author-contributions

Identify all files a specific author contributed to on a branch vs its upstream, tracing code through renames. Use when asked who edited what, what code an author contributed, or to audit authorship before a merge. This skill should be run as a subagent — it performs many git operations and returns a concise table.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%

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

A highly actionable, well-sequenced git-authorship audit skill with executable commands and a complete Python script, but it is held back by a redundant alternative script, absent validation/feedback checkpoints in the main workflow, and a long monolithic structure with no split-out bundle files.

Suggestions

Remove or justify the "Alternative Script" section: it duplicates the Python pipeline, carries a project-specific `src/vs/sessions/` exclusion that won't generalize, and contains a typo ("with an without").

Add explicit validation checkpoints in the workflow — e.g., abort with a clear message when step 1 finds no matching author, when `author_files` is empty, or when a rename chain cannot be resolved — so the process has a validate-and-recover feedback loop.

Move the example Python script(s) into a `scripts/` bundle file and reference it one level deep, keeping SKILL.md as a lean overview; this would lift progressive_disclosure toward a 3.

Dimension	Reasoning	Score
Conciseness	The core procedure is lean and command-driven, but the "Alternative Script" section (with its project-specific `grep -v '^src/vs/sessions/'` and a "with an without" typo) is largely redundant against the Python script, and author-matching guidance is repeated across steps and Important Notes — matching the level-2 anchor of mostly efficient with some unnecessary content rather than the every-token-earns-its-place level 3.	2 / 3
Actionability	Provides concrete, executable git commands for each step plus a complete copy-paste-ready Python script implementing the full pipeline, matching the level-3 anchor of fully executable code rather than the pseudocode level-2 example.	3 / 3
Workflow Clarity	The seven-step procedure is clearly sequenced and step 1 verifies the author identity, but there are no explicit validation/feedback checkpoints for failure modes (author with zero commits, empty rename map, broken chains), matching the level-2 anchor of steps listed but checkpoints missing/implicit rather than the validate-fix-retry level 3.	2 / 3
Progressive Disclosure	At roughly 180 lines this is a monolithic single file with no bundle files in references/scripts/assets; the full Python scripts are inlined when they could be split into a scripts/ file, matching the level-2 anchor of content that should be separate being inline rather than the level-3 clear-overview-with-one-level-deep-references pattern.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, third-person description that concisely states both the capability and concrete use-when triggers, with distinct natural-language keywords and no over-claims. It leaves little room for confusion about when this skill should engage.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions: "Identify all files a specific author contributed to on a branch vs its upstream, tracing code through renames" and "performs many git operations and returns a concise table", matching the level-3 anchor of multiple specific actions rather than the single-domain level-2 example.	3 / 3
Completeness	Explicitly answers both what ("Identify all files... tracing code through renames") and when ("Use when asked who edited what..."), with the explicit 'Use when...' clause required for a 3; it is not capped at 2.	3 / 3
Trigger Term Quality	Captures natural phrasing users would actually say — "who edited what", "what code an author contributed", "audit authorship before a merge" — giving good coverage of common variations rather than only technical jargon (level 2) or none (level 1).	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — per-author git contribution auditing against an upstream with rename tracing — with distinct triggers unlikely to fire for other skills; voice is third person ("Identify", not "I can" or "You can"), so no specificity penalty applies.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: posit-dev/positron
Path: .github/skills/author-contributions/SKILL.md
Commit: b87c504

Reviewed: 2 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.