CtrlK
BlogDocsLog inGet started
Tessl Logo

review-issues-severity

Find and prioritize open GitHub issues by severity, community impact, and maintainer abandonment

60

Quality

70%

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 ./.claude/skills/review-issues-severity/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 an actionable, well-sequenced read-only workflow with concrete gh commands throughout. It is efficient and well-organized, with minor gaps in section c concreteness and no validation checkpoints (not required for read-only analysis).

Suggestions

Provide a concrete gh api command or jq filter for the 'recently stale issues' case in section c instead of prose guidance.

Tighten the classification table and prose to remove cues that repeat across steps 2 and 3.

Consider splitting the per-issue analysis output template into a reference file if the skill grows further.

DimensionReasoningScore

Conciseness

Mostly lean with concrete gh commands, tables, and tight bullets, but includes a few trimmable prose passages (section 2c and some repeated classification cues).

4 / 5

Actionability

Provides copy-paste-ready gh api and gh issue view commands with --jq filters covering the main query patterns, though section c ('recently stale') lacks a concrete executable command.

4 / 5

Workflow Clarity

A clear 5-step sequence (gather, deep-dive, classify, prioritize, output) with good structure; read-only so the destructive/batch validation cap does not apply, but no explicit validation checkpoints are present.

4 / 5

Progressive Disclosure

A single self-contained file with well-organized sections and no nested or dead references; slightly long for one file but cohesive and appropriately structured with no bundle files needed.

4 / 5

Total

16

/

20

Passed

Description

66%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 and third-person with a clear 'what', but lacks any explicit 'when to use' trigger guidance, capping completeness. Distinctiveness is good for the issue-triage niche.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when triaging or prioritizing open GitHub issues for a repository.'

Include natural synonyms users say like 'triage', 'review', or 'bug reports' to broaden trigger coverage.

Optionally scope the description to a repo so it is more distinct from generic review skills.

DimensionReasoningScore

Specificity

Names the domain (open GitHub issues) and concrete actions (find, prioritize) with explicit criteria (severity, community impact, maintainer abandonment), listing several specific facets but only two verbs.

4 / 5

Completeness

The 'what' is clear ('Find and prioritize open GitHub issues by severity, community impact, and maintainer abandonment') but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

Good natural keywords ('GitHub issues', 'severity', 'community impact', 'abandonment') a user might say, but missing common synonyms like 'triage', 'review', or 'bug reports'.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (issue severity triage) and is mostly distinct, with only minor overlap risk against generic review/triage skills.

4 / 5

Total

15

/

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.

Validation15 / 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
dlt-hub/dlt
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.