CtrlK
BlogDocsLog inGet started
Tessl Logo

github

GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.

94

1.30x
Quality

Does it follow best practices?

Impact

98%

1.30x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

An efficient, highly actionable gh CLI reference that assumes Claude's competence and is well organized. Its only gap is the absence of validation/confirmation checkpoints around destructive operations (merge, close, rerun).

Suggestions

Add an explicit pre-flight check before destructive commands — e.g. run `gh pr view <n> --json mergeable,reviewDecision` and confirm CI is green before `gh pr merge`, mirroring the validate-then-proceed pattern.

Add a brief confirmation/verification note for batch-ish or irreversible actions (issue close, run rerun), such as re-checking status after the action completes.

Reduce the light redundancy between the description's "NOT for" list and the body's "When NOT to Use" section by keeping the body version focused on command-routing guidance rather than restating scope.

DimensionReasoningScore

Conciseness

Lean command snippets with terse comments and no explanation of what GitHub/PRs/CI are; every token earns its place and it assumes Claude's competence.

3 / 3

Actionability

Fully executable, copy-paste-ready commands throughout — e.g. "gh pr checks 55 --repo owner/repo", "gh run view <run-id> --log-failed" — plus concrete --jq filter templates.

3 / 3

Workflow Clarity

Scoping (When to Use / NOT to Use) and the setup login→verify sequence are clear, but destructive operations like "gh pr merge 55 --squash", "gh issue close 42", and "gh run rerun" are shown with no pre-flight validation or confirmation checkpoint, which caps the score per the rubric.

2 / 3

Progressive Disclosure

A single self-contained reference with clearly organized sections (Setup, Common Commands sub-sections, Templates, Notes) and no nested/deep references; for a reference skill the inline command examples are appropriately placed.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-structured description that concisely states capabilities, provides explicit natural-language triggers, and bounds its scope with a clear exclusion list. It cleanly satisfies all four dimensions.

DimensionReasoningScore

Specificity

Enumerates multiple concrete actions — "issues, PRs, CI runs, code review, API queries" with explicit tasks like "checking PR status or CI", "creating/commenting on issues", "viewing run logs" — matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

Clearly states both what ("GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries") and when via an explicit "Use when:" clause with four numbered triggers plus a "NOT for" exclusion list.

3 / 3

Trigger Term Quality

Uses natural terms a user would actually say — "PR status", "CI", "issues", "PRs", "code review", "run logs" — giving broad coverage rather than just some relevant keywords.

3 / 3

Distinctiveness Conflict Risk

Scoped tightly to the `gh` CLI and GitHub, with a "NOT for" list excluding local git, non-GitHub repos, cloning, and code-change review, giving it a clear niche unlikely to conflict with other skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
trpc-group/trpc-agent-go
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.