CtrlK
BlogDocsLog inGet started
Tessl Logo

results-report

This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results report", "写实验总结报告", "写实验复盘", or mentions turning completed experiment artifacts into a structured, decision-oriented research report. It assumes strict analysis should come from `results-analysis` first.

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

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A well-structured, actionable reporting skill with a gated workflow and clear reference navigation. Its main gaps are mild inline restatement of content that also lives in the reference files and one dangling reference to a missing example file.

Suggestions

Trim the inline 'Default report structure' 10-section list and the 'Required frontmatter' block to one-line summaries, since `references/report-structure.md` and `references/report-naming.md` already hold the full detail — this removes restatement and tightens token use (conciseness).

Add the missing `examples/example-results-report.md` or remove the dangling reference from the 'Reference files' list so every signaled path resolves (progressive_disclosure).

Add a brief post-write verification step in Workflow step 5 (e.g., confirm the new note resolves and links back to the `Experiments/` note) before appending the Daily trace, giving the multi-file Obsidian write-back an explicit checkpoint (workflow_clarity).

DimensionReasoningScore

Conciseness

The body is directive and avoids explaining concepts Claude already knows, but it restates the full 10-section structure and a complete frontmatter block inline while also pointing to `references/report-structure.md` and `references/report-naming.md` that hold the same detail, so it could be tightened.

2 / 3

Actionability

Concrete contracts are copy-paste ready — the filename pattern `YYYY-MM-DD--{experiment-line}--r{round}--{purpose}.md`, a filled-in frontmatter YAML block, explicit paths like `Results/Reports/{report-name}.md`, and specific next-action examples.

3 / 3

Workflow Clarity

A clearly sequenced 6-step workflow includes an explicit 'Hard gate' input check, a feedback loop that routes missing bundles back to `results-analysis`, and a 'Required quality bar' checklist.

3 / 3

Progressive Disclosure

The body is a clean overview with well-signaled one-level-deep references, but `examples/example-results-report.md` is referenced in the 'Reference files' list and does not exist, so one signaled navigation path is a broken link.

2 / 3

Total

10

/

12

Passed

Description

90%

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 explicit trigger guidance in both English and Chinese, a clear what-and-when structure, and a well-bounded niche relative to results-analysis. The only weakness is that its listed actions paraphrase a single capability rather than enumerating distinct operations.

DimensionReasoningScore

Specificity

Phrases like 'write an experiment report', 'summarize experimental results', and 'turning completed experiment artifacts into a structured, decision-oriented research report' name concrete actions, but they largely paraphrase one capability rather than listing distinct operations, so it sits at 'names domain and some actions' rather than the multi-action top anchor.

2 / 3

Completeness

It states what ('turning completed experiment artifacts into a structured, decision-oriented research report') and when ('should be used when the user asks to...'), with an explicit trigger clause, satisfying the 'both what AND when with explicit triggers' anchor.

3 / 3

Trigger Term Quality

Natural user phrasings are well covered — 'write an experiment report', 'summarize experimental results', 'do experiment retrospection', plus Chinese variants '写实验总结报告' and '写实验复盘' — matching the 'good coverage of natural terms' anchor.

3 / 3

Distinctiveness Conflict Risk

The niche is narrow and explicit — a post-experiment, decision-oriented research report that 'assumes strict analysis should come from `results-analysis` first' — so its triggers are unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
Galaxy-Dawn/claude-scholar
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.