CtrlK
BlogDocsLog inGet started
Tessl Logo

research-refine

Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.6-Sol review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

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 highly actionable, well-sequenced multi-phase workflow with strong validation feedback loops; the main gap is mild verbosity from restated principles and large inlined templates that could live in reference files.

Suggestions

Consolidate the four principles so they appear once (either Overview or Key Rules) rather than restated in both sections to reduce token overhead.

Move the full ~85-line proposal template and ~70-line reviewer prompt into reference files (e.g. references/proposal-template.md, references/reviewer-prompt.md) and link to them from the body.

Trim the exhaustive per-field proposal template to the essential structure, leaving field-level detail to a reference, to improve conciseness without losing actionability.

DimensionReasoningScore

Conciseness

Mostly efficient operational guidance, but the four principles are stated in Overview and restated in 'Key Rules', and the ~85-line proposal template and ~70-line reviewer prompt are exhaustive; some tightening is possible.

3 / 5

Actionability

Fully executable: concrete spawn_agent/send_input blocks with model, reasoning_effort, and verbatim message text, plus exact file paths, checkpoint JSON, and fill-in markdown templates.

5 / 5

Workflow Clarity

Phases 0-5 are clearly sequenced with checkpoint recovery, an explicit STOP CONDITION, anchor/simplicity checks, and a review->revise->re-evaluate feedback loop with error recovery guidance.

5 / 5

Progressive Disclosure

Clear section structure with well-signaled one-level-deep references to shared-references via markdown links, though the large reviewer-prompt and proposal-template blocks are inlined rather than split into separate files.

4 / 5

Total

17

/

20

Passed

Description

86%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 with excellent bilingual trigger coverage and an explicit Use-when clause; its only weakness is that the capability is framed as one composite action rather than a comprehensive list of concrete operations.

DimensionReasoningScore

Specificity

Names the domain and two concrete actions ('Turn a vague research direction into a ... method plan' and 'via iterative GPT-5.6-Sol review'), but it is a single composite transformation rather than a list of several distinct actions, so it is not comprehensive.

3 / 5

Completeness

Explicitly answers both what ('Turn a vague research direction into a ... method plan via iterative GPT-5.6-Sol review') and when ('Use when the user says ...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage in both English and Chinese with synonyms ('refine my approach', 'refine research plan', 'decompose this problem', '打磨idea', '细化研究方案', '帮我细化方案').

5 / 5

Distinctiveness Conflict Risk

Has a clear refinement-via-iterative-review niche with specific triggers, but sibling research skills (/idea-creator, /experiment-plan, /research-refine-pipeline) create minor overlap risk.

4 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (722 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 4 suspicious

Warning

Total

14

/

16

Passed

Repository
wanshuiyin/Auto-claude-code-research-in-sleep
Reviewed

Table of Contents

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.