wayfinder

Plan a huge chunk of work - more than one agent session can hold - as a shared map of investigation tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/wayfinder/SKILL.md

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and workflow-clear, with concrete templates, exact label vocabulary, and explicit sequenced steps with feedback loops. The only weakness is conciseness: the evocative metaphorical prose could be trimmed while preserving every operational instruction.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's intelligence and avoids padded concept explanations, but the metaphor-heavy prose ('wrapped in fog', 'the dim view', 'fog of war', 'edge of the known') adds tokens beyond what is strictly operational and could be tightened without losing clarity.	2 / 3
Actionability	As an instruction skill it provides concrete, copy-paste-ready guidance: map and ticket body templates, exact label values (wayfinder:map, wayfinder:<type> with enumerated types), and precise claim/resolve procedures ('assign it to yourself before any work'; 'post the answer as a resolution comment, close the issue').	3 / 3
Workflow Clarity	Both invocation modes are given as explicitly numbered steps with validation and feedback checkpoints ('If this surfaces no fog ... Stop and ask the user', 'create tickets then wire blocking edges in a second pass', recovery for mis-scoped tickets via ruling out of scope or deletion).	3 / 3
Progressive Disclosure	No bundle files exist, but the body is well-organized into clearly signaled sections (Map, Tickets, Ticket Types, Fog of war, Out of scope, Invocation) with only one-level-deep intra-document anchor navigation and no nested external references.	3 / 3
	Total	11 / 12 Passed

Description

57%

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 communicates a clear, distinctive niche and concrete actions, but relies on conceptual phrasing and an implied rather than explicit use-trigger, leaving it just short of the top tier on specificity, trigger terms, and completeness.

Suggestions

Add an explicit 'Use when...' clause stating the trigger (e.g., 'Use when a piece of work is too large to plan or complete in a single agent session and needs to be broken into a shared map of tickets').

Enumerate the concrete actions more crisply (chart a shared map, create labeled child tickets, resolve one ticket per session) to lift specificity toward score 3.

Surface natural trigger keywords a user would say ('too big for one session', 'break this into tickets', 'multi-session plan') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete domain (large multi-session work) and several actions ('plan ... as a shared map of investigation tickets', 'resolve them one at a time'), but the actions are conceptual rather than the crisp, enumerated concrete operations of the score-3 anchor.	2 / 3
Completeness	It clearly states what the skill does (plan large work as a ticketed map, resolve one at a time) and implies when (work too big for one session), but there is no explicit 'Use when...' trigger clause, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Phrases like 'more than one agent session can hold' and 'shared map of investigation tickets' are somewhat natural, but coverage of terms a user would actually say is limited and lacks common variations, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The niche is specific and distinctive — multi-session planning expressed as a shared map of issue-tracker tickets resolved toward a destination — making it unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: novuhq/novu
Path: .agents/skills/wayfinder/SKILL.md
Commit: 67de0fa

Reviewed: about 14 hours ago

Table of Contents

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.