CtrlK
BlogDocsLog inGet started
Tessl Logo

customize

Guided customization of your litigation practice profile — change one thing without re-running the whole cold-start interview. Adjust practice role, side (plaintiff / defense / mixed), risk calibration, landscape, house style, escalation contacts, severity vocabulary, or matter workspace paths. Use when the user says "change my [thing]", "update my profile", "edit my config", or "customize".

66

Quality

80%

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 ./litigation-legal/skills/customize/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, clearly sequenced interactive skill with strong workflow checkpoints and good organization. Weaker on conciseness (redundancy with the description) and actionability (vague edit mechanics in the core step).

Suggestions

Trim or remove the "When this runs" section, which restates the frontmatter description ("change something in their litigation profile ... without re-running the whole cold-start interview") — the description already covers it.

In step 4 ("Make the change"), specify the concrete edit mechanics: which field/section in CLAUDE.md or company-profile.md to modify and the expected format, rather than just "write it to the config".

Add a post-write re-read/validation step confirming the change landed and the profile remains internally consistent, closing the loop on the inconsistency-flagging guardrail.

DimensionReasoningScore

Conciseness

Mostly directive and free of concepts Claude already knows, but the "When this runs" section restates the frontmatter description ("change something in their litigation profile — a risk calibration, a house style rule ... without re-running the whole cold-start interview"), creating redundancy that could be tightened.

2 / 3

Actionability

Provides concrete file paths and verbatim messages, but the core "Make the change" step is high-level ("Show the current value, ask for the new value ... write it to the config") without specifying which field/format to edit, leaving a key detail incomplete.

2 / 3

Workflow Clarity

A clear six-step sequence with explicit checkpoints — a pre-check for missing/placeholder config (step 1), confirm-before-write (step 4), and a Guardrails checklist (flag internal inconsistency, guardrail degradation, never-delete) that serves as validation for the profile edit.

3 / 3

Progressive Disclosure

Well-organized into clear sections (When this runs / What to do / Guardrails) in a single self-contained file with no nested references; the only referenced paths (CLAUDE.md, company-profile.md) are runtime config targets, not skill bundle references, so nothing needs splitting out.

3 / 3

Total

10

/

12

Passed

Description

90%Weight 40%Scale 1-3

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, concrete description with explicit trigger guidance and a clear niche. The only weakness is second-person voice ("your ..."), which the rubric penalizes on specificity.

DimensionReasoningScore

Specificity

Lists multiple concrete adjustable fields ("practice role, side ... risk calibration, landscape, house style, escalation contacts, severity vocabulary, or matter workspace paths"), which is anchor-3 breadth, but the description is written in second-person voice ("your litigation practice profile", "change one thing") rather than third person, so the rubric's voice penalty drops specificity by one.

2 / 3

Completeness

Explicitly answers both what ("Guided customization of your litigation practice profile ... Adjust ...") and when ("Use when the user says ..."), with explicit triggers — the anchor-3 example.

3 / 3

Trigger Term Quality

Gives natural phrasings a user would actually say — "change my [thing]", "update my profile", "edit my config", or "customize" — matching the anchor for good coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

A clear niche (litigation profile customization within the litigation-legal plugin) with distinct triggers, making conflict with unrelated skills unlikely.

3 / 3

Total

11

/

12

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.

Validation15 / 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
anthropics/claude-for-legal
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.