CtrlK
BlogDocsLog inGet started
Tessl Logo

043-planning-github-issues

Use when you need GitHub CLI (`gh`) installation/authentication guidance and a sanitized GitHub issue inventory workflow. The agent does not ingest GitHub issue or milestone output directly; it asks the user for sanitized issue summaries before analysis or @014-agile-user-story handoff. This should trigger for requests such as GitHub issue summary workflow; GitHub CLI setup for issues; Prepare sanitized GitHub issue inventory; Analyze GitHub issues with gh CLI; Summarize milestones and issue discussions safely. Part of Plinth Toolkit

66

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

A well-organized overview with clean progressive disclosure to a real reference file, but the body is padded by repeated constraints, defers executable install/auth specifics to the reference, and lacks in-body verification checkpoints and error handling. Suggestions target conciseness, actionability, and workflow clarity.

Suggestions

State the no-direct-ingestion rule once (e.g. in Constraints) and remove its restatements from the intro, 'What is covered', and Workflow steps 2-4; drop the 'When to use this skill' section since it duplicates the description's trigger list.

Add the actual gh install commands (or an explicit in-body pointer to the reference's install section) and a brief gh auth login flow so the overview's setup guidance is copy-paste ready rather than deferred.

Add an explicit verification checkpoint after the sanitized inventory/summary is collected (confirm completeness before analysis or handoff) and surface key gh error handling (404/403/rate limits) in the body instead of only in the reference.

DimensionReasoningScore

Conciseness

Mostly efficient and free of concept-explanation padding, but the no-direct-ingestion rule is restated across the intro, 'What is covered', 'Constraints', and several Workflow steps, and 'When to use this skill' duplicates the description's trigger list. It is not a 3 because this repetition could be consolidated; not a 1 because it does not explain things Claude already knows.

2 / 3

Actionability

Provides concrete check commands (gh --version, gh auth status, gh auth login, --repo) and a clear interactive gate, but defers the actual install commands and auth-login specifics to the reference, leaving the body incomplete for copy-paste execution. It is not a 3 because key executable details are absent from the overview; not a 1 because the guidance is concrete rather than abstract.

2 / 3

Workflow Clarity

The 5-step sequence is clear with an explicit stop/wait install gate, but later steps lack verification checkpoints and error recovery lives only in the reference (Step 6), not the body. It is not a 3 because validation gaps remain after the gate; not a 1 because the sequence and gate checkpoint are explicit.

2 / 3

Progressive Disclosure

The body is a clear overview with a well-signaled, one-level-deep reference link to references/043-planning-github-issues.md, which exists as a real file; detail is appropriately split out. It is not a 2 because the reference is clearly signaled and not nested.

3 / 3

Total

9

/

12

Passed

Description

100%

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 strong, well-constructed description: it states concrete capabilities, gives explicit 'Use when' triggers with a natural-phrase list, and carves out a distinct, low-conflict niche. No weaknesses warranting suggestions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — installation/authentication guidance, sanitized issue inventory workflow, requesting user summaries, and handoff to @014-agile-user-story — rather than vague language. It is not a 2 because the actions are specific and several, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly answers both 'what' (gh setup guidance plus a sanitized inventory workflow with no direct ingestion and handoff) and 'when' via an explicit 'Use when you need...' clause and a 'This should trigger for requests such as...' list. The Use-when clause is present, so the completeness cap of 2 does not apply.

3 / 3

Trigger Term Quality

Provides five explicit trigger phrases (e.g. 'GitHub CLI setup for issues', 'Analyze GitHub issues with gh CLI', 'Summarize milestones and issue discussions safely') covering natural user terms and common variations. The 'sanitized inventory' jargon is minor; overall coverage is strong, so it is not a 2.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (GitHub CLI setup + sanitized issue inventory + chained handoff) with specific triggers and a distinctive no-direct-ingestion constraint, making conflict with other skills unlikely. It is not a 2 because the triggers are specific rather than broadly overlapping.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jabrena/plinth
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.