code-mate-pi

Runs Pi non-interactively and parses its JSON event stream for repository tasks. Use when the user asks to delegate a bounded analysis or implementation task to Pi.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%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 tight, operationally complete single-file skill: executable commands, security-conscious guards around credentials and tool exposure, and validation checkpoints in the run workflow. The one improvable area is making JSONL parsing concrete rather than directed.

Suggestions

Add a one-line executable example for consuming the JSONL stream (e.g., a jq filter for error events or how to select the final message) to close the actionability gap.

Optionally show the tool-gating decision as a compact rule table (read-only vs. write/edit/Bash) to make the narrowest-tool choice even faster to apply.

Dimension	Reasoning	Score
Conciseness	Every sentence carries Pi-specific operational detail ("Parse stdout as JSONL and inspect error events; Pi can report model or tool failure in the event stream, so process exit alone is insufficient") with zero padding or explanation of concepts Claude already knows. Matches anchor 5: lean, every token earns its place.	5 / 5
Actionability	Concrete, copy-paste-ready commands are given ("pi --mode json --no-session \"<prompt>\"", "command -v pi", "--tools read,grep,find,ls"). Falls short of anchor 5 because parsing the JSONL stream is only directed ("Parse stdout as JSONL and inspect error events") without a concrete example such as a jq filter or how to extract the final message.	4 / 5
Workflow Clarity	Steps 1-3 are clearly sequenced with explicit validation checkpoints: availability check ("command -v pi"), error-event inspection gating use of the final message, and a recovery path for auth/config failures ("stop and ask the user to configure Pi"). This matches anchor 5's sequence-plus-feedback-loop pattern.	5 / 5
Progressive Disclosure	The skill is under 50 lines, single-purpose, and needs no external references — none exist in the bundle — and content is organized into clear "Run" and "Authentication And Permissions" sections. Per the simple-skill exception, well-organized sections score 5 here.	5 / 5
	Total	19 / 20 Passed

Description

87%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.

A strong description: third-person, concise, and explicit about both capability and trigger. Its only weakness is modest breadth of stated actions and a few missing natural trigger synonyms.

Dimension	Reasoning	Score
Specificity	The description names concrete actions — "Runs Pi non-interactively" and "parses its JSON event stream for repository tasks" — going beyond anchor 3's bare 1-2 generic actions by specifying execution mode and output format. It falls short of anchor 5 because coverage is narrow: only two actions are listed.	4 / 5
Completeness	It explicitly answers both questions: what ("Runs Pi non-interactively and parses its JSON event stream for repository tasks") and when ("Use when the user asks to delegate a bounded analysis or implementation task to Pi") with a concrete trigger phrase. This matches the anchor 5 example pattern exactly.	5 / 5
Trigger Term Quality	"delegate", "analysis", "implementation task", and "Pi" are phrases a user would naturally say when needing this skill. Anchor 5 requires comprehensive synonym coverage (e.g., "hand off to Pi", "ask Pi to"), which is absent, so this sits between anchors 3 and 5, noticeably above the midpoint.	4 / 5
Distinctiveness Conflict Risk	"Pi" is a named, niche tool and the trigger is anchored to delegating tasks to it specifically, giving a clear niche with minimal conflict risk with other skills. No broader domain terms that would overlap with general coding or file skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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: CherryHQ/cherry-studio
Path: resources/code-cli-skills/code-mate-pi/SKILL.md
Commit: 113ef7e

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.