⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

v0.5.2

perch

lakeday-org@lakeday-org⭐ 315 stars· last commit 10d ago· 12 open issues

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐⭐⭐ 315 on GitHubGitHub ↗

Popular

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

Semantic code and security scanner.

Getting started

npm install -g @lakeday/perch
perch login
perch scan

perch login signs you in to Perch Cloud, where the first $5 is free. Since decisions are cached, running perch again on unchanged code is free. Perch Cloud also scans pull requests in CI, without writing any workflows.

$ perch scan
checkout.py
  ID        Line  Severity  Type    Confidence  Problem                     Method
  bdc67421    14  P1 (0.8)  defect         81%  wrong_order                 place_order
  ddc5c917    24  P1 (0.8)  defect         92%  inverted_condition          can_fulfil

cart.py
  ID        Line  Severity  Type    Confidence  Problem             Method
  287bfb9d     9  P1 (1.0)  defect         90%  off_by_one          subtotal
  80d6ebbb    29  P1 (1.4)  defect         89%  unhandled_null      cheapest

✖ 20 problems in 5 files, all failing

Run perch issues to see them worst first, and perch issues <id> to view one.

perch check <id> asks again after you think you've fixed it. It doesn't record anything.

Agent skills

perch setup claude-code   # .claude/skills/perch/SKILL.md
perch setup codex         # .codex/skills/perch/SKILL.md
perch setup pi            # .pi/skills/perch/SKILL.md
perch setup cursor        # .cursor/rules/perch.mdc

Semantic linting

You can extend perch with your own linting rules by adding them to perch.yaml:

- name: private-logs
  where: "src/**/*.ts"
  each: method
  ensure: >
    Keep passwords and access tokens out of logs.

ReviewBench

ReviewBench is GitHub's benchmark for AI code review. Perch is credited when it flags the method holding a labelled bug; the leaderboard credits a review comment that a judge model matches to one. The runs, the answers and how to reproduce them are linked from .benchmarks/reviewbench.

ReviewerRecall
Laude RevEngine Prime46.3%
Perch · OpenAI Decisions, $0.024 a pull request40.0%
block/review32.6%
Klaussy29.8%
Copilot code review26.0%
DeepSeek Harness Reviewer25.6%
Devin AI23.8%
Qodo22.1%
Codex18.5%
Cubic16.3%
Greptile16.2%
Cursor9.6%
Perch · Jev, $0.011 a pull request7.9%

Greptile benchmark

Greptile's benchmark runs code reviewers on 50 pull requests, each with one known bug. The runs and their labels are linked from .benchmarks/greptile.

Perch is credited when it flags the function holding the known bug. The published tools were credited for a line comment identifying it.

Models

By default, Perch Cloud routes your questions to the best model for answering them. To ask a specific decision model, override the endpoint, key, and model:

export PERCH_BASE_URL=https://api.typesafe.ai/v1/systemone
export PERCH_API_KEY='paste-your-TypeSafe-key-here'
export PERCH_MODEL_ID=jev-latest
ModelPERCH_BASE_URLPERCH_MODEL_ID
Jevhttps://api.typesafe.ai/v1/systemonejev-latest
Liquid AI d1https://api.liquid.ai/decisions/v1/systemoned1:free
OpenAI gpt-6-lunahttps://api.openai.com/v1/decisionsgpt-6-luna
DiffusionGemma Jev on Beamhttps://app.beam.cloud/v1/models/jev/diffusiongemma/invokejev/diffusiongemma
SemiF on Beamhttps://app.beam.cloud/v1/models/jev/semif/invokejev/semif

Any endpoint that supports the

// HOW IT'S BUILT

// FILES

1 file shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.

Plain-text copy, no login: /skill-bundles/lakeday-org-perch.md

// REPO STATS

315 stars
12 open issues
Last commit: 10d ago