chained-pr

Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./internal/assets/skills/chained-pr/SKILL.md

Quality

Content

71%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 concise, well-structured, and uses progressive disclosure effectively with a real one-level reference. Its weakest area is actionability: executable commands and examples live entirely in the reference rather than being surfaced for the common cases.

Suggestions

Inline one or two key commands for the common case (e.g., the `gh pr create --base ...` command for opening a chained child PR) so the body is actionable without opening the reference.

Add an explicit error-recovery feedback loop in Execution Steps for a polluted diff (detect -> retarget/rebase -> re-verify clean diff) to push workflow clarity toward 5.

Surface a minimal example of the Chain Context dependency diagram inline so the 📍-marking convention is visible without navigating to the reference.

Dimension	Reasoning	Score
Conciseness	A lean, well-organized body with no over-explanation of concepts Claude already knows; every section earns its place, with only minor phrasing that could be trimmed, fitting the 4-anchor over the 3-anchor.	4 / 5
Actionability	Provides concrete structural rules and a decision table, but no executable commands or examples inline — all commands and templates are deferred to the reference file, leaving the body more instructive than copy-paste executable.	3 / 5
Workflow Clarity	Execution Steps are clearly sequenced with an explicit verification step (step 5) and a feedback cap on the slicing pass; validation is present so the destructive/batch cap at 3 does not apply, but error-recovery detail is lighter than the 5-anchor.	4 / 5
Progressive Disclosure	Clear overview body with a single well-signaled, one-level-deep reference (references/chaining-details.md, a real file) that holds the diagrams, commands, and PR template; content is appropriately split and easy to navigate.	5 / 5
	Total	16 / 20 Passed

Description

73%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 specific, has explicit trigger guidance, and occupies a distinctive niche with low conflict risk. Its main weakness is specificity, where it names the domain and a few actions but does not comprehensively list multiple concrete capabilities.

Suggestions

Expand the 'what' clause to list more concrete actions (e.g., 'split oversized changes, stack slices against main, build feature-branch chains with a tracker PR') to raise specificity.

Reframe 'Trigger:' as a 'Use when...' clause and add common synonyms users say (e.g., 'large PR', 'reviewable PR', 'PR splitting') to broaden trigger coverage.

Optionally add the 400-line threshold phrasing a maintainer would naturally say ('PR is too big to review') to strengthen trigger-term naturalness.

Dimension	Reasoning	Score
Specificity	Names the domain and a couple of concrete actions ('Split oversized changes into chained PRs', 'stacked PRs, review slices') but does not enumerate multiple distinct concrete actions, fitting the 3-anchor better than the 4-anchor's 'several specific actions'.	3 / 5
Completeness	Explicitly states both what ('Split oversized changes into chained PRs that protect review focus') and when ('Trigger: PRs over 400 lines, stacked PRs, review slices'), but the trigger phrasing ('Trigger:') is slightly less explicit than 'Use when...'.	4 / 5
Trigger Term Quality	Includes natural user phrases ('PRs over 400 lines', 'stacked PRs', 'review slices') with good keyword coverage; falls just short of the 5-anchor's comprehensive synonyms and file-extension inclusion.	4 / 5
Distinctiveness Conflict Risk	A clear niche (chained/stacked PRs for review-load control) with specific, distinctive triggers that are unlikely to fire for unrelated skills, matching the 5-anchor.	5 / 5
	Total	16 / 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: Gentleman-Programming/gentle-ai
Path: internal/assets/skills/chained-pr/SKILL.md
Commit: 71cf25f

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.