CtrlK
BlogDocsLog inGet started
Tessl Logo

github-issues

Create, triage, label, assign GitHub issues via gh or REST.

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

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable with complete executable examples for every operation, but it is a large monolithic file with no progressive file structure and lacks validation/verification checkpoints around its destructive and batch workflows.

Suggestions

Add a verification/confirmation step to batch and destructive operations — e.g. list-and-confirm before bulk close, and verify state after closing — to lift workflow clarity above 2.

Move the bug-report and feature-request templates (and optionally the bulk-operations recipes) into reference files under references/ and link to them one level deep, enabling progressive disclosure for the oversized body.

Reduce token cost by factoring the repeated curl output-formatting into a single shared helper or by trimming curl examples where `gh` already covers the action.

DimensionReasoningScore

Conciseness

Mostly efficient and free of concept-explanation padding, but the repeated inline `python3 -c` output-formatting snippets across every curl example and full dual gh+curl coverage of each operation add tokens that could be factored out or tightened; not a 3 because it does not fully earn every token's place.

2 / 3

Actionability

Provides fully executable, copy-paste-ready `gh` and `curl` commands with real parameters, JSON bodies, templates, and a quick-reference table — matching the executable-and-specific anchor; not a 2 because the guidance is complete rather than pseudocode or partial.

3 / 3

Workflow Clarity

The triage workflow and bulk operations are sequenced as numbered steps, but destructive/batch operations (bulk closing all issues with a label, closing/reopening) have no validation, confirmation, or verify-after feedback loop, which caps workflow clarity at 2; not a 1 because steps and sequence are clearly present.

2 / 3

Progressive Disclosure

The skill is a single ~370-line file, well-organized into sections with a quick-reference table, but it uses no one-level-deep references and keeps content that could be split (bug/feature templates, bulk operations) inline; not a 1 because organization is good with no nested-reference mess, not a 3 because there is no progressive file structure despite the size.

2 / 3

Total

9

/

12

Passed

Description

82%

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 concise, specific description that names concrete actions and a clear niche, but it omits any explicit 'when to use this' trigger guidance, which caps completeness at 2.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to create, triage, label, or assign GitHub issues, or mentions issue tracking/bug reports.'

Broaden trigger-term coverage with natural variations like 'bug reports', 'feature requests', or 'close issues' that users commonly say.

DimensionReasoningScore

Specificity

Lists four distinct concrete actions — 'Create, triage, label, assign' — applied to a named object (GitHub issues), matching the multiple-specific-actions anchor; not a 2 because the action list is comprehensive rather than partial.

3 / 3

Completeness

Clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger for when to invoke it, so completeness is capped at 2 per the missing-trigger guideline; not a 1 because the 'what' is explicit.

2 / 3

Trigger Term Quality

'GitHub issues' is the core natural term and the verbs 'create', 'triage', 'label', 'assign' mirror how users phrase these requests, plus interface terms 'gh' and 'REST'; coverage is strong, though slightly short of the multi-variation ideal.

3 / 3

Distinctiveness Conflict Risk

'GitHub issues' is a clearly bounded niche distinct from PR workflows, and 'via gh or REST' narrows the interface, making false triggers unlikely; not a 2 because the scope is specific rather than overlapping.

3 / 3

Total

11

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
NousResearch/hermes-agent
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.