CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

create-formal-verification-skill

Verify the project's riskiest invariant with TLA+, Lean, or Kani — chosen by property shape — and leave a project-local skill the next agent reruns; assumptions are part of the deliverable. For properties tests cannot reach.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A well-crafted, disciplined skill body: the tool-selection heuristic, the assumptions register, and the counterexample protocol are concrete guidance Claude can execute directly, with genuine validation gates throughout. The main improvements are bundling the ledger-writing details into a reference file and resolving the external "figure-it-out way"/"babysit" pointers that a cold-start agent cannot follow.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what TLA+, Lean, or Kani are, only when each fits — and every section carries actionable rules. Anchor 4 rather than 5 because the opening paragraph ("this skill exists to find that one property, verify it, and leave the verification behind as structure") partially restates the description, and a few rhetorical flourishes could be trimmed.

4 / 5

Actionability

Mostly executable guidance: named run commands ("apalache/TLC, lake build, cargo kani"), an exact output path (".claude/skills/verify-formal-<property>/SKILL.md"), the generated skill's required contents, and concrete ledger imports and row values. Not anchor 5 because step 6's "resolve the package root the figure-it-out way; babysit's ledger step demonstrates the exact invocation" points to context not bundled with this skill, and no exact command-line syntax is given for the verifiers.

4 / 5

Workflow Clarity

Six clearly sequenced steps with explicit validation checkpoints and feedback loops: a violated property triggers minimize-counterexample → check the code → report before touching the model; "formally-verified" is written only after a green rerun; and "If none fits, say so and stop" guards the tool-choice step. This matches the anchor-5 pattern of explicit validation with error-recovery loops.

5 / 5

Progressive Disclosure

Well-organized single-file skill with clear sections (When to use / When not to use / Workflow / Maintenance / Rules) and no nested or buried references. Not anchor 5: the body is ~74 lines (above the sub-50-line simple-skill exception), and step 6's ledger-writing mechanics — plus the dangling pointer to "babysit's ledger step" — are content that arguably belongs in a bundled reference file.

4 / 5

Total

17

/

20

Passed

Description

78%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.

A strong description: concrete, distinctive, and honest about scope ("assumptions are part of the deliverable"). Its main weakness is the thin when-clause — "For properties tests cannot reach" is explicit but could enumerate the concrete trigger scenarios (concurrency protocols, exact arithmetic, exhaustiveness) that the body already contains.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Verify the project's riskiest invariant with TLA+, Lean, or Kani", "leave a project-local skill the next agent reruns", "assumptions are part of the deliverable" — with only minor coverage gaps. It falls short of anchor 5 because the actions are compressed and don't comprehensively convey what the skill does end-to-end, but exceeds anchor 3 by naming multiple specific actions rather than 1-2.

4 / 5

Completeness

Both parts are present: a clear what ("Verify the project's riskiest invariant... leave a project-local skill the next agent reruns") and an explicit when-equivalent clause ("For properties tests cannot reach"). The when-clause keeps it above anchor 3, but it is singular and abstract rather than the concrete trigger phrases required for anchor 5.

4 / 5

Trigger Term Quality

"TLA+, Lean, Kani", "invariant", and "properties tests cannot reach" are strong, natural trigger terms a user asking for formal verification would say. Not anchor 5 because common synonyms like "prove", "model check", "spec", or "formal methods" are absent; not anchor 3 because the tool names provide genuinely good keyword coverage.

4 / 5

Distinctiveness Conflict Risk

Naming three specific formal-methods tools carves out a clear niche — TLA+, Lean, and Kani work is unambiguous and would rarely trigger the wrong skill. Minimal conflict risk with any generic testing or verification skill.

5 / 5

Total

17

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

Yeachan-Heo/oh-my-claudecode

Path

skills/create-formal-verification-skill/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.