CtrlK
BlogDocsLog inGet started
Tessl Logo

my-pr-checker

Manage your own GitHub pull requests — check CI status, inline review comments, PR-level comments, resolve review threads, fix issues, and iterate until all checks pass and threads are resolved. Use for managing your own PRs (not external contributions). Triggers on "check my PR", "check PR", "/my-pr-checker <number>".

72

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 an efficient, actionable PR-management workflow with strong sequencing and validation checkpoints, largely free of padding. Its only weak spots are unspecific placeholders in the gh API examples and a lack of any progressive file split.

Suggestions

Replace abstract placeholders (<COMMENT_ID>, <PRRT_...>, [commit], [description]) with concrete captured-variable examples or a short note showing how to extract the real value from the prior command's JSON/JQ output.

Add a one-line note in Step 4 on how to obtain the GraphQL threadId (e.g., the id field returned by the reviewThreads query in Step 1) so the resolve mutation is fully executable.

Consider moving the Special Operations rebase/recreate/delete recipes into a referenced file or a clearly marked appendix to keep the main workflow path uncluttered.

DimensionReasoningScore

Conciseness

The body is lean — almost entirely executable commands and terse decision criteria — with no padding explaining what a PR or gh is; even rationale is compressed to one-liners like 'Why: Unresolved threads block merging even after approval.'

5 / 5

Actionability

Concrete, copy-paste-ready gh commands and GraphQL queries cover the common cases, but placeholders such as <COMMENT_ID>, <PRRT_...>, [commit], and [description] require manual substitution, leaving minor gaps.

4 / 5

Workflow Clarity

A clear 6-step sequence with an explicit feedback loop ('Repeat Steps 1–5 until: All CI checks green, All review threads resolved, No new blocking comments') and validation via re-checking CI; the 3-attempt cap and 'NEVER merge automatically' rule add safety for destructive/batch operations.

5 / 5

Progressive Disclosure

Well-organized into clearly headed sections (Step 1–6, Special Operations, Rules) in a single self-contained file with no nested references; no bundle files are needed or present, though at over 50 lines it is not a minimal simple skill.

4 / 5

Total

18

/

20

Passed

Description

92%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, complete, and well-bounded, clearly stating both the capability set and the trigger conditions with an explicit scope exclusion. It is only slightly short of perfect trigger-term synonym coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'check CI status, inline review comments, PR-level comments, resolve review threads, fix issues, and iterate until all checks pass and threads are resolved' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both what ('Manage your own GitHub pull requests — check CI status... iterate until all checks pass') and when ('Use for managing your own PRs (not external contributions). Triggers on...').

5 / 5

Trigger Term Quality

Includes natural trigger phrases users would say ('check my PR', 'check PR', '/my-pr-checker <number>'), but lacks common synonyms like 'review my PR' or 'my pull request' for full coverage.

4 / 5

Distinctiveness Conflict Risk

Clear niche — managing the user's own PRs with an explicit boundary ('not external contributions') — minimizes overlap with general code-review or external-contribution skills.

5 / 5

Total

19

/

20

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
homeassistant-ai/ha-mcp
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.