This is a strong skill description that concisely communicates specific capabilities, includes explicit trigger phrases, and clearly defines both what the skill does and when it should be used. The output fields are well-enumerated, and the trigger terms cover natural user language variations. It uses proper third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and outputs: listing PRs, returning titles, descriptions, repos, merge dates, and review counts. These are concrete, well-defined capabilities.	3 / 3
Completeness	Clearly answers both 'what' (list PRs with titles, descriptions, repos, merge dates, review counts) and 'when' (explicit 'Trigger on:' clause with specific phrases). Both are well-defined.	3 / 3
Trigger Term Quality	Includes natural trigger phrases users would actually say: 'list my PRs', 'my pull requests since', 'github contributions'. These cover common variations including abbreviations (PRs) and full terms (pull requests).	3 / 3
Distinctiveness Conflict Risk	Clearly scoped to a specific niche: listing user-authored PRs across repos since a date. The combination of GitHub PRs, authorship, date filtering, and specific output fields makes it highly distinctive and unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-crafted, concise skill that provides clear executable commands and a logical workflow for listing GitHub PRs. Its main weakness is the lack of inline error handling or validation checkpoints — the delegation to another skill for pagination and error handling is reasonable but leaves a gap if that skill is unavailable or if intermediate failures occur during the multi-repo iteration.

Suggestions

Add a brief validation checkpoint after Step 2 (e.g., 'If a repo returns an error, log a warning and continue with remaining repos; include failed repos in output').

Consider adding a fallback note for what to do if the delegated pagination skill is unavailable.

Dimension	Reasoning	Score
Conciseness	Every token earns its place. No unnecessary explanations of what GitHub PRs are or how `gh` CLI works. Inputs, prerequisites, and workflow are stated directly without padding.	3 / 3
Actionability	Provides fully executable `gh` CLI commands with specific flags and JSON output fields. The output format is shown as a concrete YAML example with realistic field values. Copy-paste ready.	3 / 3
Workflow Clarity	Steps are clearly sequenced (identify repos → fetch PRs → compile), but there's no validation or error handling within the workflow itself — errors and pagination are delegated to another skill without specifying what to do if that delegation fails or if `gh` commands return errors mid-batch.	2 / 3
Progressive Disclosure	For a skill of this size (~40 lines), the content is well-organized with clear sections (Inputs, Prerequisites, Workflow steps, Rules) and appropriately delegates pagination/error handling to a separate skill reference. No need for additional files.	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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Reviewed

1 day ago

Table of Contents

Discovery Implementation Validation