CtrlK
BlogDocsLog inGet started
Tessl Logo

understand-issue

Collaboratively investigate a GitHub issue or bug — trace history, understand architecture, diagnose root cause

63

Quality

76%

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 ./.mastracode/skills/understand-issue/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 highly actionable, well-sequenced investigative workflow with concrete gh/git commands and explicit validation gates and feedback loops. Its main weakness is conciseness — repeated menu templates and overlapping quality-gate sections add length — and a single-file structure that inlines some content that could be split out.

Suggestions

Collapse the recurring lettered-option menu templates into a single reusable pattern referenced once, instead of restating near-identical A/B/C/D blocks across phases.

Factor the verbose Phase 3 deep-context guide and the worked diagnosis templates into a references file (e.g. references/diagnosis-patterns.md) to slim the main SKILL.md.

Trim the duplicated quality-gate framing in Phases 1, 4, and 6 to a shared checkpoint convention.

DimensionReasoningScore

Conciseness

The body is information-dense and explicitly instructs short responses, but the repeated lettered menu templates and several near-duplicate quality-gate blocks add padding that could be tightened.

3 / 5

Actionability

Provides fully executable, copy-paste-ready commands with exact flags — e.g. 'gh issue view <number> --json title,body,labels,comments,assignees,state,author', 'gh pr list --author <user> --state merged --limit 100 --json number --jq length', 'git log --oneline -20 -- <file>', 'gh api rate_limit --jq .rate'.

5 / 5

Workflow Clarity

Eight clearly sequenced phases with explicit pacing rules, multiple validation checkpoints (Phase 1 issue quality gate, Phase 4 collaborative validation, Phase 6 understanding gate), and interactive feedback loops (Phase 5/6 retry-and-refine menus).

5 / 5

Progressive Disclosure

Well-organized into clearly headed phases, but it is a single ~290-line monolithic file with no bundle files; detailed menu templates and worked examples are inlined that could arguably live in separate reference files.

4 / 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.

The description is concrete and action-oriented with a clear domain, but lacks an explicit 'Use when...' trigger clause, leaving the activation condition only implied. Trigger-term coverage is good rather than comprehensive.

Suggestions

Add an explicit activation clause, e.g. 'Use when the user asks to investigate a GitHub issue or bug, triage a reported problem, or diagnose a root cause.'

Broaden trigger terms with synonyms users actually say — 'triage', 'reproduce'/'repro', 'root cause', 'why is this broken'.

Keep the third-person imperative voice (already correct) but consider naming the GitHub-issue artifact type more explicitly to sharpen distinctiveness.

DimensionReasoningScore

Specificity

Names the domain (GitHub issue/bug) and lists multiple concrete actions — 'trace history, understand architecture, diagnose root cause' — covering the diagnostic workflow comprehensively.

5 / 5

Completeness

The 'what' is clear (investigate, trace, diagnose) but there is no explicit 'Use when...' trigger clause, so the 'when' is only weakly implied — per the rubric guideline this caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural terms a user would say ('GitHub issue', 'bug', 'investigate'), but omits common synonyms like 'triage', 'reproduce'/'repro', or issue-tracker phrasings.

4 / 5

Distinctiveness Conflict Risk

'Collaboratively investigate a GitHub issue or bug' carves out a fairly distinct niche, though 'understand architecture' and 'investigate' overlap slightly with general code-reading skills.

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.

Validation14 / 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

Total

14

/

16

Passed

Repository
mastra-ai/mastra
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.