CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

address-github-comments

Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.

Quality

71%

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 ./.agents/skills/address-github-comments/SKILL.md

The canonical home for this skill is address-github-comments in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

65%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 body is well-structured for a simple single-file skill with several copy-paste-ready gh commands, but it is held back by boilerplate padding, a missing validation/feedback loop before announcing fixes, and no concrete command for the skill's central act — replying to and resolving individual review threads. Tightening the filler and adding thread-reply mechanics would lift conciseness, actionability, and workflow clarity together.

Suggestions

Delete the circular "When to Use" and boilerplate "Limitations" sections (trigger guidance belongs in the frontmatter description) and the filler sentence "This skill ensures all feedback is addressed systematically".

Add a concrete command for replying to a specific review thread and resolving it (e.g., the GraphQL mutation via `gh api graphql` or `gh pr review --comment`), since `gh pr comment` only posts a general PR comment.

Insert a validation checkpoint between applying fixes and responding — e.g., run tests or check `gh pr checks` and only post "Addressed in latest commit" once they pass.

DimensionReasoningScore

Conciseness

The workflow steps and commands are lean, but the body carries unnecessary padding: "This skill ensures all feedback is addressed systematically", and the circular "When to Use" section ("applicable to execute the workflow or actions described in the overview") plus generic boilerplate "Limitations" add ~8 lines of no value. This is more than minor trimming, so it sits at 3 rather than 4.

3 / 5

Actionability

Most steps have concrete, executable commands ("gh auth status", "gh auth login", "gh pr view --comments", "gh pr comment <PR_NUMBER> --body \"...\""). It is not a 5 because the core final step — replying to and resolving a specific review thread — has no command, and the given `gh pr comment` posts a general PR comment rather than a threaded reply or resolution.

4 / 5

Workflow Clarity

A clear 4-step sequence exists (inspect → categorize/plan → apply → respond) with one checkpoint ("Wait for user confirmation"), but there is no validation of the applied fixes (e.g., running tests or checking CI) before declaring comments "Addressed in latest commit". Since addressing multiple review comments is a batch operation, the rubric's batch-operation cap limits this to 3.

3 / 5

Progressive Disclosure

This is a short (~59-line) single-file skill with no bundle files and no content that belongs in separate references; sections (Overview, Prerequisites, Workflow, Common Mistakes) are cleanly organized and easy to navigate. Per the rubric's simple-skill note, well-organized sections with no need for external references merit a 5.

5 / 5

Total

15

/

20

Passed

Description

65%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 has a clear, explicit trigger and a well-scoped niche, but its capability statement is thin: one action phrased in second person with no enumeration of what the skill actually does (fetch, plan, fix, reply, resolve). Rewriting in third person with 2-3 concrete actions would raise both specificity and completeness.

Suggestions

Rewrite the capability statement in third person and enumerate the concrete actions, e.g., "Fetches, triages, and resolves GitHub PR review and issue comments via the gh CLI: inspect threads, propose and apply fixes, and reply to reviewers."

Add natural trigger variations such as "PR feedback", "respond to review comments", or "resolve review threads" so users' phrasing matches more readily.

State the what and when as two distinct parts: a lead sentence of capabilities followed by a separate "Use when..." sentence with concrete trigger phrases.

DimensionReasoningScore

Specificity

The description names the domain and a single action ("address review or issue comments on an open GitHub Pull Request using the gh CLI"), which matches the anchor for naming domain plus 1-2 actions (3), but it is phrased in second person ("Use when you need to"), which the guidelines penalize by reducing specificity by 1. It does not list several specific actions, so it cannot reach 4.

2 / 5

Completeness

It has an explicit "Use when..." trigger clause and the action is stated ("address review or issue comments... using the gh CLI"), so both what and when are present. It is not a 5 because the what is only embedded inside the when clause and the trigger could be more specific (e.g., mentioning responding to PR feedback or resolving review threads).

4 / 5

Trigger Term Quality

It includes natural terms users would say such as "review", "issue comments", "GitHub", "Pull Request", and "gh CLI", giving good keyword coverage. It falls short of 5 because common variations like "PR feedback", "respond to comments", "resolve threads", or "PR" are missing.

4 / 5

Distinctiveness Conflict Risk

The niche is clear (addressing PR review/issue comments via the gh CLI) with distinct triggers, so conflict risk is low. Minor overlap remains with general GitHub, PR-management, or code-review skills, keeping it below 5.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

BigSimmo/Communication

Path

.agents/skills/address-github-comments/SKILL.md

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.