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

73%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/skills-codex/idea-discovery-robot/SKILL.md

Quality

Discovery

100%

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

This is a strong skill description that clearly defines a specific robotics research ideation workflow with concrete steps, excellent bilingual trigger terms, and explicit 'Use when' guidance. It covers both the 'what' and 'when' thoroughly while maintaining a distinct niche that would be easily distinguishable from other skills. The description uses proper third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'robotics-aware literature survey, idea generation, novelty check, and critical review' and specifies the goal 'go from a broad robotics direction to benchmark-grounded, simulation-first ideas'. These are concrete, well-defined steps in a workflow.	3 / 3
Completeness	Clearly answers both 'what' (orchestrates literature survey, idea generation, novelty check, critical review for robotics) and 'when' (explicit 'Use when' clause with specific trigger phrases and use cases). Both dimensions are thoroughly covered.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms including English and Chinese variations: 'robotics idea discovery', '机器人找idea', 'embodied AI idea', '机器人方向探索', 'sim2real 选题', plus domain-specific terms like 'manipulation, locomotion, navigation, drones, humanoids, robot learning'. These are terms users would naturally use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche: robotics/embodied AI idea discovery workflow. The combination of robotics domain specificity, bilingual triggers, and the specific workflow steps (simulation-first, benchmark-grounded) make it very unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

47%

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

This is a well-structured orchestration workflow with clear phase sequencing, explicit checkpoints, and strong safety gates around hardware execution. However, it is severely over-verbose — repeating the 'sim-first, no real robot' constraint in nearly every section and explaining research judgment that Claude already possesses. The content would benefit from aggressive trimming and splitting detailed templates into referenced sub-files.

Suggestions

Cut content by 50%+: remove redundant restatements of 'simulation first' and 'no real robot' (state once in Constants/Key Rules), eliminate the 'Good/Weak Robotics Idea Patterns' prose that explains research taste Claude already has, and condense the Landscape Matrix into a compact reference.

Move the detailed Landscape Matrix template, pilot design template, and filtering rules into separate referenced files (e.g., LANDSCAPE_TEMPLATE.md, PILOT_TEMPLATE.md) to keep the main skill as a lean orchestration overview.

Consider whether the Phase 0 'Robotics Problem Frame' fields list and the Phase 1 matrix really need to enumerate every possible value (e.g., 'single-arm, mobile manipulator, humanoid, drone, quadruped') — Claude can infer these without exhaustive examples.

Dimension	Reasoning	Score
Conciseness	At ~350+ lines, this skill is extremely verbose. It over-explains concepts Claude already knows (what embodiments are, what metrics mean, what constitutes good/bad ideas), repeats constraints multiple times (e.g., 'simulation first' and 'no real robot' appear in nearly every phase), and includes extensive tables and lists that could be dramatically condensed. The 'Weak Robotics Idea Patterns' and 'Good Robotics Idea Patterns' sections explain research taste that Claude already possesses.	1 / 3
Actionability	The skill provides concrete sub-skill invocations (e.g., `/research-lit`, `/idea-creator`, `/novelty-check`, `/research-review`) with specific argument templates, and includes a concrete output template for the final report. However, there is no executable code — the 'code blocks' are mostly prompt strings and markdown templates rather than runnable commands. The pilot design section is a checklist template rather than executable guidance.	2 / 3
Workflow Clarity	The six-phase workflow is clearly sequenced with explicit checkpoints after Phase 1 and Phase 2, AUTO_PROCEED behavior is well-defined, and there are clear feedback loops (e.g., user requests changes → re-run earlier phase). The real-robot safety gate is an explicit validation checkpoint. The execution rule at the top clearly states when to stop vs. continue.	3 / 3
Progressive Disclosure	The skill references external sub-skills (`/research-lit`, `/idea-creator`, `/novelty-check`, `/research-review`) and shared protocols at the end, which is good progressive disclosure. However, the main body itself is a monolithic wall of text that could benefit from splitting detailed filtering rules, the landscape matrix template, and the pilot design template into separate reference files. The inline content is far too long for a top-level orchestration skill.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Commit: 700fbe2

Reviewed: 2 days 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.