CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

github-issues

GitHub issue comment guidelines for community interaction. Use when: "respond to this issue", "reply to this bug report", "close this issue", or any GitHub discussion.

Quality

80%

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/github-issues/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a highly actionable, project-specific style guide with copy-paste response templates and concrete links, organized into clear sections. Its weaknesses are redundancy across the fixed-issue guidance, anti-patterns, and examples, plus hedged qualifiers that leave minor ambiguity about when to apply optional elements.

Suggestions

Consolidate the fixed-issue guidance that currently appears in the Comment Compression Rule, Fixed Issues section, inline 'Good' example, and Feature Implementation Response example into one canonical section with one example.

Tighten hedged instructions like 'Occasionally, when the reporter seems invested' and 'Add celebration emoji sparingly' into explicit conditions (e.g. 'invite to Discord only on a first substantive report; use emoji at most once per comment').

Move the four response templates into a references/examples.md file and keep a one-line pointer per scenario in SKILL.md to reduce inline length.

DimensionReasoningScore

Conciseness

Fixed-issue guidance repeats across the Comment Compression Rule, the Fixed Issues section, the inline 'Good' example, and the Response Examples, and the Anti-Patterns overlap the compression rule, so the document could be noticeably tightened even though all content is project-specific rather than concepts Claude already knows. It fits anchor 3 (mostly efficient with some redundancy) rather than 4 because the repetition exceeds minor trimming, and not 2 because there is no padding or explanation of general knowledge.

3 / 5

Actionability

The guidance is copy-paste ready for an instruction-only skill: four complete response templates (feature implementation, debugging, quick acknowledgment, PR back-and-forth), exact suggested phrasings, and concrete links (cal.com and Discord URLs) covering the common cases. It fits the top anchor rather than 4 because the examples are complete, with only intentional placeholders.

5 / 5

Workflow Clarity

This single-task skill has an unambiguous core reply shape (acknowledgment, state/answer, next action, warm closing) and an explicit ordered sequence for fixed issues, but soft qualifiers like 'Occasionally, when the reporter seems invested', 'Add celebration emoji sparingly', and the greeting-required vs. PR-brief tension leave minor judgment-call gaps. It fits anchor 4 rather than 5 because some guidance is hedged, and not 3 because the reply structure and fixed-issue ordering are explicit.

4 / 5

Progressive Disclosure

The single SKILL.md file is well organized into clearly headed sections with one clearly signaled external reference (AGENTS.md writing conventions), and no bundle files exist, but at roughly 150 lines the response examples could be split into a separate reference file. It fits anchor 4 rather than 5 because the file exceeds the under-50-line simple-skill case and keeps all templates inline, and not 3 because sections are clear and well-signaled.

4 / 5

Total

16

/

20

Passed

Description

78%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 with an explicit and natural 'Use when' trigger clause and a clearly stated domain. The main weakness is that the capability statement is a topic label ("comment guidelines") rather than a list of concrete actions, and the broad "any GitHub discussion" catch-all slightly raises conflict risk.

Suggestions

Replace the generic capability phrase 'comment guidelines for community interaction' with concrete actions, e.g. 'Draft replies, acknowledge reports, and close the loop on GitHub issues and PRs following project tone conventions.'

Add the missing natural trigger variants such as 'comment on this issue' or 'reply to this PR review' to the Use when clause.

Narrow the catch-all 'or any GitHub discussion' to reduce overlap with other GitHub-oriented skills, e.g. 'or when drafting any GitHub issue/PR comment'.

DimensionReasoningScore

Specificity

"GitHub issue comment guidelines for community interaction" names the domain clearly, and the trigger phrases "respond to this issue", "reply to this bug report", and "close this issue" imply 1-2 concrete actions, but the description never lists the skill's capabilities as concrete verbs, so coverage is not comprehensive.

3 / 5

Completeness

It explicitly answers both what ("GitHub issue comment guidelines for community interaction") and when ("Use when: 'respond to this issue', 'reply to this bug report', 'close this issue', or any GitHub discussion") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

The triggers "respond to this issue", "reply to this bug report", "close this issue", and "any GitHub discussion" are natural phrases a user would say, but common variants like "comment on this issue" or "reply to this PR" are missing, so coverage falls short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

The niche (GitHub issue/PR comment etiquette) is distinct with specific triggers, but the catch-all "or any GitHub discussion" widens the net and creates minor overlap risk with other GitHub-related skills.

4 / 5

Total

16

/

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

relative_links

Relative link issues: 2 missing, 1 suspicious

Warning

Total

15

/

16

Passed

Repository

EpicenterHQ/epicenter

Path

.agents/skills/github-issues/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.