proof-carrying-code-generator

Generate executable code together with formal proofs certifying safety and correctness properties in Isabelle/HOL or Coq. Use when building verified software, safety-critical systems, or when formal guarantees are required. Produces code with accompanying proofs for memory safety, bounds checking, functional correctness, invariant preservation, and termination. Supports extraction to OCaml/Haskell/SML and integration with existing codebases.

1.01x

Quality

76%

Does it follow best practices?

Impact

92%

1.01x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/proof-carrying-code-generator/SKILL.md

Quality

Content

60%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-structured, code-rich body with clear workflows and properly signaled one-level references, but it loses points for incomplete proof stubs presented as examples and redundancy between inline safety patterns and the safety_properties reference.

Suggestions

Complete or remove the stubbed proofs (find_refines, insert_preserves_BST, VerifiedList operations) so every code example is fully executable rather than pseudocode.

Move the inline Memory/Null/Bounds safety property patterns into references/safety_properties.md to eliminate duplication with that reference file.

Tighten the body by trimming the ASCII workflow diagram and the Overview's restatement of PCC, which Claude already understands.

Dimension	Reasoning	Score
Conciseness	Mostly code-driven and assumes Claude's baseline knowledge, but the body is lengthy with some redundancy — inline Memory/Null/Bounds safety patterns overlap with the separate safety_properties.md reference, and the ASCII workflow diagram adds limited value.	3 / 5
Actionability	Provides many concrete Isabelle/Coq examples, but several proofs are incomplete stubs (find_spec '...', find_refines '(* Proof that concrete refines abstract *)', insert_preserves_BST with unfinished bullet stubs, VerifiedList ':= ...') without explicit justification for the pseudocode.	3 / 5
Workflow Clarity	A clear sequenced workflow (Requirements → Specification → Implementation → Proof Obligations → Certified Code → Extraction) plus numbered per-approach steps and a final Verification Checklist; only minor validation-checkpoint gaps since this is non-destructive code generation.	4 / 5
Progressive Disclosure	References are one level deep, real files (isabelle_pcc.md, coq_pcc.md, safety_properties.md), and clearly signaled with descriptions of their contents; the main gap is inline safety-property patterns that duplicate content belonging in the reference file.	4 / 5
	Total	14 / 20 Passed

Description

92%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, specific description that clearly states what the skill does and when to use it, with concrete tool names and a detailed list of certified properties. Minor keyword synonym coverage keeps trigger quality just below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the domain — 'certifying safety and correctness properties', 'memory safety, bounds checking, functional correctness, invariant preservation, and termination', 'extraction to OCaml/Haskell/SML' — giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' ('Generate executable code together with formal proofs...') and 'when' ('Use when building verified software, safety-critical systems, or when formal guarantees are required') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('building verified software', 'safety-critical systems', 'formal guarantees') plus concrete tool names ('Isabelle/HOL', 'Coq'), but misses a few common synonyms/variations a user might naturally utter.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear, specialized niche (formal verification in Isabelle/HOL and Coq) with distinct triggers that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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: ArabelaTso/Skills-4-SE
Path: skills/proof-carrying-code-generator/SKILL.md
Commit: 4f38503

Reviewed: 19 days ago

Table of Contents

Discovery Implementation Validation

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.