pull-request

Standardized guidelines and procedural execution flow for opening a Pull Request. CRITICAL: Do NOT run default `npx playwright test` (use custom configs). MANDATORY ROI WARNING: Skipping the PR body template guarantees CI lint failure. Triggers: Code modifications complete; before opening PR — stepping-back reflection, commit format, cross-family review mandate, post-comment A2A commentId hand-off (author→reviewer) per review-response-protocol.md §14, Evidence declaration line for substrate/runtime-AC PRs per [evidence-ladder.md](learn/agentos/process/evidence-ladder.md).

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/pull-request/SKILL.md

Quality

Content

72%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 an exemplary lean pointer that offloads detail to a single, real reference file with clear guardrails, scoring well on conciseness and progressive disclosure. It is weaker on actionability and workflow clarity because the body itself contains no executable PR examples, validation steps, or multi-step sequence — all are deferred to the reference.

Suggestions

Add a brief inline summary of the core PR workflow steps or a minimal copy-pasteable commit/PR command example so the body is actionable before the reference is read.

Surface the other bundle files (e.g. review-response-protocol.md, the review-response-template.md asset) directly from the body or a short index so navigation does not require digging through the main reference.

Add an explicit validation checkpoint in the body (e.g. 'confirm CI is green before gh pr create') since the gated commands are semi-destructive.

Dimension	Reasoning	Score
Conciseness	The body is a lean five-line pointer that assumes Claude's competence and gives only guardrails ('Do NOT run git commit or gh pr create without first reading the reference payload'); every token earns its place with no concept explanation.	3 / 3
Actionability	Gives some concrete guidance (specific 'view_file' tool, an explicit reference path, forbidden commands 'git commit' / 'gh pr create') but the executable PR-creation detail is deferred entirely to the reference, so key details and examples are missing from the body itself.	2 / 3
Workflow Clarity	A clear read-first-then-act gate is present ('MUST immediately use the view_file tool to read ... before proceeding'), but the full multi-step PR workflow and any validation/feedback checkpoints live in the reference, and destructive commands (git commit, gh pr create) lack an inline verification step, capping this at 2.	2 / 3
Progressive Disclosure	The body is a clean overview with a single well-signaled one-level-deep reference (references/pull-request-workflow.md, which exists) and content appropriately split out of the overview; the heavier workflow correctly lives in the reference file.	3 / 3
	Total	10 / 12 Passed

Description

85%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 specific and complete, clearly stating what the skill does and when to use it with an explicit trigger clause. Its main weakness is trigger-term quality: much of the text is internal jargon and emphatic padding ('CRITICAL', 'MANDATORY ROI WARNING', 'guarantees CI lint failure') rather than natural user phrasing.

Suggestions

Replace internal jargon ('A2A commentId hand-off', 'substrate/runtime-AC PRs', 'cross-family review mandate') with plain trigger phrasing a user would actually say.

Drop emphatic padding and over-claims ('CRITICAL', 'MANDATORY ROI WARNING', 'guarantees CI lint failure') to improve clarity and reduce token cost.

Fix or remove the broken frontmatter link to evidence-ladder.md, which does not exist in the skill bundle.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete PR actions — 'stepping-back reflection, commit format, cross-family review mandate, ... A2A commentId hand-off ... Evidence declaration line' — matching the anchor for several specific concrete actions.	3 / 3
Completeness	Answers both what ('Standardized guidelines and procedural execution flow for opening a Pull Request' plus steps) and when with an explicit trigger clause ('Triggers: Code modifications complete; before opening PR'), so it is not capped at 2.	3 / 3
Trigger Term Quality	Includes some natural terms a user would say ('Pull Request', 'PR', 'opening a PR', 'commit format') but is dominated by internal jargon ('A2A commentId hand-off', 'substrate/runtime-AC PRs', 'cross-family review mandate') users would not naturally say, missing common variations.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (opening a Pull Request) with distinct triggers ('before opening PR') making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: neomjs/neo
Path: .agents/skills/pull-request/SKILL.md
Commit: b4a1b58

Reviewed: 8 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.