yzj623/pplab/apt-recovery-evaluation-harness
Claude Code and agent skill by yzj623/pplab
- community
Checking that the SKILL.md file is still in the repository.
Build bounded APT recovery experiments with executable evidence, generated-skill invocation logs, source manifests, and mechanism checks.
Install
npx vskill@latest install yzj623/pplab/apt-recovery-evaluation-harnessSKILL.md
The same SKILL.md was published earlier as yzj623/pplab/apt-recovery-evaluation-harness.
APT Recovery Evaluation Harness
Use this skill when a Distiller recovery run needs to test whether generated APT skills can recover the paper's mechanism without reading the original implementation repository. The harness is especially useful in soft mode, where a declared reduced/proxy experiment may be accepted only after executable evidence and validation pass.
Inputs
- Attempt directory with
module_plan.json,paper_profile.md, andenvironment/runtime_handoff.json. - Generated skills root containing the APT protocol, transformation, and atomic-loss skills.
- Recovery mode from the normalized run config.
- Bounded command budget and source-boundary constraints.
Outputs
recovery/experiment_plan.md.recovery/source_manifest.json.recovery/logs/experiment_command_log.json.recovery/logs/generated_skill_invocations.json.recovery/logs/generated_data_item.json.recovery/logs/training_trace.json.recovery/recovery_result.json.
Workflow
- Read the fast recovery target from the module plan.
- Read the runtime handoff and decide whether full neural recovery is available.
- If full recovery is blocked and soft mode allows proxy recovery, declare the reduced target.
- Invoke generated helper scripts for sequential proposal records, posterior transformation, and atomic loss.
- Run an executable experiment command that computes numeric metrics and mechanism checks.
- Write a source manifest that lists allowed sources and excludes original repositories.
- Run the Distiller recovery gate after the command completes.
Validation
The script scripts/check_recovery_artifacts.py performs a lightweight local check for key files and mechanism fields. The Distiller gate remains authoritative:
The same script also checks that source_manifest.json does not list forbidden sources and that it mentions runtime_handoff.json, which catches common source-boundary mistakes before full analysis.
Limitations
- This skill does not choose ambiguous paper sources.
- It cannot turn a proxy experiment into hard-mode success.
- It should not silently create data from a previous attempt; every recovery run must produce its own command-generated artifacts.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingbasicagent-skill/skill_library/paperbench/all-in-one/skill/automatic_posterior_transformation/apt_recovery_evaluation_harness/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/yzj623/pplab/apt-recovery-evaluation-harness)