idea-discovery-robot

Workflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas. Use when user says "robotics idea discovery", "机器人找idea", "embodied AI idea", "机器人方向探索", "sim2real 选题", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured orchestration skill with highly actionable invocation commands, templates, and a clear phase-gated workflow with safety validation. Its main weakness is redundancy of the robotics frame across multiple sections, which inflates length without adding guidance.

Suggestions

De-duplicate the Robotics Problem Frame: define it once in Phase 0 and have the Phase 6 report template reference it rather than re-listing the fields.

Trim or merge the "Key Rules" section with the closest earlier guidance (e.g. Filtering Rules / Good-Weak patterns) to remove restated content.

Consider extracting the landscape matrix axes and the full report template into a reference file to shorten the core SKILL.md and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with clear headers and an ASCII pipeline diagram, but the robotics frame fields recur across the Overview, Phase 0, and the Phase 6 report template, and the "Key Rules" section restates earlier guidance, so it could be tightened.	3 / 5
Actionability	Copy-paste-ready sub-skill invocation commands (e.g. `/research-lit "$ARGUMENTS — focus venues: ..."`), a concrete landscape matrix, idea checklists, and a fill-in pilot plan template give fully executable guidance.	5 / 5
Workflow Clarity	Phases 0–6 are clearly sequenced with explicit checkpoints, AUTO_PROCEED feedback rules, re-run-on-change loops, and a safety validation ("Never auto-proceed to physical robot testing") with checklists for idea quality.	5 / 5
Progressive Disclosure	Well-sectioned body with clearly signaled one-level-deep references to shared protocols (output-versioning, output-manifest, output-language); no bundle files exist, and some inlineable content (full report template, full matrix) is reasonably kept inline for an orchestration skill.	4 / 5
	Total	17 / 20 Passed

Description

91%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, concrete actions, explicit bilingual trigger phrases, and clear what/when coverage. Only minor gaps in action granularity and a slight overlap hint from the "adaptation" framing.

Dimension	Reasoning	Score
Specificity	Lists several concrete orchestration actions ("literature survey, idea generation, novelty check, and critical review") and a concrete outcome ("benchmark-grounded, simulation-first ideas"), though the actions are pipeline-stage names rather than fine-grained operations, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what (orchestrates survey→generation→novelty→review into benchmark-grounded sim-first ideas) and when ("Use when user says..." with concrete trigger phrases).	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including English and Chinese phrases ("robotics idea discovery", "机器人找idea", "sim2real 选题") plus topical synonyms (manipulation, locomotion, navigation, drones, humanoids).	5 / 5
Distinctiveness Conflict Risk	Robotics-specific bilingual triggers carve a clear niche with minimal conflict risk, but it is explicitly a "Workflow 1 adaptation" that delegates to generic sub-skills, leaving minor overlap risk with a non-robotics idea-discovery skill.	4 / 5
	Total	18 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 suspicious	Warning

	Total	13 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/idea-discovery-robot/SKILL.md
Commit: f4f20f9

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.