CtrlK
BlogDocsLog inGet started
Tessl Logo

matter-workspace

Manage matter workspaces — new, list, switch, close, or detach (practice-level). Use when working across multiple clients or matters in private practice and you need to create, list, switch, close, or detach the active matter so context from one engagement doesn't leak into another.

70

Quality

86%

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

72%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.

Highly actionable and well-organized, with concrete templates, exact paths, and clear subcommand logic. The main weakness is redundancy across the duplicated overview sections and the absence of explicit validation feedback loops for the destructive archive/write operations.

Suggestions

Collapse the duplicated '# Matter Workspace' overview and the repeated disabled-state explanation into a single section; reference it instead of restating the `/cold-start-interview --redo` guidance twice.

Add an explicit validation step to the `close` and `new` workflows — e.g., after archiving, confirm the source path is gone and the archived path exists; after writing matter.md, verify the file parses before reporting success.

De-duplicate the slug rules (currently stated in both the 'Notes' and 'Storage layout' sections) to a single authoritative location.

DimensionReasoningScore

Conciseness

Mostly efficient and free of explaining concepts Claude already knows, but the body carries redundancy — a duplicated '# Matter Workspace' overview, the disabled-state explanation repeated in both 'Instructions' and the second section, and slug rules stated twice — that could be tightened.

2 / 3

Actionability

Concrete and copy-ready throughout: exact storage paths, a fill-in matter.md template, a history.md seed, table column specs for `list`, and explicit per-subcommand file operations.

3 / 3

Workflow Clarity

Steps are well sequenced and include confirmation checkpoints ('Show the user what changed and confirm before writing'), but destructive/batch operations like `close` (archive move) and `new` (writing files) lack an explicit validate→fix→retry feedback loop, which caps this dimension per the rubric.

2 / 3

Progressive Disclosure

No bundle files exist, yet the skill is appropriately sectioned (Subcommand logic, Storage layout, templates, Cross-matter context, What this skill does not do) with one-level internal navigation and no nested references — well-organized for a self-contained skill under the rubric's simple-skill note.

3 / 3

Total

10

/

12

Passed

Description

100%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 tight, third-person description that pairs concrete operations with an explicit Use-when clause grounded in a distinct legal-practice scenario. It is specific, trigger-rich, and unlikely to conflict with other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'create, list, switch, close, or detach the active matter' — naming five distinct operations rather than vague domain gestures.

3 / 3

Completeness

Answers both what (manage matter workspaces: new/list/switch/close/detach) and when with an explicit 'Use when working across multiple clients or matters in private practice... so context from one engagement doesn't leak into another.'

3 / 3

Trigger Term Quality

Uses natural practitioner vocabulary ('matters', 'clients', 'switch', 'detach', 'context leak') a user would plausibly say, with strong coverage across the named subcommands.

3 / 3

Distinctiveness Conflict Risk

The private-practice/matter-isolation niche and the specific detachment trigger are unlikely to fire for unrelated skills, giving it a clear, well-bounded activation surface.

3 / 3

Total

12

/

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.