CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

trail-sense-user-guide

Write or edit Trail Sense tool user guides (guides/en-US/guide_tool_*.txt) in the established house style - task-based headings, numbered procedures, warning callouts, and consistent UI wording. Use when adding a user guide, documenting a new or changed feature, or reviewing guide wording.

75

Quality

94%

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

96%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.

Excellent instruction-only skill: lean, fully actionable house-style rules with executable validation checks and a well-sequenced workflow that includes an explicit validation gate. The only structural observation is that everything lives inline in SKILL.md with no reference files, which is defensible for a style manual but leaves minor organization headroom.

DimensionReasoningScore

Conciseness

The body is a dense, project-specific house-style manual: rendering rules ("The app splits a guide into sections in `TextUtils.getSections`"), a wording table, banned words, and reusable templates, with no padding or explanations of concepts Claude already knows. Every token carries a rule Claude could not derive on its own, matching the lean score-5 anchor rather than the minor-trimming score-4 anchor.

5 / 5

Actionability

Guidance is fully executable: copy-paste procedure and reusable-section templates, exact verification commands (grep/xxd checks that "complete when none of them print anything"), and a precise wording table ("`Tap the **+** button in the bottom-right corner.`"). This matches the score-5 anchor of copy-paste-ready commands covering common cases.

5 / 5

Workflow Clarity

The Workflow section gives a clear six-step sequence with an explicit validation checkpoint ("This step is complete when none of them print anything") plus a follow-up reading confirmation of lead-ins, numbering, and cross-references. The completion criterion defines a validate-fix-retry loop, matching the score-5 anchor; it exceeds score 4 because validation is explicit and specific rather than a vague "verify output".

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so all content is inline in a clearly sectioned 149-line body with descriptive headings that make navigation easy. It sits at score 4 rather than 5 because there are no well-signaled one-level-deep references — the wording table and reusable-section templates are reference-style material that could be split into a separate file.

4 / 5

Total

19

/

20

Passed

Description

92%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: concrete, domain-specific, with explicit what and when clauses and natural trigger phrases. The only minor gap is missing synonyms such as "documentation" or "help text" that some users might use.

DimensionReasoningScore

Specificity

Concrete actions ("Write or edit Trail Sense tool user guides") target an exact artifact ("guides/en-US/guide_tool_*.txt") and enumerate the specific style dimensions covered ("task-based headings, numbered procedures, warning callouts, and consistent UI wording"). Coverage is comprehensive rather than having the minor gaps that define the score-4 anchor.

5 / 5

Completeness

The description explicitly answers "what" (write or edit Trail Sense tool user guides in the established house style, with specifics) and "when" via an explicit "Use when adding a user guide, documenting a new or changed feature, or reviewing guide wording" clause with concrete triggers. This matches the score-5 anchor; it is above score 4 because the "when" is specific rather than generic.

5 / 5

Trigger Term Quality

Natural trigger phrases are present ("adding a user guide", "documenting a new or changed feature", "reviewing guide wording") and would be said by users needing this skill. However, common synonyms such as "documentation", "help text", or "docs" are missing, so it does not meet the comprehensive-synonyms bar of the score-5 anchor.

4 / 5

Distinctiveness Conflict Risk

It names a unique application ("Trail Sense"), an exact file path pattern, and a distinct task domain (tool user guides in house style), giving it a clear niche with minimal conflict risk. It would not plausibly trigger for any other skill.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

16

Passed

Repository

kylecorry31/Trail-Sense

Path

.agents/skills/trail-sense-user-guide/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.