update-docs-from-commits

Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages. Use when docs have fallen behind code changes, after a batch of features lands, or when preparing a release. Trigger keywords - update docs, draft docs, docs from commits, sync docs, catch up docs, doc debt, docs behind, docs drift.

Quality

100%

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

100%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 a well-structured, actionable workflow with executable git/mise commands, a commit-to-doc mapping table, and an explicit build-and-verify step. It is concise without concept padding and appropriately organized as a single self-contained skill file.

Suggestions

Replace the Step 4 stub code block ('# Read the file') with a concrete command such as a Read/cat of the target .mdx path, so every code block is executable rather than a placeholder.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no generic concept explanations appear, and the long Step 5 rule list consists of project-specific style rules (Fern frontmatter, NVIDIA casing, no colons in titles) Claude could not know, so each token earns its place.	3 / 3
Actionability	Provides copy-paste-ready commands throughout ('git log v0.2.0..HEAD --oneline --no-merges', 'git show <commit-hash> --stat', 'mise run docs'), a concrete code-area-to-doc-page mapping table, and a result-summary template; the only soft spot is Step 4's stub '# Read the file' block, which is trivially obvious rather than a real gap.	3 / 3
Workflow Clarity	Seven clearly sequenced steps with an explicit validation/verification stage (Step 7: 'mise run docs', checking for warnings, broken cross-references, and PR-preview rendering) provide a feedback loop for this batch doc-editing operation.	3 / 3
Progressive Disclosure	No bundle files exist, and the single SKILL.md body is well organized into clear sections (Prerequisites, When to Use, Steps 1–7, Tips, Example Usage) with the one external reference (docs/CONTRIBUTING.mdx) signaled one level deep.	3 / 3
	Total	12 / 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, specific, and complete — it states concrete actions, an explicit 'Use when' clause, and a broad set of natural trigger keywords. It is clearly distinguishable from other documentation skills and carries no vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages' — matching the anchor for several specific concrete actions rather than just naming a domain.	3 / 3
Completeness	Explicitly answers both what (scan commits, draft/update doc pages) and when ('Use when docs have fallen behind code changes, after a batch of features lands, or when preparing a release'), with explicit trigger guidance rather than implied timing.	3 / 3
Trigger Term Quality	Provides broad natural trigger keywords users would actually say — 'update docs, draft docs, docs from commits, sync docs, catch up docs, doc debt, docs behind, docs drift' — giving good coverage rather than jargon or partial variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (mapping git commits to doc updates) with distinct triggers unlikely to fire for general doc-editing skills, so it is well distinguishable from sibling skills.	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: NVIDIA/OpenShell
Path: .agents/skills/update-docs/SKILL.md
Commit: deced87

Reviewed: 6 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.