CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

issues

Interact with GitHub issues - create, list, and view issues.

Quality

69%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/issues/SKILL.md

The canonical home for this skill is issues in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured, actionable single-file skill: every gh command is concrete, the multi-path workflow is clearly sequenced, and error handling is addressed. Its main weakness is redundancy — title/body/label guidance is stated twice and prompt scaffolding is heavier than needed, which inflates token cost without adding capability.

Suggestions

Deduplicate the title-guidance and label-option content between the step sections and "Important Notes" — state each rule once and reference it.

Trim the AskUserQuestion scaffolding (full question/header/option blocks) to the essential prompts; Claude can construct well-formed questions from brief descriptions.

Show a realistic, fully executable `gh issue create` example (multi-label flags, escaped body) instead of the placeholder single-line form.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows (no "what is GitHub" padding) and its commands are lean, but it repeats itself: the title-length guidance appears in full in Step 2a and again nearly verbatim in "Important Notes" ("Titles should be succinct (5-10 words)"), and the label option lists are duplicated across Steps 4a and 2b. This matches anchor 3 ("mostly efficient but could be tightened") rather than anchor 4, which requires only minor trimming.

3 / 5

Actionability

Concrete, executable commands are provided throughout: `gh issue create --title ... --body ... --label ...`, `gh issue list --assignee @me`, `gh issue view [number]`, a HEREDOC example, and error-recovery via `gh auth status`. It sits at anchor 4 rather than 5 because the create command shows a naive single-line form with placeholders and the label handling (multi-select joined into one --label flag) is not fully worked out.

4 / 5

Workflow Clarity

The process is clearly sequenced with numbered steps and explicit branching (2a/2b/2c paths), an error-handling section with recovery steps, and a checkpoint ("Always confirm the issue was created successfully by showing the URL"). It is not anchor 5 because there are no explicit validate-then-retry feedback loops (e.g. handling a failed `gh issue create` beyond the generic error section), fitting anchor 4 (clear sequence, most checkpoints present).

4 / 5

Progressive Disclosure

No bundle files exist and the body references none, so nothing dangles; the ~250-line single-file workflow is organized under clear section headers (Instructions, per-action sections, Error Handling, Important Notes) making it easy to navigate. This matches anchor 4 (good structure, minor organization gaps) rather than anchor 5 — the skill exceeds 50 lines, so the simple-skill exception does not apply, and some of the duplicated interactive-prompt scaffolding could live in a separate reference.

4 / 5

Total

15

/

20

Passed

Description

58%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 states its capabilities concretely and is appropriately concise, but it lacks any explicit "when to use" guidance and only covers a thin slice of natural trigger phrasing. Adding a Use-when clause and synonyms like "open/file an issue" or "bug reports" would raise completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to create, list, view, file, or browse GitHub issues."

Include natural synonyms users actually say, such as "open an issue", "file a bug report", or "issue tracker".

Consider mentioning what a created issue contains (title, body, labels) to sharpen the capability description without adding fluff.

DimensionReasoningScore

Specificity

The description lists three concrete actions — "create, list, and view issues" — in a named domain (GitHub issues). It fits anchor 4 ("several specific actions; minor gaps") better than anchor 3 (only 1-2 actions) but not anchor 5, since coverage omits common operations like editing, commenting on, closing, or labeling issues.

4 / 5

Completeness

The "what" is clear (create, list, and view GitHub issues), but there is no "Use when..." clause or equivalent trigger guidance, so per the judging guideline completeness is capped at 3. It is above anchor 2 because the "what" is concrete, not vague.

3 / 5

Trigger Term Quality

"GitHub issues", "create", "list", and "view" are natural terms a user would say, but the description misses common variations and synonyms such as "open an issue", "file an issue", "report a bug", or "browse issues". This matches anchor 3 (relevant keywords but missing common variations) rather than anchor 4's fuller coverage.

3 / 5

Distinctiveness Conflict Risk

"GitHub issues" carves out a fairly distinct niche with natural triggers, though "Interact with GitHub issues" has minor overlap risk with adjacent GitHub skills (pull requests, gh CLI general usage). This matches anchor 4 ("mostly distinct; minor overlap risk").

4 / 5

Total

14

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/issues/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.