learn-from-pr

Analyzes a completed PR to extract lessons learned from agent behavior. Use after any PR with agent involvement - whether the agent failed, succeeded slowly, or succeeded quickly. Identifies patterns to reinforce or fix, and generates actionable recommendations for instruction files, skills, and documentation.

Quality

79%

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 ./.github/skills/learn-from-pr/SKILL.md

Quality

Content

75%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 content is well-structured and actionable, with concrete gh commands, a clear six-step workflow, completion criteria, and illustrative examples. It stays lean without over-explaining basics, with only minor trim opportunities and the option to externalize examples into bundle files.

Dimension	Reasoning	Score
Conciseness	The body is dense with actionable tables, commands, and structured steps rather than explanations of concepts Claude already knows, though the three full worked examples and large pattern-mapping tables add length that could be trimmed slightly.	4 / 5
Actionability	Provides concrete executable commands (gh pr view/diff, find invocations) and a precise recommendation template (Category, Priority, Location, Specific Change, Why It Helps) with real file paths, but the XXXXX placeholder requires substitution, a minor gap.	4 / 5
Workflow Clarity	Six steps are clearly sequenced with a Completion Criteria checklist and an Error Handling table providing checkpoints; the skill is analysis-only (non-destructive), so the missing validate-then-retry feedback loop is not penalizing, leaving it just below the explicit-feedback-loop anchor of 5.	4 / 5
Progressive Disclosure	The single self-contained file is well organized into clearly headed sections (Inputs, Outputs, Workflow, Examples, Integration) with no nested multi-level references, though the sizable Examples and pattern-mapping tables are inlined rather than split into separate bundle files, a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

83%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 strong, explicitly covering both what the skill does and when to use it with concrete trigger scenarios and named output targets. Minor gaps in synonym coverage and slight overlap risk with adjacent PR skills keep specificity, trigger, and distinctiveness at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Analyzes a completed PR to extract lessons learned', 'Identifies patterns to reinforce or fix', 'generates actionable recommendations for instruction files, skills, and documentation') with named output targets, but 'lessons learned' and 'patterns' carry slight generality that keeps it just shy of fully comprehensive.	4 / 5
Completeness	Explicitly answers both what (analyze PR, extract lessons, identify patterns, generate recommendations) and when ('Use after any PR with agent involvement' with three concrete scenarios), matching the top anchor's requirement for clear trigger phrases.	5 / 5
Trigger Term Quality	Provides good natural trigger coverage via 'Use after any PR with agent involvement - whether the agent failed, succeeded slowly, or succeeded quickly', naming PR and agent scenarios users would say, though synonyms like 'post-mortem' or 'retrospective' are absent.	4 / 5
Distinctiveness Conflict Risk	The niche of extracting agent-behavior lessons from completed PRs is fairly distinct, but 'PR analysis' could overlap marginally with related PR skills (e.g. pr-finalize), so it is mostly distinct rather than conflict-free.	4 / 5
	Total	17 / 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: dotnet/maui
Path: .github/skills/learn-from-pr/SKILL.md
Commit: 90afade

Reviewed: ~17 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.