CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

loogle-search

Search Mathlib for lemmas by type signature pattern

Quality

83%

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 body is an exemplary compact, single-file skill: executable commands, a syntax reference table, realistic performance expectations, and a concrete proof-integration example with no padding. The only flaws are minor — a redundant opening line duplicating the description and slight overlap between the Commands and Examples sections.

Suggestions

Delete the opening line 'Search Mathlib for lemmas by type signature pattern.' — it duplicates the frontmatter description verbatim and adds no information.

Trim the overlap between Commands and Examples: the '(?a → ?b) → List ?a → List ?b' and 'IsCyclic, center' queries appear in both sections; keep each pattern in one place.

DimensionReasoningScore

Conciseness

The body is lean — a syntax table, command blocks, and performance numbers with no concept over-explanation — but the opening line 'Search Mathlib for lemmas by type signature pattern.' duplicates the description verbatim, and the Examples section re-runs two queries already shown in Commands ('(?a → ?b) → List ?a → List ?b' and 'IsCyclic, center'). These minor redundancies fit 'Efficient; minor instances of over-explanation that could be trimmed' rather than the every-token-earns-its-place anchor.

4 / 5

Actionability

Fully executable, copy-paste-ready guidance throughout: real 'loogle-search' invocations with concrete Mathlib patterns, 'loogle-server &' startup, build commands, and a worked end-to-end Lean example (goal → query → 'Fintype.one_lt_card_iff_nontrivial' → 'exact' line) covering the common cases. Matches the top anchor.

5 / 5

Workflow Clarity

A simple, single-purpose, read-only skill whose single action is unambiguous (run loogle-search with a pattern); the 'Integration with Proofs' section sequences the three-step workflow and the Performance section gives the server-vs-cold-start decision point. No validation checkpoints are needed for non-destructive queries, and the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

A compact single-file skill with well-organized sections (When to Use, Commands, Query Syntax, Examples, Performance, Setup, Integration), no buried content, and nothing that clearly belongs in a separate reference file. Per the scoring note, a small self-contained skill with clear organization scores 5 without external file references.

5 / 5

Total

19

/

20

Passed

Description

65%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 states a clear, distinct, appropriately narrow capability in third person, but it covers only one action and omits any explicit 'when to use' trigger guidance. Adding a 'Use when...' clause and Lean-oriented synonyms (Lean, theorem, proof search, Loogle) would raise both completeness and trigger coverage.

Suggestions

Add an explicit trigger clause, e.g. 'Use when stuck in a Lean/Mathlib proof and you need to find a lemma by its type, or when exploring what Mathlib offers for a type.'

Include natural synonyms a user would actually say — 'Lean', 'theorem', 'proof search', 'Loogle' — so the description matches varied phrasings.

Mention the additional concrete capabilities the skill supports (exact-name search, JSON output, server mode for fast repeated queries) to improve specificity.

DimensionReasoningScore

Specificity

Names the domain ('Mathlib', 'lemmas') and one concrete action ('Search ... by type signature pattern'), matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. Not a 4 because only a single search action is stated — no mention of name search, JSON output, or server mode.

3 / 5

Completeness

The 'what' is clear ('Search Mathlib for lemmas by type signature pattern') but there is no 'Use when...' clause or equivalent explicit trigger guidance — the 'when' is only weakly implied. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Contains natural terms a Lean user would say — 'Mathlib', 'lemmas', 'type signature', 'search' — giving good keyword coverage. Not a 5 because common synonyms like 'Lean', 'theorem', 'proof search', and the tool name 'Loogle' are absent.

4 / 5

Distinctiveness Conflict Risk

'Mathlib', 'lemmas', and 'type signature pattern' define a clear niche with distinct triggers and minimal conflict risk with any other skill. Uses third-person voice as required.

5 / 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

parcadei/Continuous-Claude-v3

Path

.claude/skills/loogle-search/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.