github-repo-signals

Extract and score leads from GitHub repositories by analyzing stars, forks, issues, PRs, comments, and contributions. Produces unified multi-repo CSV with deduplicated user profiles. No paid API credits required.

Quality

69%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/lead-generation/packs/lead-gen-devtools/github-repo-signals/SKILL.md

Quality

Content

67%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.

The body is well-structured and actionable, delegating implementation to bundled scripts and giving concrete commands, tables, and a sequenced workflow with explicit checkpoints. It could be tighter in the analysis/recommendation sections, which contain some restated guidance.

Suggestions

Trim the analyze/recommend section by removing restated commentary (e.g. 'This is the highest-signal segment', 'These are potential advocates, not just buyers') and keep only the actionable instructions.

Add a brief validation step after Step 2 (e.g. confirm the two CSV files exist and are non-empty before proceeding to analysis) to close the minor workflow gap.

Consider moving the detailed scoring-weight table and column schemas into a referenced reference file so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The execution steps and column tables are efficient, but the analyze/recommend sections (Steps 5–8) contain restated or padded guidance such as 'This is the highest-signal segment' and 'These are potential advocates, not just buyers' that could be trimmed without losing clarity.	3 / 5
Actionability	Provides a concrete executable command with real flags, full output column tables, explicit scoring weights, and real output paths; only minor gaps (env-var substitution and limit value) remain before copy-paste readiness.	4 / 5
Workflow Clarity	A clear numbered Step 1–8 sequence with explicit checkpoints ('Do NOT proceed until you have this context', 'Wait for user confirmation before spending any credits'); the CSV extraction is non-destructive, so the missing post-run validation is a minor gap rather than a cap.	4 / 5
Progressive Disclosure	Well-organized sections with the heavy extraction logic delegated to a real bundled script (scripts/gh_repo_signals.py exists) at one level of depth; inline column docs and analysis guidance are appropriate for an overview, with only minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

71%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.

The description is specific and distinctive about what the skill does, but it omits an explicit 'Use when' trigger clause, which limits its completeness and leaves the activation context implicit. Trigger terms are good but lack natural-speech synonyms.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases such as 'find leads from GitHub repos', 'GitHub lead generation', or 'identify prospects from open-source repositories'.

Include natural user phrasings alongside the technical interaction types so the trigger terms match what a user would actually say.

Consider naming the output deliverable format (e.g. '.csv') in the description to improve trigger-term file-extension coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Extract and score leads', 'analyzing stars, forks, issues, PRs, comments, and contributions', 'Produces unified multi-repo CSV with deduplicated user profiles' — with comprehensive coverage of the domain.	5 / 5
Completeness	The 'what' is clearly stated (extract/score leads, produce deduplicated CSV) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Good keyword coverage ('GitHub repositories', 'leads', 'stars, forks, issues, PRs') but missing common natural-speech synonyms a user would say (e.g. 'find leads from GitHub', 'GitHub lead generation') and any file extensions, so it stops short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche — GitHub lead signal extraction into a unified CSV — that is distinguishable from most skills, with only minor overlap risk against generic GitHub-related skills.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/lead-generation/packs/lead-gen-devtools/github-repo-signals/SKILL.md
Commit: 2523432

Reviewed: 7 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.