CtrlK
BlogDocsLog inGet started
Tessl Logo

map

The yard's skill map — which skill owns which job, in delivery-loop order. Use when something needs doing but not which of the shipped skills owns it; the map routes, it never executes.

69

Quality

85%

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.

An exemplary lean router: concrete job→skill tables, explicit tiebreak and no-match rules, and correct delegation of all detail to the routed skills' own doctrine. The only flaw is a small amount of duplication between the opening paragraph, the Rules section, and the frontmatter description.

DimensionReasoningScore

Conciseness

The job→skill tables are lean with every row earning its place, but the opening line "You know something needs doing; you do not know which skill owns it" and the Rules bullet "The map routes; it never executes" restate the frontmatter description — a minor redundancy that could be trimmed.

4 / 5

Actionability

"Find the job below, call the Skill tool with the routed skill" plus concrete job→skill rows, an explicit tiebreak rule ("earlier legs come first"), and a no-match rule ("say so plainly rather than picking the nearest-sounding skill") make the single action fully executable with edge cases handled.

5 / 5

Workflow Clarity

A single-purpose routing skill whose one action is unambiguous, with explicit decision checkpoints (two-rows-fit tiebreak, no-match handling); no destructive or batch operations, so no validation cap applies.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed; four well-organized sections (delivery loop, on-ramps, utilities, rules) delegate all doctrine to the routed skills instead of inlining it, which is exactly the right split for a router.

5 / 5

Total

19

/

20

Passed

Description

78%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 well-formed router description: it explicitly answers both what and when with a concrete trigger clause in third-person voice. Its main weakness is that the stated capability stops at a single routing action, and trigger-term coverage lacks common synonyms.

Suggestions

Broaden the stated capability beyond the single routing action — e.g., mention that it covers delivery-loop jobs, on-ramps (debugging, research, memory), and utility off-ramps, so the 'what' is more comprehensive.

Add one or two natural trigger variations users would actually say, such as "which skill should I use" or "who owns this task", to strengthen keyword coverage.

Consider naming the artifact it operates on at trigger time (e.g., "job", "task", "request") so the description matches more of the phrasings users produce.

DimensionReasoningScore

Specificity

"which skill owns which job, in delivery-loop order" and "the map routes, it never executes" name the domain and one concrete action (routing), but there is no enumeration of capabilities beyond routing — comprehensive it is not.

3 / 5

Completeness

Both are explicit: the what ("The yard's skill map — which skill owns which job... the map routes, it never executes") and a concrete when ("Use when something needs doing but not which of the shipped skills owns it").

5 / 5

Trigger Term Quality

"Use when something needs doing but not which of the shipped skills owns it" plus "skill map" give good natural phrasing a user in that situation would echo, but common variations (e.g., "which skill should I use") are missing.

4 / 5

Distinctiveness Conflict Risk

The routing-only niche ("the map routes, it never executes") is clearly distinct, but the trigger condition — not knowing which skill owns a job — can co-occur with almost any task, leaving minor overlap risk.

4 / 5

Total

16

/

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
Yeachan-Heo/oh-my-claudecode
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.