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

82%

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

65%Weight 40%Scale 1-3

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

The body is highly actionable with executable code and method tables, but it is a monolithic API reference inflated with hype commentary and content Claude already knows. It lacks explicit verification feedback loops and does not split detail into one-level-deep reference files.

Suggestions

Remove hype padding ("forensic gold!") and drop the enumerated GitHub event-types table or move it to a reference file, since Claude already knows these event types.

Add an explicit validate->fix->retry checkpoint around evidence verification (e.g., "run store.verify_all(); if errors, fix the failing evidence and re-verify before exporting").

Extract the per-collector API reference, IOC types, and BigQuery credential setup into one-level-deep reference files and link to them from a concise overview in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient API reference and code, but padded with hype ("This is forensic gold!", "reveals force-pushed or deleted commits!") and a full enumerated table of standard GitHub event types that Claude already knows.	2 / 3
Actionability	Quick Start and per-collector sections give complete, executable Python with method-return-type tables; code is copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	A collect->store->verify sequence is shown and verification exists, but there are no explicit validation checkpoints or validate->fix->retry feedback loops for this accuracy-sensitive forensic process.	2 / 3
Progressive Disclosure	Sections are organized but the API reference, event-type catalog, and BigQuery setup are all inline in SKILL.md; no reference files exist and the only bundle script (init_investigation.py) is never referenced from the body.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 concise, third-person, and clearly answers both what the skill does and when to use it with an explicit trigger clause. It enumerates concrete actions and distinctive source-specific triggers with no vague fluff.

Dimension	Reasoning	Score
Specificity	"Generate, export, load, and verify forensic evidence" plus "Handles evidence storage, querying, and re-verification" lists multiple distinct concrete actions, matching the multiple-specific-actions anchor rather than a single domain+actions level.	3 / 3
Completeness	It states what ("Generate, export, load, and verify forensic evidence from GitHub sources") and an explicit "Use when..." trigger enumerating the source scenarios, clearly answering both what and when.	3 / 3
Trigger Term Quality	"GitHub API, GH Archive, Wayback Machine, local git repositories, or security vendor reports" gives good coverage of the natural terms a forensics user would actually say, beyond just one keyword.	3 / 3
Distinctiveness Conflict Risk	The GitHub-source forensics/verification niche with distinctive triggers (GH Archive, Wayback, vendor reports) is unlikely to conflict with generic skills.	3 / 3
	Total	12 / 12 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: 75f6956

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.