add an explicit validate-the-findings step to reach the top workflow-clarity anchor.

Suggestions

Trim the inline Pirolli/Card and Lynch framing prose in 'Information Scent' and 'Lynch's Five Elements' since the full treatment already lives in references/scent-and-landmarks.md.

Add an explicit validation step to the Cold-Entry Audit (e.g. re-check that each finding maps to exactly one of the four questions) to strengthen workflow_clarity toward a 5.

Consider listing 2-3 concrete audit actions in the description (e.g. 'sample entry points, score each file 0–3, trace unsignposted exits') to lift specificity.

DimensionReasoningScore

Conciseness

The body is largely lean tables and procedures and defers the full theory to the reference, but retains a few inline explanatory passages (e.g. the Pirolli/Card and Lynch framing prose) that could be trimmed, fitting efficient-with-minor-over-explanation rather than fully lean.

4 / 5

Actionability

Concrete sampling criteria (stack traces, grep hits, recent commits, deepest file, random from largest dir), an explicit 0–3 scoring rubric, and a copy-paste output template give fully executable, specific guidance covering the common cases.

5 / 5

Workflow Clarity

The Cold-Entry Audit is a clear 4-step sequence (sample → simulate → score → trace exits) with a scoring checkpoint; it is a read-only audit so the destructive-cap does not apply, but there is no explicit validation loop, which holds it just below a 5.

4 / 5

Progressive Disclosure

The body is a well-structured overview that signals a single one-level-deep reference ("See references/scent-and-landmarks.md for the full treatment", verified present), splitting theoretical detail out appropriately.

5 / 5

Total

18

/

20

Passed

Description

90%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: third-person voice, explicit trigger phrases a user would naturally say, and a clear what/when pair. The only weak spot is specificity, which lists a single audit action rather than a fuller set of concrete capabilities.

DimensionReasoningScore

Specificity

"Audit whether someone dropped into an arbitrary file can tell where they are and where to go next" names the domain and one concrete action, but does not enumerate multiple concrete actions, fitting the 1-2-actions anchor rather than the comprehensive 5.

3 / 5

Completeness

It clearly states what the skill does (audit cold-entry orientation) and explicitly answers when with concrete "Use when the user says..." trigger phrases, matching the both-what-and-when anchor.

5 / 5

Trigger Term Quality

"onboarding is painful", "agents get lost in this repo", "nobody can find their way around", "add breadcrumbs" are natural phrases users would actually say, giving comprehensive trigger coverage.

5 / 5

Distinctiveness Conflict Risk

The wayfinding/orientation niche is distinct, and the description even delineates it from "/ia" and "readers still stall," giving minimal conflict risk.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tslateman/duet
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.