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

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

77%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.

Highly actionable and exceptionally well-sequenced with strong validation feedback loops, but the body is monolithic and redundant, repeating the state machine across multiple sections and inlining templates/examples that could live in reference files.

Suggestions

Move the plan-comment, PR, and E2E-attestation heredoc templates into reference files (e.g. references/templates.md) and link to them, reducing inline bulk and enabling progressive disclosure.

Collapse the redundancy between the State Machine Overview ASCII tree, Steps 1–3, and Branches A–D into a single authoritative sequence, referencing it from the branches instead of restating it.

Move the six Example Usage walkthroughs into a separate references/examples.md, keeping only one or two short examples inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The 760-line body is mostly actionable but noticeably redundant — the state machine appears as an ASCII tree, is re-explained across Steps 1–3, re-expanded in Branches A–D, and then walked through again in six detailed examples — fitting 'mostly efficient but could be tightened' rather than the lean 4 or 5.	3 / 5
Actionability	Provides fully executable, copy-paste-ready gh/git commands, complete heredoc templates for plan comments and PRs, and concrete retry-loop commands covering the common cases, matching the top anchor.	5 / 5
Workflow Clarity	Clear sequenced Steps 1–14 with explicit validation checkpoints (conflict detection, scope check, retry loops with 'do not proceed if Phase 1 is not green'), feedback loops for error recovery, and checklists, matching the top anchor; the destructive/batch cap does not apply because validation is present.	5 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the entire workflow — state machine, all branches, comment/PR templates, command reference table, and six example walkthroughs — is inlined in one 760-line file with good headers but no file splitting, fitting 'some structure but content that should be separate is inline'.	3 / 5
	Total	16 / 20 Passed

Description

87%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, concrete description with explicit trigger keywords and a clear niche. It answers both what and when without vague fluff, though trigger-term synonyms could be marginally broader.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'plan and implement the work', 'Includes tests, documentation updates, and PR creation', plus queue processing via 'agent:*' labels — with only minor coverage gaps, fitting the 'lists several specific actions' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	Explicitly answers 'what' (plan and implement issue work, tests, docs, PR) and 'when' via concrete trigger phrases ('Trigger keywords - build from issue, implement issue...'), which is equivalent to a 'Use when...' clause with concrete triggers; not capped at 3 because explicit trigger guidance is present.	5 / 5
Trigger Term Quality	Provides five natural trigger phrases ('build from issue, implement issue, work on issue, build issue, start issue') that users would actually say, matching good keyword coverage; a few natural synonyms like 'fix issue' or 'resolve issue' are missing, keeping it below 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (building from GitHub issues) with distinctive trigger phrases and explicit routing of security issues away from this skill, giving minimal conflict risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (761 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	12 / 16 Passed

Repository: NVIDIA/OpenShell
Path: .agents/skills/build-from-issue/SKILL.md
Commit: 292559c

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.