lofi-gate-checkpoint

LoFi Gate Judge Skill

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "lofi-gate-checkpoint" with this command: npx skills add lofi-monk/lofi-gate/lofi-monk-lofi-gate-lofi-gate-checkpoint

LoFi Gate Judge Skill

[!CAUTION] MANDATORY CHECKPOINT. You cannot commit until this skill approves your changes. Skipping this step will result in rejection at the Gate.

You have completed coding and tests are passing. Now you must judge your own work before declaring victory.

Step 1: Gather Evidence

Run this command to see exactly what you changed:

git diff --staged

If nothing is staged, run:

git diff HEAD

Save the output. This is your evidence.

Step 2: Recall Your Mission

Find the original instructions. Check these locations in order:

  • The user's original request (in conversation history)

  • implementation_plan.md (if you created one)

  • task.md (if it exists)

This is your mission.

Step 3: The Anti-Cheat Check

Look at your evidence (the diff). Answer these questions:

Q1: Did you modify any EXISTING test files?

  • Look for changes to files matching: .test. , .spec. , test_*.py , *_test.go

  • If YES → Did the mission explicitly ask you to modify tests?

  • NO → VERDICT: FAIL - "Modified existing tests without authorization"

  • YES → Continue

Q2: Did you disable, skip, or weaken any tests?

  • Look for: .skip , .only , @pytest.mark.skip , expect(true).toBe(true) , commented-out assertions

  • If YES → VERDICT: FAIL - "Weakened test integrity"

Q3: Did you delete test files or test cases?

  • If YES and not authorized → VERDICT: FAIL - "Deleted tests without authorization"

Step 4: The Scope Check

Compare your evidence against your mission:

Q4: Did you stay within scope?

  • Did you only change what was asked?

  • Did you add files or features that weren't requested?

  • If you went outside scope → VERDICT: FAIL - "Scope creep detected"

Q5: Did you complete the mission?

  • Review each requirement in the mission

  • Is each one addressed in your changes?

  • If incomplete → VERDICT: FAIL - "Mission incomplete"

Step 5: Deliver Judgment

If all checks pass:

✅ JUDGMENT: APPROVED All changes align with the mission. No test manipulation detected.

If any check fails:

❌ JUDGMENT: REJECTED Reason: [specific failure reason] Required action: [what to fix]

Step 6: Act on Judgment

  • If APPROVED: You may proceed to commit/push.

  • If REJECTED: You MUST fix the issues before proceeding. Do not ignore this judgment.

Step 7: Log Your Verdict

Record your decision in the official log:

If Passed

python .agent/skills/lofi-gate-checkpoint/scripts/logger.py --source "CHECKPOINT" --status "PASS" --message "Approved changes."

If Failed

python .agent/skills/lofi-gate-checkpoint/scripts/logger.py --source "CHECKPOINT" --status "FAIL" --message "Reason for rejection..."

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

image-gen

Generate AI images from text prompts. Triggers on: "生成图片", "画一张", "AI图", "generate image", "配图", "create picture", "draw", "visualize", "generate an image".

Archived SourceRecently Updated
General

explainer

Create explainer videos with narration and AI-generated visuals. Triggers on: "解说视频", "explainer video", "explain this as a video", "tutorial video", "introduce X (video)", "解释一下XX(视频形式)".

Archived SourceRecently Updated
General

asr

Transcribe audio files to text using local speech recognition. Triggers on: "转录", "transcribe", "语音转文字", "ASR", "识别音频", "把这段音频转成文字".

Archived SourceRecently Updated
General

axure-prototype-generator

Axure 原型代码生成器 - 输出 JavaScript 格式 HTML 代码,支持内联框架直接加载可交互原型

Archived SourceRecently Updated