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

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

65%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 an appropriately lean pointer to a well-organized reference bundle with excellent progressive disclosure, but it offloads nearly all actionable detail and validation to the reference, leaving inline actionability and workflow checkpoints thin.

Suggestions

Add 2–3 inline concrete anchors — e.g. the branch naming pattern, the commit message format, and a one-line PR body self-identification snippet — so Claude has immediate executable guidance before opening the reference.

State an explicit validation checkpoint in the body (e.g. 'verify CI is green and the PR body template is complete before `gh pr create`') to satisfy the destructive/batch validation expectation inline.

De-duplicate the 'do not run git commit / gh pr create' prohibition against the frontmatter warning to avoid restating the same constraint twice.

Dimension	Reasoning	Score
Conciseness	The body is short (~68 words) and avoids explaining concepts Claude already knows, but the second paragraph re-states a prohibition ('Do NOT run git commit...') that partly overlaps the frontmatter's warnings; minor trimming possible.	4 / 5
Actionability	It gives one concrete action (read pull-request-workflow.md via view_file) and an absolute prohibition, but provides no inline executable steps, command examples, or commit/PR-body specifics — everything actionable is deferred to the reference.	3 / 5
Workflow Clarity	A rough two-step sequence exists (read the reference, then do not commit/create without it), but there are no explicit validation checkpoints in the body and the destructive-batch cap applies because commits/PR creation lack inline validation guidance.	3 / 5
Progressive Disclosure	The body is a lean overview that points to a single real one-level-deep reference (pull-request-workflow.md, confirmed present in references/) with clear signaling and no nested indirection; content is appropriately split.	5 / 5
	Total	15 / 20 Passed

Description

71%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 conveys both purpose and triggers with concrete PR-specific actions, but it is overstuffed with internal warnings and jargon that dilute the core trigger signal and create overlap with sibling review skills.

Suggestions

Front-load the 'Use when' trigger clause (e.g. 'Use when code modifications are complete and you are about to open a pull request') before the warnings so the activation signal is immediate.

Trim internal-only jargon like 'A2A commentId hand-off', 'substrate/runtime-AC', and the 'MANDATORY ROI WARNING' from the description; move those specifics into the reference body.

Add the plain synonym 'pull request' as an explicit trigger term and add a one-line action summary so the 'what' reads as a clean capability list.

Dimension	Reasoning	Score
Specificity	Names the PR domain and several concrete sub-actions ('stepping-back reflection, commit format, cross-family review mandate, A2A commentId hand-off'), but coverage is padded with operational warnings rather than a clean action list.	4 / 5
Completeness	Both the 'what' (PR guidelines and execution flow) and the 'when' ('Triggers: Code modifications complete; before opening PR') are present and explicit, but the triggers are buried after multiple warning clauses rather than cleanly foregrounded.	4 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('Code modifications complete', 'before opening PR') plus technical terms, but lacks the common plain-language synonym 'pull request' as a trigger and mixes in internal jargon ('A2A commentId hand-off', 'substrate/runtime-AC').	4 / 5
Distinctiveness Conflict Risk	The niche is fairly distinct (PR opening workflow) but the heavy mix of cross-cutting mandates (cross-family review, A2A hand-off, substrate awareness) overlaps with broader review/handoff skills and risks triggering for adjacent review tasks.	3 / 5
	Total	15 / 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: neomjs/neo
Path: .agents/skills/pull-request/SKILL.md
Commit: 210c03c

Reviewed: 4 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.