github-evidence-kit

Generate, export, load, and verify forensic evidence from GitHub sources. Use when creating verifiable evidence objects from GitHub API, GH Archive, Wayback Machine, local git repositories, or security vendor reports. Handles evidence storage, querying, and re-verification against original sources.

Quality

83%

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

Quality

Content

78%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.

Highly actionable with executable examples and built-in verification, but it leans on a long inline API reference and fails to link the bundle scripts that actually ship with the skill, weakening progressive disclosure.

Suggestions

Move the collector method tables, evidence-type tables, and IOC-type enumeration into a separate REFERENCE.md and link to it from SKILL.md so the main file stays an overview.

Reference the bundled scripts/ingest_bq_events.py and scripts/init_investigation.py from the relevant sections (e.g. GH Archive and investigation setup) so shipped files are discoverable.

Render the collect → store → verify pipeline as numbered steps with an explicit 'if verification fails, fix and re-verify' feedback loop rather than a single flat code block.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean executable code and API tables, but a few editorializing lines ('Forensic gold!', 'Essential for forensic analysis', 'first-class forensic source') and minor parentheticals explaining concepts Claude already knows could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready import blocks, complete method signatures in tables, concrete collect/verify/save examples, and exact shell commands (pytest invocations, env-var exports) covering the common cases.	5 / 5
Workflow Clarity	The Quick Start sequences collect → store → save → verify_all, and verification against original sources is an explicit, prominent checkpoint, but the workflow is shown as flat code rather than numbered steps with documented fix-and-re-verify feedback loops.	4 / 5
Progressive Disclosure	Sections are clearly headed, but a large amount of API reference (collector method tables, evidence-type tables, the full IOC-type enumeration) is inlined rather than split into a separate reference file, and the existing bundle scripts (scripts/ingest_bq_events.py, scripts/init_investigation.py) are never referenced from the body.	3 / 5
	Total	16 / 20 Passed

Description

88%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, well-structured description that explicitly covers both capability and trigger conditions with concrete source names. Trigger-term coverage is good but could add a few more natural synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Generate, export, load, and verify forensic evidence' plus 'Handles evidence storage, querying, and re-verification' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ('Generate, export, load, and verify forensic evidence') and when ('Use when creating verifiable evidence objects from GitHub API, GH Archive...'), matching the top anchor's structure.	5 / 5
Trigger Term Quality	Names concrete natural sources users would cite — 'GitHub API, GH Archive, Wayback Machine, local git repositories, or security vendor reports' — but a few common phrasings/synonyms (e.g. 'deleted GitHub content', 'git history') are absent.	4 / 5
Distinctiveness Conflict Risk	The GitHub-forensics framing is a clear niche with distinct triggers, but minor overlap risk remains with general git or OSINT skills that also touch repositories and archived content.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: gadievron/raptor
Path: .claude/skills/oss-forensics/github-evidence-kit/SKILL.md
Commit: 4e75ac9

Reviewed: 4 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.