CtrlK
BlogDocsLog inGet started
Tessl Logo

understand-onboard

Use when you need to generate an onboarding guide for new team members joining a project

68

Quality

81%

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.

The content is highly actionable and well-structured, with concrete commands, explicit validation checkpoints, and a feedback loop for stale data. The only slack is minor verbose prose in the freshness-check step.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence; the graph schema and bash commands earn their tokens, though step 2's prose and the slight overlap between 'How to Read Efficiently' and the Instructions could be trimmed.

4 / 5

Actionability

Provides a copy-paste-ready bash block, specific grep targets ("layers", "tour"), concrete node types and fields to extract, and an explicit output section list — fully executable guidance.

5 / 5

Workflow Clarity

Eleven clearly sequenced steps with explicit validation checkpoints (file-existence check in step 1, graph-freshness diff in step 2) and a feedback loop (warn and suggest running /understand when stale).

5 / 5

Progressive Disclosure

Single-file skill with no bundle directories and clean section headers (Graph Structure Reference, How to Read Efficiently, Instructions); the inline schema is essential per-run context, and there are no nested references.

5 / 5

Total

19

/

20

Passed

Description

70%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 clear and well-formed with an explicit Use-when trigger and a distinct niche, but it states only a single concrete action and a narrow set of trigger phrases, limiting specificity and trigger-term coverage.

Suggestions

Add 1-2 more concrete actions (e.g., 'summarize architecture layers and flag complexity hotspots') to lift specificity toward 5.

Broaden trigger terms with synonyms users actually say, such as 'ramp up', 'onboarding doc', or 'new hires'.

Mention the knowledge-graph source in the description to sharpen distinctiveness from generic documentation skills.

DimensionReasoningScore

Specificity

Names the domain and one concrete action ("generate an onboarding guide") but offers no further specific actions, matching the anchor for 1-2 concrete actions without comprehensive coverage.

3 / 5

Completeness

Explicitly answers both what ("generate an onboarding guide") and when ("Use when you need to... for new team members joining a project"), but the when is a single restated trigger rather than varied concrete trigger phrases.

4 / 5

Trigger Term Quality

Includes several natural phrases a user would say ("onboarding guide", "new team members", "joining a project"), but lacks common synonyms like "ramp up", "onboarding doc", or "new hires".

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (onboarding-guide generation) with minimal conflict risk, though not naming the knowledge-graph source leaves minor overlap with generic documentation skills.

4 / 5

Total

15

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Egonex-AI/Understand-Anything
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.