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

84%

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

77%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-sequenced, domain-fluent workflow with concrete sub-skill invocations and strong checkpoints. Its main weakness is progressive disclosure: it is a long monolithic file with no in-bundle reference structure despite sizable inline templates.

Suggestions

Move the Phase 1 Robotics Landscape Matrix and the Phase 6 report template into a references/ file (e.g. references/report-template.md) and link to them from SKILL.md to reduce inline bulk.

Consolidate the repeated simulation-first / benchmark-specificity rules into one Constants or Key Rules section and reference it from the phases instead of restating.

If the shared-references/output-*.md protocols are part of this skill's bundle, place copies under references/ so the links resolve one level deep within the skill rather than relying on an external ../../shared-references path.

Dimension	Reasoning	Score
Conciseness	Dense and assumes domain knowledge (VLA/VLM, sim2real, RLBench, ManiSkill) without explaining it, but the simulation-first and benchmark-specificity rules are restated across Overview, Constants, Phase 3, and Key Rules — minor redundancy that keeps it below the lean 5 anchor.	4 / 5
Actionability	Provides concrete copy-paste-ready sub-skill invocations with specific argument formatting plus filtering rules and pilot/report templates, but execution is delegated to other skills and pilots are plans rather than runnable commands — mostly executable with minor gaps.	4 / 5
Workflow Clarity	Phases 0–6 are clearly sequenced with explicit checkpoints, an AUTO_PROCEED fallback, and feedback loops (refine frame → re-run earlier phase; label high-execution-risk ideas), matching the clear-sequence-with-explicit-validation anchor.	5 / 5
Progressive Disclosure	No in-bundle references/scripts/assets exist; the shared-references links point outside the bundle, and the large landscape matrix and full report template are inlined in a ~360-line SKILL.md — some structure with clearly signaled external refs but content that could be split into separate files remains inline.	3 / 5
	Total	16 / 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, specific description with excellent bilingual trigger coverage and explicit what/when guidance. The only soft spot is mild overlap with the parent idea-discovery workflow it adapts.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "literature survey, idea generation, novelty check, and critical review" chained as research-lit → idea-creator → novelty-check → research-review — with only minor coverage gaps, fitting the "lists several specific actions" anchor rather than the fully comprehensive 5.	4 / 5
Completeness	Explicitly answers both what (orchestrates survey → generation → novelty check → review toward benchmark-grounded ideas) and when ("Use when user says ... or wants ideas for ...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms and bilingual phrases ("robotics idea discovery", "机器人找idea", "embodied AI idea", "sim2real 选题") plus enumerated sub-domains (manipulation, locomotion, drones, humanoids), matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Robotics-specific niche with distinct triggers and minimal conflict risk, but it is explicitly an adaptation of an existing Workflow 1 / idea-discovery skill, creating minor overlap with the base skill — between anchors 4 and 5.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/skills-codex-gemini-review/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.