harbor-adapter-creator
Create Harbor benchmark adapters that convert external benchmark datasets into Harbor task format.
Skill by junjiezhou1122
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/junjiezhou1122-harbor-adapter-creator
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/harbor-adapter-creator
What's inside
- Skill name
harbor-adapter-creator- Description
- Create Harbor benchmark adapters that convert external benchmark datasets into Harbor task format. Use when porting an existing benchmark to Harbor, running parity experiments, registering a dataset to the Harbor registry, or debugging adapter validation failures. Covers: adapter class interface (generate_task, make_local_task_id), directory layout including YAML job configs, oracle verification, parity planning and experiments, dataset registration, and the full post-implementation workflow.
- License
- unknown
- Instructions
- 494 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Agent Skills spec issues
- files: referenced but missing: scripts/validate_adapter.py
Files (3)
- LICENSE
- SKILL.md
- adapter-anatomy.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from junjiezhou1122/autoResearch
- 0.521score
create-adapter
junjiezhou1122
Scaffold a new Harbor benchmark adapter by running `harbor adapter init` and then guide implementation using the Adapters Agent Guide as the authoritative spec.
SkillAFreshness: AClaude Code +9 - 0.518score
research-mode
junjiezhou1122
Route the current research task to useful research skills and execute them through to the requested output.
SkillAFreshness: AClaude Code +9 - 0.513score
assumption-map
junjiezhou1122
Identify the important assumptions that the current mechanism depends on.
SkillAFreshness: AClaude Code +9 - 0.513score
boundary-push
junjiezhou1122
Discover a research problem by pushing a method beyond the conditions where it currently works.
SkillAFreshness: AClaude Code +9 - 0.513score
contrast
junjiezhou1122
Discover a candidate mechanism by comparing similar cases with different outcomes.
SkillAFreshness: AClaude Code +9 - 0.513score
counterfactual
junjiezhou1122
Reveal or test a mechanism by changing one meaningful condition while keeping the rest similar.
SkillAFreshness: AClaude Code +9 - 0.513score
factorize-failure
junjiezhou1122
Decompose one observed failure into distinct failure mechanisms.
SkillAFreshness: AClaude Code +9 - 0.513score
minimal-experiment
junjiezhou1122
Design the smallest experiment that can distinguish the current hypothesis from its main alternative.
SkillAFreshness: AClaude Code +9 - 0.513score
observe
junjiezhou1122
Extract useful observations from results, traces, examples, errors, papers, or other evidence before explaining them.
SkillAFreshness: AClaude Code +9 - 0.513score
prediction
junjiezhou1122
Derive an observable prediction from the current mechanism or hypothesis.
SkillAFreshness: AClaude Code +9 - 0.513score
prior-art-falsify
junjiezhou1122
Test whether a candidate research idea is actually novel by searching for equivalent prior mechanisms.
SkillAFreshness: AClaude Code +9 - 0.513score
reconstruct
junjiezhou1122
Recover the minimal mechanism that makes an existing method, paper, or result work.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 4
- Last commit (this folder)
- Oct 9, 2026 (20 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/junjiezhou1122/autoResearch
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from junjiezhou1122
- 0.580score
resume
junjiezhou1122
Validate a saved native IdeaScientist run and continue its next admissible stage without resetting budgets or overwriting outputs.
SkillAFreshness: A★ 47Claude Code +9 - 0.580score
check
junjiezhou1122
Run the standalone offline validator for a native IdeaScientist run's artifacts, evidence receipts and stage dependencies.
SkillAFreshness: A★ 47Claude Code +9 - 0.580score
evaluate
junjiezhou1122
Independently evaluate a native proposal with explained quality scores, coverage-limited novelty and a previously frozen blind baseline.
SkillAFreshness: A★ 47Claude Code +9 - 0.580score
ideate
junjiezhou1122
Start a bounded native IdeaScientist run for a research problem, grounded gaps, one intuition and an independently reviewed proposal.
SkillAFreshness: A★ 47Claude Code +9 - 0.574score
ideascientist-ideate
junjiezhou1122
Start automatic grounded scientific ideation for a research problem.
SkillAFreshness: A★ 47Claude Code +9 - 0.574score
ideascientist-check
junjiezhou1122
Check saved IdeaScientist artifacts using the canonical offline validator.
SkillAFreshness: A★ 47Claude Code +9
Cite this page
harbor-adapter-creator skill. Agent Mart. https://agentmart.dev/skills/junjiezhou1122-harbor-adapter-creator (last updated 2026-10-24)