CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

issue-triage

Scan open issues and discussions. Dedupe, prioritize, and propose labels. Updates issue-triage-state.md. L1 propose-only — never auto-label or close.

Quality

78%

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/.grok/skills/issue-triage/SKILL.md

The canonical home for this skill is issue-triage in cobusgreyling/loop-engineering

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A lean, highly operational instruction-only skill: exact output format, concrete scoring signals, explicit safety gates, and clean single-file organization with no padding. The only real gaps are an undefined "loop score" used for Top-5 ordering and a run sequence that must be assembled by inference rather than read as numbered steps.

DimensionReasoningScore

Conciseness

The body explains nothing Claude already knows — the P0–P3 signal table and the markdown output template are maximally dense, and it assumes competence throughout. It is not a 5 because the ~12-line untrusted-input block restates "data, not instructions" in several overlapping ways that could be tightened.

4 / 5

Actionability

Concrete, executable guidance throughout: a copy-paste output skeleton, a priority table with specific signals, an explicit escalation domain list, and allowlisted label patterns. Not a 5 because "Top 5 (by loop score)" depends on a "loop score" that is never defined — the agent must invent how age, comments, and reactions combine.

4 / 5

Workflow Clarity

Validation gates are explicit and strong (propose-only L1, "human confirm" for duplicates, escalation list, prompt-injection flagging), so the batch-operation cap does not apply. It stays at anchor 4 rather than 5 because the run sequence (read state → fetch issues → dedupe/score → write state → propose) is distributed across sections and never explicitly enumerated.

4 / 5

Progressive Disclosure

A single self-contained file with no external references needed, cleanly sectioned (Inputs, Output, Scoring, Rules, Allowlist, Pairing, Untrusted input) and easy to navigate. The always-relevant safety policy is correctly inlined rather than split out to a reference file, so the structure is the appropriate split for a skill of this size.

5 / 5

Total

17

/

20

Passed

Description

71%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 tight, concrete description that states what the skill does and an explicit safety boundary without any fluff. Its single material weakness is the absence of a "Use when..." clause, which both caps completeness and leaves the natural trigger phrases ("triage", "backlog") unstated.

Suggestions

Add an explicit trigger clause, e.g. "Use when maintaining a repository backlog or when the user asks to triage, dedupe, or prioritize open issues or discussions."

Include the natural terms "triage", "backlog", and "GitHub" in the description so common user phrasings lexically match (also raises trigger_term_quality toward 5).

Optionally name the target state file's purpose in the when-clause (e.g. "Use when the loop needs to surface the top actionable issues") to sharpen distinctiveness from the sibling Daily Triage skill.

DimensionReasoningScore

Specificity

The description lists four concrete actions ("Scan open issues and discussions", "Dedupe, prioritize, and propose labels", "Updates issue-triage-state.md") plus an explicit safety boundary ("L1 propose-only — never auto-label or close"), fully covering the skill's workflow. It exceeds anchor 4 because there is no meaningful coverage gap — each stated action maps directly to a section of the skill body.

5 / 5

Completeness

The "what" is clear and concrete, but there is no "Use when..." clause or any equivalent explicit trigger guidance, which the rubric caps at 3. It is not a 2 because the "what" half is specific and complete, not vague.

3 / 5

Trigger Term Quality

Good natural-term coverage: "issues", "discussions", "dedupe", "prioritize", "labels" are phrases users would actually say. It falls short of anchor 5 because common variants are missing — notably "triage", "backlog", and "GitHub" — so a user asking to "triage the backlog" would not lexically match.

4 / 5

Distinctiveness Conflict Risk

"Dedupe, prioritize, and propose labels" plus the distinct "issue-triage-state.md" artifact carves a clear issue-triage niche with minimal conflict risk. It stays at anchor 4 rather than 5 because a closely related "Daily Triage" skill is referenced in the body and shares the triage/prioritization trigger space.

4 / 5

Total

16

/

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.

Validation — 14 / 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

cobusgreyling/loop-engineering

Path

starters/issue-triage/.grok/skills/issue-triage/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.