build-from-issue

Given a GitHub issue number, plan and implement the work described in the issue. Supports direct user requests and unattended queue processing through the `agent:*` workflow labels. Includes tests, documentation updates, and PR creation. Trigger keywords - build from issue, implement issue, work on issue, build issue, start issue.

Quality

90%

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

81%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.

The body is highly actionable with an exceptionally clear, validation-gated workflow and concrete commands throughout. Its main weakness is conciseness — the file is long and repeats label-handling rationale — and progressive disclosure could be improved by moving the commands reference and examples into bundled reference files.

Suggestions

Consolidate the repeated direct-vs-queue `agent:*` label philosophy into one authoritative section and cross-reference it from Step 1, the state machine, and Branch C to cut length.

Move the "Useful Commands Reference" table and the four "Example Usage" walkthroughs into a bundled references file (e.g. references/usage.md) and link to it from the body, improving progressive disclosure.

Tighten or remove the full heredoc plan/PR/comment templates in favor of the essential fields, relying on Claude to format the boilerplate.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural guidance but is long (~750 lines) and repeats the direct-vs-queue label philosophy across Step 1, the state machine, and Branch C; the four worked examples and full plan/PR templates add length that could be tightened or split out.	3 / 5
Actionability	Provides copy-paste-ready `gh`/`git` commands with heredoc-templated comments and concrete placeholders (e.g. `gh issue view <id> --json ...`, the plan-comment and PR bodies), covering the common cases fully.	5 / 5
Workflow Clarity	A clear decision-tree state machine plus sequenced Steps 1–14 with explicit validation checkpoints — conflict detection (Step 5) and the retry-loop verification in Step 10 with "do not proceed if not green" feedback loops — match the top anchor.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections and branches, but it is a single monolithic file with no bundle references; the commands-reference table and example-usage block could live in separate reference files, leaving minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

100%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.

The description is strong across all dimensions: it states concrete actions, supplies explicit natural trigger keywords, answers both what and when, and occupies a distinct niche. It is written in third person with no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "plan and implement the work", "tests, documentation updates, and PR creation" — giving comprehensive coverage of the skill's workflow, matching the anchor for listing multiple specific concrete actions.	5 / 5
Completeness	Clearly answers what ("plan and implement... Includes tests, documentation updates, and PR creation") and when (explicit trigger keywords), satisfying the anchor for both with concrete trigger phrases.	5 / 5
Trigger Term Quality	Explicit "Trigger keywords - build from issue, implement issue, work on issue, build issue, start issue" provides comprehensive natural-term coverage with synonyms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The GitHub-issue scope plus "unattended queue processing through the `agent:*` workflow labels" carves a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (759 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: NVIDIA/OpenShell
Path: .agents/skills/build-from-issue/SKILL.md
Commit: 69a05eb

Reviewed: 1 day 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.