CtrlK
BlogDocsLog inGet started
Tessl Logo

issue-to-pr-resolver

Implement a GitHub issue end-to-end — create a worktree branch, implement the feature with tests, create a draft PR, then iteratively resolve all CI failures and review comments until the PR is clean. Use when you need to fully implement a GitHub issue from start to merge-ready. Triggers on "implement issue", "resolve issue", "/issue-to-pr-resolver <number>".

73

Quality

92%

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

96%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.

An excellent procedural skill body: fully executable commands, a clearly sequenced five-phase workflow with explicit CI/review validation loops and safety rules, and near-zero token waste. The only structural consideration is that some denser procedural detail (PR body construction, resolution-loop mechanics) could be moved to reference files to lighten the top-level SKILL.md.

DimensionReasoningScore

Conciseness

The ~110-line body is almost entirely exact commands and terse directives with no explanation of concepts Claude already knows; sections like the Rules block and PR-body instructions are maximally compressed, so every token earns its place.

5 / 5

Actionability

Nearly copy-paste-ready throughout: exact gh/git commands including the GraphQL review-thread query and resolveReviewThread mutation, PR-number extraction via grep -oE '[0-9]+$', and explicit handling of the git-ignored local/ directory. Placeholders like <COMMENT_ID> and <PRRT_...> are inherent dynamic substitution points, not missing detail.

5 / 5

Workflow Clarity

Five clearly sequenced phases with explicit validation checkpoints and a genuine feedback loop: gh pr checks --watch, a repeat-until-green resolution loop, re-check after each push, a 5-iteration cap before reporting blockers, and a rule never to mark ready without user request. This matches the top anchor with error-recovery loops.

5 / 5

Progressive Disclosure

No bundle files exist and nothing that belongs in a separate file is inlined — the single well-sectioned file with phase headers is appropriately structured. However, at ~105 lines it exceeds the under-50-line simple-skill exception and offers no one-level-deep references for its longer procedural detail (e.g., the PR-body construction or resolution-loop specifics), so it fits the good-structure-with-minor-gaps anchor rather than the clear-overview-with-references anchor.

4 / 5

Total

19

/

20

Passed

Description

88%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.

A strong description: it states a concrete multi-action pipeline (worktree, tests, draft PR, CI/review resolution loop) and gives explicit 'Use when' guidance with trigger phrases. The only weakness is slightly thin trigger coverage — a few natural synonyms for implementing or resolving GitHub issues are absent.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the full lifecycle — "create a worktree branch, implement the feature with tests, create a draft PR, then iteratively resolve all CI failures and review comments until the PR is clean" — with no meaningful coverage gaps, matching the comprehensive-coverage anchor rather than the minor-gaps anchor below it.

5 / 5

Completeness

It explicitly answers both what (end-to-end implementation through a clean, merge-ready PR) and when ("Use when you need to fully implement a GitHub issue from start to merge-ready" plus explicit trigger phrases), matching the top anchor; the anchor below would require a less explicit 'when'.

5 / 5

Trigger Term Quality

"Triggers on 'implement issue', 'resolve issue', '/issue-to-pr-resolver <number>'" provides natural phrases users would say, but common variations and synonyms (e.g., "fix issue", "close issue", "implement this issue end-to-end") are missing, fitting the good-coverage-with-a-few-gaps anchor rather than the comprehensive one.

4 / 5

Distinctiveness Conflict Risk

The end-to-end issue-to-merge-ready-PR niche is clear with distinct triggers, but "resolve issue" could overlap with general issue-triage or code-fix skills, so it fits the mostly-distinct/minor-overlap anchor rather than the minimal-conflict one.

4 / 5

Total

18

/

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.

Validation — 14 / 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.