wayfinder

把单个 agent session 装不下的一大块工作规划成 issue tracker 上的 decision tickets shared map，并逐一解决，直到通往 destination 的路清晰。

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

75%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 efficient, well-structured instruction skill with concrete labels, templates, and clearly sequenced multi-step workflows plus several explicit checkpoints. Its main gap is the absence of an explicit validate-and-retry feedback loop for the issue create/close operations.

Suggestions

Add an explicit verification step after resolving a ticket (e.g. confirm the resolution comment is posted, issue closed, and Decisions-so-far pointer appended before moving on) to strengthen the feedback loop.

Tighten the metaphorical framing in 'Fog of war'/'Out of scope' where the evocative language duplicates the operational point.

Signal the map-body and ticket templates more explicitly as reusable sub-units (e.g. a short 'Templates' header) to improve navigability.

Dimension	Reasoning	Score
Conciseness	The body is dense and information-rich, assumes Claude knows trackers/labels/issue mechanics, and reserves its prose for skill-specific concepts (map, frontier, fog); only minor metaphorical framing ('已知世界的边缘') could be trimmed.	4 / 5
Actionability	Gives concrete, specific guidance — exact labels (wayfinder:map, wayfinder:<type>), ticket templates, numbered steps, and named subagents (/grilling, /research) — with minor gaps where specifics are delegated to tracker docs.	4 / 5
Workflow Clarity	Both modes ('Chart the map' 6 steps, 'Work through the map' 5 steps) are clearly sequenced with explicit checkpoints (stop if no fog, claim before work, max one ticket/session, rule out of scope), but lack a validate-then-retry feedback loop.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with inlined templates appropriately kept inline and no nested references; no bundle files exist, and all content belongs in this single self-contained file, with only minor organization gaps.	4 / 5
	Total	16 / 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 conveys a clear, distinctive 'what' but omits explicit trigger guidance, so the 'when' is only weakly implied and completeness is capped at 3. Trigger-term coverage is adequate but not rich in natural user phrasings.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g. a request too large for one session, needing to map out decisions before building).

Broaden trigger terms with common synonyms a user would actually say ('too big for one pass', 'break this into decisions', 'plan before building').

Surface 1-2 more concrete actions (chart the map, grill out decisions, graduate fog into tickets) to lift specificity above 3.

Dimension	Reasoning	Score
Specificity	Names the domain (work too big for one agent session, issue tracker, decision tickets, shared map) and 1-2 concrete actions ('规划成 decision tickets shared map', '逐一解决'), but is not comprehensive.	3 / 5
Completeness	The 'what' is clear (plan large work into decision tickets on a tracker and resolve them until the path is clear), but 'when' is only weakly implied by '装不下单个 session' with no explicit 'Use when...' clause, which caps completeness at 3 per the guideline.	3 / 5
Trigger Term Quality	Has some relevant keywords ('单个 agent session 装不下', 'issue tracker', 'decision tickets') that a user might echo, but lacks common variations/synonyms and any explicit trigger phrasing.	3 / 5
Distinctiveness Conflict Risk	The wayfinding/planning niche (session-overflow work mapped to tracker decision tickets until the destination path clears) is distinctive and unlikely to trigger execution skills, with only minor overlap risk against general planning/spec skills.	4 / 5
	Total	13 / 20 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: vinvcn/mattpocock-skills-zh-CN
Path: skills/engineering/wayfinder/SKILL.md
Commit: 9fb0161

Reviewed: 4 days 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.