CtrlK
BlogDocsLog inGet started
Tessl Logo

github-pr-query

Query GitHub pull requests with jq filtering and reusable selectors.

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/github-pr-query/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 copy-paste-ready commands and clear option documentation, but it is somewhat verbose with redundant example queries and references a script that does not exist as a bundled file, capping conciseness and progressive disclosure.

Suggestions

Trim the redundant jq example queries; consolidate overlapping examples to reduce token load.

Provide the referenced './query-prs.sh' as a bundled script in ./scripts/ so the cited path is real and verifiable.

Condense the 'jq Parameter is Optional' section; the default-schema behavior can be a one-line note in the options list.

DimensionReasoningScore

Conciseness

It is mostly efficient with lean code examples, but the long sequence of nearly redundant jq example queries and the 'Important: jq Parameter is Optional' section pad the body beyond what is essential.

2 / 3

Actionability

It provides many fully executable, copy-paste-ready command examples with concrete jq expressions and a documented options list, hitting the 'fully executable / specific examples' anchor.

3 / 3

Workflow Clarity

This is a simple single-task skill (run the script with flags); the single action is unambiguous, options are documented, and the per-rubric note allows simple skills to score 3 here.

3 / 3

Progressive Disclosure

The body is well-organized into clear sections, but there are no bundle files (references/scripts/assets) despite the body referencing './query-prs.sh', so the referenced path cannot be verified as a real bundled file.

2 / 3

Total

10

/

12

Passed

Description

50%

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 and on-domain but reads as a one-line capability statement lacking an explicit 'Use when...' trigger and natural-term coverage (PRs, GitHub PRs). It is solid but not exemplary.

Suggestions

Add an explicit trigger clause, e.g. 'Use when querying or filtering GitHub pull requests, finding PRs by author/state/label, or inspecting PR review status.'

Broaden trigger terms to include 'PRs', 'GitHub PRs', and 'review status' so it matches natural user phrasing.

List one or two concrete additional actions (e.g. count PRs by state, find PRs awaiting review) to raise specificity.

DimensionReasoningScore

Specificity

Quotes 'Query GitHub pull requests' and 'jq filtering and reusable selectors' — it names the domain and some actions but does not enumerate multiple concrete capabilities (e.g., filter, count, find large PRs).

2 / 3

Completeness

It states what the skill does but has no 'Use when...' trigger clause, so per the guidelines completeness is capped at 2.

2 / 3

Trigger Term Quality

'pull requests', 'jq filtering', and 'selectors' are relevant, but it omits common variations users say like 'PRs', 'GitHub PRs', or 'review PRs'.

2 / 3

Distinctiveness Conflict Risk

It is fairly specific to GitHub PRs, but could overlap with general GitHub or code-review skills without a clearer niche trigger.

2 / 3

Total

8

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
github/gh-aw
Reviewed

Table of Contents

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.