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

83%

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

The canonical home for this skill is author-contributions in microsoft/vscode

Quality

Content

75%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 highly actionable, well-sequenced procedure with exact commands and a complete reference script. The main weaknesses are redundancy — the procedure is restated twice as scripts — and an Alternative Script section whose vague, typo'd intro and repo-specific path add noise without clear guidance.

Suggestions

Rewrite or remove the 'Alternative Script' section: fix its vague intro ("You can do this both with an without src/vs/sessions"), strip the repo-specific src/vs/sessions path, and explain when the shell alternative is preferable to the Python script.

Deduplicate the workflow: either present the numbered procedure with commands and let the Python script be the single implementation, or drop the per-step command repetition and lead with the script annotated by step.

Add explicit intermediate validation to the workflow — e.g., abort with a clear message if the author-matching step finds no commits, or if the rename map is empty — to turn implicit checkpoints into a feedback loop.

Dimension	Reasoning	Score
Conciseness	The numbered procedure is then re-implemented as a full Python script, and a third "Alternative Script" section adds a vague, typo'd intro ("You can do this both with an without src/vs/sessions") that leaks a repo-specific path. Mostly efficient, but the triplicated workflow and the alternative section's noise go beyond minor trimmings.	3 / 5
Actionability	Every step has an exact bash command (e.g., "git diff-tree --no-commit-id -r -M <hash>") and the Python script is complete and copy-paste executable, with placeholders limited to genuine parameters like author name and upstream ref.	5 / 5
Workflow Clarity	A clear 7-step sequence with an explicit identity-verification checkpoint ("Do not guess — short usernames won't match full display names") and solid edge-case notes (multi-hop renames, all-authors rename map). Validation of intermediate results (e.g., empty commit lists, malformed rename output) is implicit rather than an explicit feedback loop, keeping it below a 5.	4 / 5
Progressive Disclosure	No bundle files exist, and the single-file body has well-labeled sections with no nested references. However, the ~70-line inline script plus the redundant Alternative Script could be consolidated or split, leaving minor organization gaps.	4 / 5
	Total	16 / 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 strong description: third-person, concrete about both capability and usage triggers, and differentiated from related git skills. Trigger coverage is good but could add a few more natural synonyms.

Dimension	Reasoning	Score
Specificity	"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" list multiple concrete actions with comprehensive coverage, including the rename-tracing edge case and the output format.	5 / 5
Completeness	It explicitly answers both what ("Identify all files a specific author contributed to... tracing code through renames") and when ("Use when asked who edited what, what code an author contributed, or to audit authorship before a merge") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"who edited what", "what code an author contributed", and "audit authorship before a merge" are natural user phrasings with good synonym coverage, though common variants like "who wrote/touched/changed" or "commits by an author" are missing.	4 / 5
Distinctiveness Conflict Risk	The git authorship-audit niche is distinct from general git or code-review skills, and the trigger phrases (audit authorship before a merge, who edited what) are specific enough to pose minimal conflict risk.	5 / 5
	Total	19 / 20 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: b0258bc

Reviewed: 5 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.