CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

router

Fixture skill that addresses another skill's helper across a skill boundary when assessing reference rebasing.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./internal/adaptertest/testdata/skill-reference-boundary/package/skills/router/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 exemplar of lean, imperative instruction: an ordered three-step workflow with exact commands and a clear finish marker, and a single one-level-deep companion reference that exists in the bundle. The only deductions are the workspace-rooted reference path style and the absence of any statement of expected behavior for the helper commands.

DimensionReasoningScore

Conciseness

The body is ~20 lines with zero padding: "Process steps in order. Do not skip ahead.", three one-line steps with exact commands, and "Finish here." Every token earns its place and nothing explains concepts Claude already knows. This squarely matches the lean-and-efficient anchor.

5 / 5

Actionability

Both run steps are copy-paste-ready commands with exact paths and arguments ("Run `skills/advocate/scripts/check.sh --router`"). It falls just short of fully-executable (5) because the helper paths target files outside this skill's bundle that are not verifiable from the skill itself, and no expected output or result handling is stated — minor gaps, matching the mostly-executable anchor.

4 / 5

Workflow Clarity

A three-step sequence with explicit ordering ("Process steps in order. Do not skip ahead."), per-step headers, and a termination marker ("Finish here."). The operations are non-destructive single commands, so no validation checkpoint is required, and under the simple-skill exception the clear, well-organized sequence earns the top score.

5 / 5

Progressive Disclosure

The skill is under 50 lines with well-organized sections, and its single reference ("See `skills/router/references/notes.md`") is one level deep, clearly signaled, and resolves to a real bundle file (references/notes.md). It is not 5 because the companion is cited via a workspace-rooted path rather than a bundle-relative link, a minor organization gap; the remaining step-1/2 paths are cross-skill operational targets rather than disclosure references.

4 / 5

Total

18

/

20

Passed

Description

58%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 is honest, third-person, and highly distinct, but it reads as internal test-fixture jargon rather than a trigger description. What and when are both present yet the trigger vocabulary contains no natural user phrases, which caps its routing usefulness.

Suggestions

Add natural trigger phrases users would actually say, e.g. "Use when rebasing references across skills, updating legacy Tessl plugin paths, or verifying cross-skill helper scripts."

Replace jargon like "addresses another skill's helper across a skill boundary" with concrete plain-verb actions, e.g. "Runs the advocate helper's check script via both its package-root and legacy Tessl-installed paths, then reads the companion notes."

State what the skill does with the helper's output (verify, compare, report) so the capability coverage is comprehensive rather than stopping at one action.

DimensionReasoningScore

Specificity

"Fixture skill that addresses another skill's helper across a skill boundary" names the domain (cross-skill helper invocation) and one concrete action, with "assessing reference rebasing" as a second; coverage stops there. It fits the anchor for 1-2 concrete actions without comprehensiveness — not 2 (actions are more than minimal/generic) and not 4 (it does not list several specific actions or say what the skill does with the helper).

3 / 5

Completeness

Both parts are explicitly present: the what ("addresses another skill's helper across a skill boundary") and the when ("when assessing reference rebasing"). It matches the both-present-but-could-be-more-explicit anchor — not 5 because the when is a single narrow jargon phrase with no concrete trigger terms, and not 3 because the when is explicitly stated rather than missing or weakly implied.

4 / 5

Trigger Term Quality

The only keywords are domain jargon — "helper", "skill boundary", "reference rebasing" — with no natural phrase a user would actually say when needing this skill. It sits between the pure-technical-jargon anchor (1) and the one-or-two-generic-keywords anchor (2): "skill" and "reference" are semi-natural domain terms, but common variations and synonyms are entirely absent.

2 / 5

Distinctiveness Conflict Risk

"assessing reference rebasing" and cross-skill-boundary helper invocation carve out a clear, narrow niche that virtually no other skill would claim, giving minimal conflict risk. It is not 4, because there is no meaningful overlap with closely related skills — the topic vocabulary is highly distinct even though it is jargon-heavy.

5 / 5

Total

14

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

jbaruch/agentic-context-registry

Path

internal/adaptertest/testdata/skill-reference-boundary/package/skills/router/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.