CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

load-issues

Load all open issues from GitHub and save them as markdown files

Quality

72%

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 ./antigravity/skills/load-issues/SKILL.md

The canonical home for this skill is load-issues in NeoLabHQ/context-engineering-kit

SKILL.md
Quality
Evals
Security

Quality

Content

76%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 content is a lean, highly actionable procedure with exact gh commands, a concrete naming convention, and a complete output template. Its main weakness is the absence of validation and error handling for a batch operation — null bodies, gh failures, and file-creation checks are unaddressed — which caps workflow clarity at 3.

Suggestions

Add a validation step after saving, e.g. verify each expected file exists and is non-empty before reporting the summary.

Handle edge cases explicitly: issues with null/empty bodies, missing labels/assignees, and gh CLI failures (auth, network) with a retry or skip-and-report loop.

Trim the closing 'IMPORTANT: Execute all steps in the correct order...' line — the numbered sequence already conveys it.

DimensionReasoningScore

Conciseness

The body is efficient: it skips concept explanations and delivers commands, a naming pattern, and a template with no filler beyond the trailing 'IMPORTANT: Execute all steps in the correct order...' line, which is minor over-explanation that could be trimmed. Not 5 because that closing exhortation and template comments add small token overhead.

4 / 5

Actionability

Guidance is fully executable and copy-paste ready: 'gh issue list --limit 100', 'gh issue view <number> --json number,title,body,state,createdAt,updatedAt,author,labels,assignees,url', 'mkdir -p ./specs/issues', a concrete file-naming pattern with a worked example ('007-make-code-review-trigger-on-sql-sh-changes.md'), and a complete markdown template covering the common case.

5 / 5

Workflow Clarity

The six steps are clearly sequenced, but this is a batch operation (up to 100 issues written to many files) with no validation checkpoints: no handling of null/empty issue bodies, no gh CLI error handling, and no verification that files were created correctly. Per the rubric's guidelines, missing validation in batch operations caps workflow clarity at 3 even though the sequence itself is clean.

3 / 5

Progressive Disclosure

This is a simple, single-purpose skill under 50 lines with no external bundle files, and its numbered-step structure keeps everything well organized and navigable. It falls just short of 5 because there are no section headers to separate the workflow from the template, though for a skill this small that is only a minor gap.

4 / 5

Total

16

/

20

Passed

Description

53%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 concise, in third person, and clearly states what the skill does, but it entirely lacks a 'when to use' trigger clause and offers only minimal action coverage with limited keyword variation. Adding an explicit trigger sentence would lift both completeness and trigger term quality.

Suggestions

Append a trigger clause such as: 'Use when the user asks to load, export, or fetch GitHub issues, or wants issues saved as markdown specs.'

Broaden natural trigger terms with synonyms like 'export issues', 'download issues', or 'back up issues' so more user phrasings match.

Optionally mention the output format/location (e.g., 'one markdown file per issue with metadata') to sharpen the what.

DimensionReasoningScore

Specificity

The description names the domain ('open issues from GitHub') and exactly two concrete actions ('Load... and save them as markdown files'), matching the anchor for 1-2 concrete actions but not comprehensive. It omits specifics like the output directory and file format details that would raise it to 4.

3 / 5

Completeness

It clearly answers 'what' (load open GitHub issues, save as markdown) but contains no 'when' or 'Use when...' clause whatsoever; the judging guidelines explicitly cap completeness at 3 for a missing trigger clause. It cannot be 4, which requires both what and when.

3 / 5

Trigger Term Quality

Terms like 'GitHub', 'open issues', and 'markdown files' are natural phrases users would say, but common variations such as 'export issues', 'fetch issues', or 'download issues' are missing. This sits at 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

'Load all open issues from GitHub and save them as markdown files' carves out a fairly distinct niche with specific triggers (GitHub issues, markdown export). It is not 5 because it could mildly overlap with other GitHub-issue or docs-export skills, but the overlap risk is minor.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

NeoLabHQ/context-engineering-kit

Path

antigravity/skills/load-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.