Execute
alirezarezvani/claude-skills
/cs:execute <decision — Generate a 90-day execution plan with weekly milestones, DRIs, and check-in cadence from an approved decision.
Generate executable code together with formal proofs certifying safety and correctness properties in Isabelle/HOL or Coq.
$ npx skills add ArabelaTso/Skills-4-SE --skill proof-carrying-code-generator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ArabelaTso/Skills-4-SE proof-carrying-code-generator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/proof-carrying-code-generator .claude/skills/proof-carrying-code-generator && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "proof-carrying-code-generator" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/proof-carrying-code-generator into .claude/skills/proof-carrying-code-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proof-carrying-code-generator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/proof-carrying-code-generatorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ArabelaTso/Skills-4-SE --skill proof-carrying-code-generator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ArabelaTso/Skills-4-SE proof-carrying-code-generator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/proof-carrying-code-generator .agents/skills/proof-carrying-code-generator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "proof-carrying-code-generator" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/proof-carrying-code-generator into .agents/skills/proof-carrying-code-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proof-carrying-code-generator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ArabelaTso/Skills-4-SE --skill proof-carrying-code-generator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ArabelaTso/Skills-4-SE proof-carrying-code-generator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/proof-carrying-code-generator .cursor/skills/proof-carrying-code-generator && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "proof-carrying-code-generator" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/proof-carrying-code-generator into .cursor/skills/proof-carrying-code-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proof-carrying-code-generator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ArabelaTso/Skills-4-SE.git --path skills/proof-carrying-code-generator--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ArabelaTso/Skills-4-SE --skill proof-carrying-code-generator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ArabelaTso/Skills-4-SE proof-carrying-code-generator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/proof-carrying-code-generator .gemini/skills/proof-carrying-code-generator && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "proof-carrying-code-generator" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/proof-carrying-code-generator into .gemini/skills/proof-carrying-code-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proof-carrying-code-generator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ArabelaTso/Skills-4-SE proof-carrying-code-generatorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ArabelaTso/Skills-4-SE --skill proof-carrying-code-generator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/proof-carrying-code-generator .github/skills/proof-carrying-code-generator && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "proof-carrying-code-generator" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/proof-carrying-code-generator into .github/skills/proof-carrying-code-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proof-carrying-code-generator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ArabelaTso/Skills-4-SE --skill proof-carrying-code-generator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ArabelaTso/Skills-4-SE proof-carrying-code-generator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/proof-carrying-code-generator .opencode/skills/proof-carrying-code-generator && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "proof-carrying-code-generator" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/proof-carrying-code-generator into .opencode/skills/proof-carrying-code-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "proof-carrying-code-generator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
proof-carrying-code-generatorGenerate executable code together with formal proofs certifying safety and correctness properties in Isabelle/HOL or Coq.
Proof Carrying Code Generator is an agent skill from ArabelaTso/Skills-4-SE. 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.
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/coq_pcc.md`, `references/isabelle_pcc.md` and `references/safety_properties.md`).
The repository describes itself as: A curated list of 180+ useful Claude Skills for Software Engineering and resources for customizing AI for SE workflows. The licence is Apache-2.0.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 4f38503. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are isabelle and coq).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Proof Carrying Code Generator loads about 2.9k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 119 tokens; SKILL.md has 510 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from ArabelaTso/Skills-4-SE at commit 4f38503, republished under its Apache-2.0 licence (© ArabelaTso). 510 words, ~2,903 tokens.
.claude/skills/proof-carrying-code-generator/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Generate executable code bundled with formal proofs that certify key safety and correctness properties.
Proof-carrying code (PCC) is executable code accompanied by formal proofs that certify specific properties. This skill helps generate:
The generated code can be extracted to mainstream languages (OCaml, Haskell, SML) while maintaining proof certificates.
Requirements
↓
Formal Specification
↓
Verified Implementation
↓
Proof Obligations
↓
Certified Code + Proofs
↓
Code ExtractionStart with formal specification, implement, then prove.
Steps:
Example (Isabelle):
(* Specification *)
definition sorted_spec :: "nat list ⇒ nat list ⇒ bool" where
"sorted_spec input output ≡ sorted output ∧ mset output = mset input"
(* Implementation *)
fun insertion_sort :: "nat list ⇒ nat list" where
"insertion_sort [] = []" |
"insertion_sort (x # xs) = insert x (insertion_sort xs)"
(* Correctness theorem *)
theorem insertion_sort_correct:
"sorted_spec input (insertion_sort input)"
proof (induction input)
case Nil
then show ?case by (simp add: sorted_spec_def)
next
case (Cons x xs)
then show ?case
using insert_sorted mset_insert
by (auto simp: sorted_spec_def)
qed
(* Extract code *)
export_code insertion_sort in SML file "sort.sml"Start abstract, refine to concrete with proofs at each step.
Steps:
Example (Coq):
(* Abstract specification *)
Definition find_spec {A} (P : A → bool) (l : list A) : option A :=
(* Nondeterministic: any element satisfying P *)
...
(* Concrete implementation *)
Fixpoint find {A} (P : A → bool) (l : list A) : option A :=
match l with
| [] => None
| x :: xs => if P x then Some x else find P xs
end.
(* Refinement proof *)
Theorem find_refines : forall A P l,
find P l = find_spec P l.
Proof.
(* Proof that concrete refines abstract *)
Qed.
(* Extract *)
Extraction "find.ml" find.Write code with annotations, generate proof obligations, prove them.
Steps:
Example (Coq with Program):
Require Import Program.
Program Definition safe_div (a b : nat) (H : b ≠ 0) : nat :=
a / b.
(* Proof obligation automatically generated *)
Next Obligation.
(* Prove division is safe *)
Qed.Property: No buffer overflows, out-of-bounds access.
Pattern:
lemma array_access_safe:
"⟦ i < length arr ⟧ ⟹ ∃v. arr ! i = v"
by auto
fun safe_get :: "'a list ⇒ nat ⇒ 'a option" where
"safe_get [] _ = None" |
"safe_get (x # xs) 0 = Some x" |
"safe_get (x # xs) (Suc n) = safe_get xs n"
lemma safe_get_bounds:
"safe_get xs i = Some v ⟹ i < length xs"
by (induction xs i rule: safe_get.induct) autoProperty: No null pointer dereferences.
Pattern:
Definition safe_head {A} (l : list A) (H : l ≠ []) : A :=
match l with
| [] => match H eq_refl with end
| x :: _ => x
end.
Lemma safe_head_correct : forall A (l : list A) H,
l ≠ [] → safe_head l H = hd_error l.
Proof.
intros. destruct l; auto. contradiction.
Qed.Property: All array accesses within bounds.
Pattern:
definition bounded_access :: "'a array ⇒ nat ⇒ 'a option" where
"bounded_access arr i = (if i < array_length arr
then Some (array_get arr i)
else None)"
lemma bounded_access_safe:
"bounded_access arr i = Some v ⟹ i < array_length arr"
by (simp add: bounded_access_def split: if_splits)Property: Function computes correct result.
Pattern:
fun factorial :: "nat ⇒ nat" where
"factorial 0 = 1" |
"factorial (Suc n) = Suc n * factorial n"
function fact_spec :: "nat ⇒ nat" where
"fact_spec 0 = 1" |
"fact_spec n = n * fact_spec (n - 1)"
by auto
theorem factorial_correct:
"factorial n = fact_spec n"
by (induction n) autoProperty: Data structure invariants maintained.
Pattern:
Inductive BST : tree → Prop :=
| BST_leaf : BST Leaf
| BST_node : forall l x r,
BST l → BST r →
(forall y, In y l → y < x) →
(forall y, In y r → x < y) →
BST (Node l x r).
Fixpoint insert (x : nat) (t : tree) : tree :=
match t with
| Leaf => Node Leaf x Leaf
| Node l y r =>
if x <? y then Node (insert x l) y r
else if y <? x then Node l y (insert x r)
else t
end.
Theorem insert_preserves_BST : forall x t,
BST t → BST (insert x t).
Proof.
induction t; intros; simpl.
- constructor; constructor.
- inversion H; subst.
destruct (x <? n) eqn:E1.
+ (* Insert left *)
+ destruct (n <? x) eqn:E2.
* (* Insert right *)
* (* Equal, no change *)
Qed.Property: Function always terminates.
Pattern:
function gcd :: "nat ⇒ nat ⇒ nat" where
"gcd a 0 = a" |
"gcd a b = gcd b (a mod b)"
by auto
termination
by (relation "measure (λ(a, b). b)") auto
lemma gcd_terminates:
"∃result. gcd a b = result"
by autoFor Isabelle-specific code generation, extraction, and certification patterns, see references/isabelle_pcc.md.
Key features:
For Coq-specific extraction, Program framework, and certification, see references/coq_pcc.md.
Key features:
For detailed safety and correctness property patterns, see references/safety_properties.md.
Categories include:
Specification:
definition binary_search_spec :: "nat list ⇒ nat ⇒ nat option" where
"binary_search_spec xs target = (
if sorted xs ∧ target ∈ set xs
then Some (THE i. i < length xs ∧ xs ! i = target)
else None)"Implementation:
fun binary_search :: "nat list ⇒ nat ⇒ nat option" where
"binary_search xs target = bs_aux xs target 0 (length xs)"
fun bs_aux :: "nat list ⇒ nat ⇒ nat ⇒ nat ⇒ nat option" where
"bs_aux xs target low high = (
if low ≥ high then None
else let mid = (low + high) div 2 in
if xs ! mid = target then Some mid
else if xs ! mid < target then bs_aux xs target (mid + 1) high
else bs_aux xs target low mid)"Safety proofs:
lemma bs_aux_bounds:
"⟦ bs_aux xs target low high = Some i; low ≤ high; high ≤ length xs ⟧
⟹ low ≤ i ∧ i < high"
proof (induction xs target low high rule: bs_aux.induct)
case (1 xs target low high)
then show ?case
by (auto simp: Let_def split: if_splits)
qed
lemma bs_aux_no_overflow:
"⟦ low ≤ high; high ≤ length xs ⟧
⟹ (low + high) div 2 < length xs"
by autoCorrectness proof:
theorem binary_search_correct:
"sorted xs ⟹ binary_search xs target = binary_search_spec xs target"
proof -
assume "sorted xs"
show ?thesis
proof (cases "target ∈ set xs")
case True
then show ?thesis
using binary_search_finds_target[OF `sorted xs` True]
by (simp add: binary_search_spec_def)
next
case False
then show ?thesis
using binary_search_not_found[OF `sorted xs` False]
by (simp add: binary_search_spec_def)
qed
qedCode extraction:
export_code binary_search in SML file "binary_search.sml"
export_code binary_search in OCaml file "binary_search.ml"Before finalizing proof-carrying code:
Pattern: Verify critical components, interface with unverified code.
Example:
(* Verified core *)
definition verified_sort :: "nat list ⇒ nat list" where
"verified_sort = insertion_sort"
theorem verified_sort_correct:
"sorted (verified_sort xs) ∧ mset (verified_sort xs) = mset xs"
by (simp add: verified_sort_def insertion_sort_correct)
(* Export for use in larger system *)
export_code verified_sort in OCaml file "verified_sort.ml"Pattern: Build library of verified functions.
Example:
Module VerifiedList.
(* Verified operations *)
Definition safe_nth := ...
Definition safe_update := ...
Definition verified_map := ...
(* Correctness theorems *)
Theorem safe_nth_correct : ...
Theorem safe_update_correct : ...
Theorem verified_map_correct : ...
End VerifiedList.
(* Extract entire module *)
Extraction "verified_list.ml" VerifiedList.For detailed guidance on specific aspects:
© ArabelaTso, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (references) in skills/proof-carrying-code-generator of ArabelaTso/Skills-4-SE.
Open the folder on GitHubat commit 4f38503
Proof Carrying Code Generator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Proof Carrying Code Generator this skillArabelaTso/Skills-4-SE | 253 | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Executealirezarezvani/claude-skills | 28k | — | ~831 | Automated safety check: Pass | MIT | |
| Generatealirezarezvani/claude-skills | 28k | 1 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Fal Generatenexu-io/open-design | 100k | — | ~306 | Automated safety check: Pass | Apache-2.0 | |
| Generate Then Executemohitagw15856/pm-claude-skills | 1.4k | — | ~938 | Automated safety check: Pass | MIT | |
| Video Generationbytedance/deer-flow | 83k | 3 repos | ~1.4k | Automated safety check: Pass | MIT |
alirezarezvani/claude-skills
/cs:execute <decision — Generate a 90-day execution plan with weekly milestones, DRIs, and check-in cadence from an approved decision.
alirezarezvani/claude-skills
Generate Playwright tests. An agent skill from alirezarezvani/claude-skills.
nexu-io/open-design
Generate images and videos using fal.ai AI models. An agent skill from nexu-io/open-design.
mohitagw15856/pm-claude-skills
Separate raw idea-generation from judgment so creativity isn't strangled by your inner critic — diverge with zero evaluation, then switch to hard critique.
bytedance/deer-flow
Generates short videos from a structured JSON prompt, optionally guided by a reference image used as the first or last frame.
onyx-dot-app/onyx
Generate or edit raster images (photos, illustrations, textures, sprites, mockups, logos, infographics) using the workspace's configured image-generation provider via onyx-cli image.
ArabelaTso/Skills-4-SE
Generate prioritized CVE watchlists and actionable security recommendations for repositories.
ArabelaTso/Skills-4-SE
Automatically migrate Python web applications between frameworks (Flask → FastAPI, Django → FastAPI).
ArabelaTso/Skills-4-SE
Generate test cases using metamorphic testing by applying transformations based on metamorphic properties.
ArabelaTso/Skills-4-SE
Instruments programs to capture execution traces specifically for reproducing reported bugs, enabling consistent replay and diagnosis of failures.
ArabelaTso/Skills-4-SE
Automatically migrate Spring MVC applications to Spring Boot.
ArabelaTso/Skills-4-SE
Instrument programs (Python, C/C++, Java) to capture snapshots of key program states at runtime, including variables, memory, and call stacks.
Generate executable code together with formal proofs certifying safety and correctness properties in Isabelle/HOL or Coq. Proof Carrying Code Generator is an agent skill from ArabelaTso/Skills-4-SE. Generate executable code together with formal proofs certifying safety and correctness properties in Isabelle/HOL or Coq.
Proof Carrying Code Generator fits situations like: building verified software; safety-critical systems; formal guarantees are required.
Run `npx skills add ArabelaTso/Skills-4-SE --skill proof-carrying-code-generator -a claude-code`. Or copy the skill folder (skills/proof-carrying-code-generator in ArabelaTso/Skills-4-SE) into .claude/skills/proof-carrying-code-generator in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ArabelaTso/Skills-4-SE --skill proof-carrying-code-generator -a codex`. Or copy the skill folder (skills/proof-carrying-code-generator in ArabelaTso/Skills-4-SE) into .agents/skills/proof-carrying-code-generator in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ArabelaTso/Skills-4-SE --skill proof-carrying-code-generator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/proof-carrying-code-generator, .gemini/skills/proof-carrying-code-generator, .github/skills/proof-carrying-code-generator and .opencode/skills/proof-carrying-code-generator in your project.
SKILL.md names no scripts, command-line tools or credentials: Proof Carrying Code Generator is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Proof Carrying Code Generator is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.5k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Proof Carrying Code Generator: Execute (alirezarezvani/claude-skills, 28k stars), Generate (alirezarezvani/claude-skills, 28k stars), Fal Generate (nexu-io/open-design, 100k stars) and Generate Then Execute (mohitagw15856/pm-claude-skills, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
ArabelaTso (a GitHub user) maintains it in ArabelaTso/Skills-4-SE, which has 253 GitHub stars. The repository holds 151 skills in this directory. The repository was last updated on August 21, 2026.
Source: ArabelaTso/Skills-4-SE on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.