CtrlK
BlogDocsLog inGet started
Tessl Logo

github-deep-research

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on Github repository URL or open source projects.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

71%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, actionable skill body that leverages its bundle files appropriately and gives concrete commands. Its main weakness is the absence of explicit validation/checkpoint steps in the multi-round research workflow.

Suggestions

Add explicit validation checkpoints between research rounds (e.g., 'After Round 2: confirm 3+ credible sources identified; if not, expand queries before proceeding') to support a feedback loop.

Replace the '/path/to/skill/scripts/github_api.py' placeholder with the resolved relative path so commands are directly executable.

Consider moving the illustrative Mermaid examples into a separate reference file or trimming them, keeping only the inline guidance that earns its token cost.

DimensionReasoningScore

Conciseness

Efficient, sectioned, and assumes Claude's competence; minor padding in the illustrative Mermaid snippets and the source-prioritization list could be trimmed without losing value.

4 / 5

Actionability

Provides concrete executable commands ('python /path/to/skill/scripts/github_api.py <owner> <repo> summary') and an enumerated command list, plus copy-ready citation examples; the '/path/to/skill/' placeholder is the main gap.

4 / 5

Workflow Clarity

The four research rounds are clearly sequenced with per-round sub-steps, but there are no explicit validation checkpoints or feedback loops (verify -> fix -> retry) between rounds, which matters for a multi-step research workflow.

3 / 5

Progressive Disclosure

SKILL.md is a concise overview that points to real bundle files at one level of depth ('scripts/github_api.py', 'assets/report_template.md') with well-signaled references; minor organization gaps in inline Mermaid examples.

4 / 5

Total

15

/

20

Passed

Description

92%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 well-crafted description that is specific, third-person, and explicitly covers both capabilities and trigger conditions with a distinct GitHub-research niche. Only minor room for additional synonym coverage in trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('multi-round deep research', 'timeline reconstruction', 'competitive analysis', 'metrics analysis', 'Mermaid diagrams', 'structured markdown reports') with comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' ('Produces structured markdown reports...') and 'when' ('Use when users request...', 'Triggers on Github repository URL or open source projects') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural trigger phrases ('comprehensive analysis', 'timeline reconstruction', 'competitive analysis', 'in-depth investigation', 'GitHub repository URL', 'open source projects'); a few common variations like 'repo audit' or 'project history' are missing.

4 / 5

Distinctiveness Conflict Risk

Clear GitHub-research niche with distinct triggers (repo URL, open source projects, timeline reconstruction); minimal overlap risk with other skills.

5 / 5

Total

19

/

20

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

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
bytedance/deer-flow
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.