CtrlK
BlogDocsLog inGet started
Tessl Logo

issue-triage

Scan open issues and discussions, deduplicate, prioritize, and propose labels. Provides a clean actionable queue.

61

Quality

73%

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 ./starters/issue-triage-opencode/skills/issue-triage/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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 exceptionally concise and well-structured with concrete, actionable rules, but it lacks an explicit verification checkpoint before updating the state file, which caps workflow clarity for a batch operation. Adding a brief validation step would round it out.

Suggestions

Add an explicit verification checkpoint before writing the state file, e.g. "Before writing issue-triage-state.md, confirm no auto-label/close/comment was performed and that every P0/P1 item is escalated."

Define the P0-P3 priority mapping and the L2 allowlist (or point to where they live) to close the actionability gaps.

Specify how duplicates are detected (e.g. title similarity, linked-PR overlap) so the dedup step is executable rather than implied.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — terse role framing ("You are an issue triage agent. Keep the issue queue legible.") and tight bullets with no explanation of concepts Claude already knows; every token earns its place, matching the 5 anchor.

5 / 5

Actionability

Concrete, specific guidance: exact scan sources, a defined output format (Top 5 P0-P3, proposed labels, needs-human bucket, possible duplicates), and precise rules (e.g. note "possible duplicate of #NNN"); it stays at 4 rather than 5 because the deduplication method, the P0-P3 mapping, and the L2 allowlist contents are left undefined.

4 / 5

Workflow Clarity

A clear scan→output→rules sequence is present, but this is a batch operation (scans all open issues) with no explicit validation/verification checkpoint before writing the state file, so the rubric's batch-operation cap limits workflow_clarity to 3 even though the steps themselves are well ordered.

3 / 5

Progressive Disclosure

Under 50 lines with no need for external references, yet well-organized into clearly headed sections (Scan Sources, Output, Rules); per the rubric's simple-skill exception this earns a 5 on progressive disclosure.

5 / 5

Total

17

/

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 reasonably distinct, naming several concrete triage actions, but it omits any explicit "Use when..." trigger guidance, which caps its completeness. Adding trigger phrases would lift both completeness and distinctiveness.

Suggestions

Append a "Use when..." clause naming natural triggers, e.g. "Use when triaging GitHub issues or discussions, prioritizing a backlog, or proposing labels."

Include synonyms users actually say ("triage", "bug reports", "backlog") to improve trigger-term coverage.

Mention the output artifact (e.g. updates an issue-triage state file) to close the minor specificity gap.

DimensionReasoningScore

Specificity

Names the domain plus several concrete actions — "Scan open issues and discussions, deduplicate, prioritize, and propose labels" — but the closing "Provides a clean actionable queue" is abstract and leaves minor gaps (no mention of the needs-human bucket or output artifact), so it sits at 4 rather than 5.

4 / 5

Completeness

The "what" is clear (scan, deduplicate, prioritize, propose labels), but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3; it is not 4 because "when" is fully absent rather than weakly implied.

3 / 5

Trigger Term Quality

Good coverage of natural terms a user would say ("issues", "discussions", "prioritize", "labels", "deduplicate"), but it omits common synonyms/variations such as "triage", "bug reports", or "GitHub issues", keeping it just below 5.

4 / 5

Distinctiveness Conflict Risk

It targets a clear niche (issue triage) with low conflict risk, but without explicit trigger phrases it could mildly overlap with general project-management skills, so it does not reach the minimal-conflict 5.

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
cobusgreyling/loop-engineering
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.