CtrlK
BlogDocsLog inGet started
Tessl Logo

outline-builder

Build or extend a course outline in your format, from class notes and casebook. Scaffolds — it does not write the outline for you. Use when the user says "outline [subject]", "add to my outline", "build an outline from", or points at class materials.

74

Quality

92%

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

85%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, highly actionable instruction-only skill with concrete templates, markers, and dialogues plus a clear sequenced workflow. Its one weakness is conciseness: the core 'don't write it for me' rule is restated several times and some rationale is redundant for Claude.

Suggestions

Consolidate the 'don't write it for me' rule: state it once authoritatively in its dedicated section, then have later sections reference it briefly rather than re-explaining the rationale each time.

Trim philosophical framing like 'Building it is half the studying — that's a literal claim, not a throwaway. An outline you didn't build is an outline you won't know on the exam.' down to a single line, since the behavioral rule already conveys the intent.

The 'What this skill does not do' closing section largely repeats the hard-rule section and Confidence discipline; merge the unique points (no exam-coverage guarantee) into the existing sections and drop the rest.

DimensionReasoningScore

Conciseness

The body is mostly actionable but padded with repeated reinforcement of the 'don't write it for me' principle (stated in the hard-rule section, Confidence discipline, Step 3, and the closing section) and philosophical framing Claude already grasps ('Building it is half the studying — that's a literal claim, not a throwaway'). Not score 3 because the redundancy could be tightened; not score 1 because the core guidance is efficient and concrete.

2 / 3

Actionability

Provides copy-paste-ready artifacts: exact Socratic questions, concrete gap markers ([GAP — fill from class notes], [NEEDS CASES], [UNCERTAIN], [VERIFY]), three filled-in outline format templates, an exact refusal dialogue, and exact reconciliation prompts. Matches the score-3 anchor of specific, executable examples.

3 / 3

Workflow Clarity

A clearly sequenced workflow (Steps 1-4: Inputs, Structure, Build, Gaps) with explicit guardrails and feedback loops — the refusal dialogue and the rule-contradiction reconciliation serve as validation checkpoints. The operations are not destructive/batch, so the absence of a formal validate-fix-retry loop does not cap the score.

3 / 3

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so the skill is a single self-contained file with well-organized sections and clear headers enabling easy navigation, with no nested or multi-level references. Not score 2 because organization is clean and there are no deep-reference or monolithic-wall failures; the length is the only minor drag but the sectioning keeps it navigable.

3 / 3

Total

11

/

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 strong description: it states multiple concrete capabilities, gives explicit natural-language trigger phrases, and covers both 'what' and 'when'. It is concise and well-targeted to its niche with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Build or extend a course outline', 'Scaffolds', 'does not write the outline for you', 'from class notes and casebook' — rather than vague language. Not score 2 because it goes beyond naming a single domain/action to enumerating several specific capabilities.

3 / 3

Completeness

Explicitly answers both what ('Build or extend a course outline... Scaffolds') and when (an explicit 'Use when the user says...' clause). Matches the score-3 anchor of clearly answering both with explicit triggers.

3 / 3

Trigger Term Quality

Includes natural phrases users would actually say: 'outline [subject]', 'add to my outline', 'build an outline from', or 'points at class materials'. Not score 2 because it covers several common phrasings rather than a single keyword.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear law-student outline-building niche with distinct triggers unlikely to fire for unrelated skills. Not score 2 because the domain and triggers are specific enough to avoid overlap with general writing or study skills.

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.