CtrlK
BlogDocsLog inGet started
Tessl Logo

phoenix-github

Manage GitHub issues, labels, project boards, sprint operations, and roadmap health for the Arize-ai/phoenix repository. Use when filing roadmap issues, triaging bugs, applying labels, running sprint close-out and rollover, auditing board hygiene, checking ticket-load balance across the team, keeping roadmap epics up to date, flagging epics that need planning, or querying issue/project state via the GitHub CLI.

75

Quality

94%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 operational reference: executable commands throughout, clear multi-step workflows with dry-run validation and feedback loops, and good navigation. The only weaknesses are minor verbosity in cautionary prose and large inline reference tables that could live in separate files.

Suggestions

Move the Label Taxonomy and Project Field Mechanics tables into a references/ file (e.g. references/fields-and-labels.md) and link to them from SKILL.md to improve progressive disclosure and reduce SKILL.md length.

Tighten repeated cautionary prose — e.g. consolidate the "Stranded means ..." and dry-run-emphasis notes so each warning appears once near the relevant command rather than recurring across sections.

Consider a short "First time / setup" callout near the top noting the one-time `needs planning` label creation and snapshot prerequisite, so onboarding steps are grouped rather than scattered.

DimensionReasoningScore

Conciseness

Dense and operational with no basic-concept padding (no "what is a sprint" filler) and every section assumes Claude's competence; a few cautionary prose passages (e.g. the "Stranded means ..." paragraph, repeated dry-run emphasis) could be trimmed slightly.

4 / 5

Actionability

Copy-paste-ready `gh api graphql` mutations, `gh issue create/edit` commands, and script invocations with concrete stable field IDs and option IDs covering the common cases.

5 / 5

Workflow Clarity

Sprint close-out is a numbered snapshot → dry-run review → apply sequence with explicit validation ("Always review the dry run before --apply"), plus feedback loops (snapshot freshness refusal, re-snapshot before/after apply) and a six-item hygiene checklist.

5 / 5

Progressive Disclosure

A Quick Reference table gives clear navigation, and the five bundled scripts are referenced one level deep with clear signaling; the minor gap is that large static reference tables (Label Taxonomy, Project Field Mechanics) are inlined rather than split into reference files.

4 / 5

Total

18

/

20

Passed

Description

100%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.

An excellent description: third-person voice, concrete capability list, explicit "Use when" triggers, and tightly scoped to a single repository's board/sprint operations. No fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "filing roadmap issues, triaging bugs, applying labels, running sprint close-out and rollover, auditing board hygiene, checking ticket-load balance ... flagging epics that need planning, or querying issue/project state" — with comprehensive coverage of the skill's scope.

5 / 5

Completeness

Clearly states what ("Manage GitHub issues, labels, project boards, sprint operations, and roadmap health for the Arize-ai/phoenix repository") and when (explicit "Use when ..." with concrete trigger phrases).

5 / 5

Trigger Term Quality

The explicit "Use when" clause enumerates nine natural trigger activities a user would actually say (e.g. "triaging bugs", "running sprint close-out and rollover", "flagging epics that need planning"); no file extensions apply here.

5 / 5

Distinctiveness Conflict Risk

Scoped to the Arize-ai/phoenix repository and GitHub project-board/sprint operations — a clear niche with distinct triggers and minimal overlap with generic GitHub skills.

5 / 5

Total

20

/

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

skill_md_line_count

SKILL.md is long (745 lines); consider splitting into references/ and linking

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
Arize-ai/phoenix
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.