CtrlK
BlogDocsLog inGet started
Tessl Logo

github-review-follow-up

Inspect unresolved GitHub pull request review threads, group actionable feedback, implement selected fixes locally, and only reply or resolve threads after explicit user intent.

65

Quality

77%

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 ./examples/plugin-packages/github/.opencode/skills/github-review-follow-up/SKILL.md
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.

The body is concise, well-organized, and actionable with concrete service-action names and clear write-safety guardrails. The main gap is the lack of an explicit feedback loop (run tests, fix failures, re-run, only then resolve) for a batch/outward-facing operation, which caps workflow clarity.

Suggestions

Add an explicit feedback loop in the workflow, e.g. after step 7: if tests fail, fix and re-run before proceeding, and only resolve a thread once its change passes tests.

Make the validation gate for resolving threads explicit, e.g. a step stating "Re-run the narrowest tests and confirm they pass before calling resolve-review-thread."

Consider a short note on how to handle partial completion (some items fixed, others blocked) so remaining-work summarization is consistent.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what a PR or review thread is, and every line (workflow steps, write-safety rules) earns its place, matching the score-3 anchor of lean, efficient content.

3 / 3

Actionability

It names concrete GitHub service actions ("pull-request-detail", "review-threads", "resolve-review-thread"), explicit triage buckets, and a concrete test step; for an instruction-only skill this specific, actionable guidance meets the score-3 bar without requiring code.

3 / 3

Workflow Clarity

A clear 7-step sequence with a triage checkpoint and a test step is present, but there is no explicit validate-fix-retry feedback loop for the batch/destructive operation of posting comments and resolving threads; per the guideline, missing feedback loops in such contexts cap workflow_clarity at 2.

2 / 3

Progressive Disclosure

At under 50 lines with no need for external references, the well-organized Workflow and Write-safety sections satisfy the score-3 allowance for simple skills without requiring bundle files.

3 / 3

Total

11

/

12

Passed

Description

67%

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 well-scoped to GitHub PR review follow-up with a strong distinctiveness profile. Its weakness is the absence of an explicit "Use when..." trigger clause and broader natural trigger terms, which caps both completeness and trigger_term_quality.

Suggestions

Add an explicit "Use when..." clause naming common user phrasings, e.g. "Use when the user asks to address PR review comments, requested changes, or unresolved review threads on a GitHub pull request."

Broaden trigger terms to include natural variations users say, such as "PR comments", "code review feedback", and "review nits".

Keep the existing gating language ("only reply or resolve threads after explicit user intent") as it strongly supports distinctiveness.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Inspect unresolved GitHub pull request review threads", "group actionable feedback", "implement selected fixes locally", "only reply or resolve threads after explicit user intent" — matching the score-3 anchor that expects several specific concrete actions.

3 / 3

Completeness

It clearly states what the skill does, but the "when" is only implied by the actions and there is no explicit "Use when..." clause; per the guideline a missing explicit trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

It surfaces natural terms like "GitHub pull request review threads" and "review feedback", but omits common variations users would say ("PR comments", "code review feedback", "review nits") and provides no enumerated trigger list, so it sits at the score-2 anchor of some relevant keywords missing common variations.

2 / 3

Distinctiveness Conflict Risk

The niche is narrowly scoped to GitHub PR review-thread follow-up with a clear gating behavior (reply/resolve only after explicit intent), making it unlikely to trigger for unrelated skills.

3 / 3

Total

10

/

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
Devin-AXIS/iPolloWork
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.