CtrlK
BlogDocsLog inGet started
Tessl Logo

triage-issue

Use when triaging a GitHub issue - analyzes issue, checks for duplicates, categorizes, and drafts response

66

Quality

81%

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

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.

Highly actionable triage skill with executable commands and comprehensive response templates, clear step sequencing, and good single-file organization. The main weakness is token efficiency from redundant tables and the inline template block.

Suggestions

Consolidate the issue-type table: Step 2 defines types and Step 6 maps them to actions/labels — merge into one table or have Step 6 reference Step 2 to remove the duplication.

Drop or shrink the graphviz workflow diagram; the numbered section headers already convey the same fetch→classify→duplicates→analyze→response→action sequence.

Add an explicit validation gate before destructive actions (e.g. 'Confirm confidence is HIGH before closing or transferring an issue') to strengthen the workflow's feedback loop.

DimensionReasoningScore

Conciseness

Mostly concrete domain guidance with little concept over-explanation, but the issue-type table is repeated in Steps 2 and 6, the graphviz workflow duplicates the section structure, and the Overview restates the description — several sections could be tightened.

3 / 5

Actionability

Fully executable gh CLI commands plus copy-paste response templates covering all six common issue types, with specific labels and actions — concrete examples cover the common cases.

5 / 5

Workflow Clarity

Clear six-step sequence with a classification checklist and confidence rating as checkpoints, but there is no explicit validation gate before destructive actions (close/transfer) and no re-classify feedback loop.

4 / 5

Progressive Disclosure

Well-organized single file with clear section headers and no nested references, but the ~90-line response-templates block is content that could live in a one-level-deep reference file.

4 / 5

Total

16

/

20

Passed

Description

87%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 cleanly states both capability and trigger in concise third-person voice with several concrete actions. Minor genericness in verbs ('analyzes', 'categorizes') keeps specificity just below maximum.

DimensionReasoningScore

Specificity

Names the domain ('triaging a GitHub issue') and lists several concrete actions — 'analyzes issue, checks for duplicates, categorizes, and drafts response' — but the actions are somewhat generic compared to the level-5 example's granular verbs.

4 / 5

Completeness

Explicitly answers both 'what' (analyze, dup-check, categorize, draft response) and 'when' ('Use when triaging a GitHub issue') with a concrete trigger clause.

5 / 5

Trigger Term Quality

'Use when triaging a GitHub issue' is a natural phrase a user would say, with good keywords ('GitHub issue', 'duplicates'), though a few common variants (e.g. 'triage this issue') are implicit rather than enumerated.

4 / 5

Distinctiveness Conflict Risk

'Triaging a GitHub issue' is a clear niche with distinct triggers and minimal overlap risk with other skills.

5 / 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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
mysticaltech/terraform-hcloud-kube-hetzner
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.