trailofbits/calcifier

최근 기록된 소스 활동: 2026년 10월 14일 15:44

SkillsMP 카탈로그 업데이트: 2026년 11월 2일 18:02

수집된 skills: 15

GitHub 스타: 18
GitHub 포크: 0

AI 어시스턴트로 설치

이 프롬프트를 복사해 사용 중인 AI 어시스턴트에 입력하세요.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/trailofbits/calcifier.

저장소 README

README 원본 파일: README.md

README 원본 보기

README 전체 펼치기

# calcifier Calcifier turns Claude/Codex skills into executable Python workflows. Give it a `SKILL.md`; it produces a recipe that you can read, review, run, and debug. Python handles repeatable operations. Agents handle reasoning. ## Why use it? A skill is a set of instructions that an agent interprets each time it runs. That works well for exploration, but a recurring task often has a stable procedure: gather files, run a script, ask for a judgment, then write a report. Repeating that planning costs model calls and makes the procedure harder to inspect. Calcifier makes the procedure explicit. For example, a review skill can become Python that selects files, calls an agent to assess them, validates the returned findings, and writes the report. You can change the file selection or report format without asking a model to invent the whole workflow again. Use it for skills you run repeatedly, such as code reviews, data triage, and report generation, when you want: - **A workflow you own:** ordinary Python functions and control flow that humans can maintain. - **Less repeated model work:** file operations, scripts, transformations, and rendering execute directly in Python. - **Checked answers:** agent responses are parsed into typed values with explicit validation and a bounded retry. - **Visible execution:** budgets, permissions, artifacts, and traces make it easier to see what ran and where it failed. Agent answers remain nondeterministic. Compilation checks catch mechanical errors; whether a recipe follows the skill and produces good answers needs testing on real tasks. Recipes execute Python on your host, so review generated code before granting trust. ## Try it Install from PyPI. Requires Python 3.13+, [uv](https://docs.astral.sh/uv/), and an authenticated Claude or Codex CLI (or a custom agent adapter). ```bash uv tool install calcifier calcifier --version ``` Follow the [quickstart](docs/usage.md#quickstart) to configure agent roles, compile a skill, review the generated recipe, and run it. Compilation starts with a runnable baseline that gives one agent session the intact skill and its resources. It then tries to move repeatable work into Python. If that fails, it retains and labels the baseline; use `--require-compiled` when you need compilation failure to exit nonzero. The Claude Code plugin provides compilation, execution, debugging, and update skills: ```text /plugin marketplace add trailofbits/calcifier /plugin install calcifier@calcifier ``` For local testing, use the checkout's absolute path as the marketplace. ## Commands and documentation | Command | Purpose | | ------- | ------- | | `calcify SKILL.md` | Compile a skill and package its resources. | | `exec recipe.py` | Run a reviewed, trusted recipe. | | `debug recipe.py` | Run with verbose diagnostics. | | `update SKILL.md` | Compile a candidate and print a diff without changing the package. | | `lint recipe.py --portable` | Check recipe and dependency contracts. | | `build-graph build.json` | Compile dependencies and publish a closed catalog. | | `profile run.json` | Summarize timings, attempts, prompt sizes, and token use. | Use `calcifier COMMAND --help` for flags. - [Usage](docs/usage.md): setup, compilation, inputs, trust, outputs, and traces. - [Recipe authoring](docs/recipes.md): typed answers, effects, budgets, parallel work, and composition. - [Providers](docs/providers.md): agent roles and custom agent/tool contracts. - [Architecture](docs/architecture.md): compiler and runtime internals. - [Contributing](CONTRIBUTING.md): development, testing, and compiler replay. ## Development ```bash uv --no-config sync --all-groups --locked gmake verify ``` See [CONTRIBUTING.md](CONTRIBUTING.md) and [SUPPORT.md](SUPPORT.md) for contribution and support policies. Report vulnerabilities privately using [SECURITY.md](SECURITY.md). Project interactions follow the [Code of Conduct](CODE_OF_CONDUCT.md). [MIT](LICENSE), copyright Trail of Bits, Inc.

저장소 README를 불러오는 중…

이 저장소의 skills

분류 대기 중

미분류

Find the files in a workspace that mention a phrase and explain each match.

원문 언어: 영어

2026-10-14

수집된 skill 15개 중 15개를 표시합니다.