pr-lifecycle

Complete issue → PR → merge lifecycle with readiness checks

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./.copilot/skills/pr-lifecycle/SKILL.md

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.

The body is highly actionable with a well-sequenced, validated workflow and concrete examples. Its main weaknesses are the inlined implementation/analysis section that hurts both conciseness and progressive disclosure.

Suggestions

Move the "Readiness Check Gaps & Recommendations" section (the JavaScript implementations and integration analysis) into a separate reference file and link to it one level deep.

Trim explanatory prose around the gap analysis; keep only the operational guidance an agent needs to pass the readiness checks.

Add a short "Quick start" overview near the top pointing to the detailed phase and readiness-check sections for navigation.

Dimension	Reasoning	Score
Conciseness	The procedure is mostly efficient, but the "Readiness Check Gaps & Recommendations" section inlines ~60 lines of JavaScript implementation plus analysis that is not needed to execute the lifecycle and could be trimmed or moved out.	3 / 5
Actionability	Copy-paste-ready bash commands, full commit/PR templates, and two complete worked examples (docs fix, SDK feature) cover the common cases with executable specifics.	5 / 5
Workflow Clarity	A clear 6-phase sequence with explicit validation checkpoints (pre-push safety check, build/test/lint, 11-item readiness checklist) and per-check Fix/Gotcha feedback loops for error recovery.	5 / 5
Progressive Disclosure	Sectioning is clear, but no bundle files exist and content that belongs in a separate file (the gap-analysis JS implementations) is inlined in the monolithic SKILL.md rather than split out with one-level-deep references.	3 / 5
	Total	16 / 20 Passed

Description

53%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 a clear purpose and reasonable trigger terms but omits any explicit "when to use" guidance, which limits completeness and trigger quality. It is fairly distinct within the workflow-skill niche.

Suggestions

Add an explicit "Use when…" clause naming concrete triggers (e.g. "Use when picking up a GitHub issue, opening a PR against the Squad repo, or fixing a failing readiness check").

Expand specificity by listing 1-2 more concrete actions (e.g. "runs all 11 PR readiness checks, squashes to a single commit, targets the dev branch").

Include synonyms like "pull request" alongside "PR" to improve natural-keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete stages ("issue → PR → merge lifecycle") plus "readiness checks", but the actions are high-level rather than a comprehensive list of specific capabilities.	3 / 5
Completeness	The "what" is clear (complete the issue→PR→merge lifecycle with readiness checks), but there is no "Use when…" clause or equivalent trigger guidance, which caps completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Relevant keywords like "issue", "PR", "merge", and "readiness checks" appear, but common variations/synonyms (e.g. "pull request", "review") are absent.	3 / 5
Distinctiveness Conflict Risk	The PR-lifecycle-with-readiness-checks niche is mostly distinct, with only minor overlap risk against closely related git-workflow skills.	4 / 5
	Total	13 / 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 (538 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: bradygaster/squad
Path: .copilot/skills/pr-lifecycle/SKILL.md
Commit: a0d2563

Reviewed: about 13 hours 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.