Tessl • The management layer for AI agent skills

A tight, instruction-only skill that is fully actionable: exact commands, explicit validation and failure-handling steps, safety constraints on credentials and interactivity, and clean section structure with zero padding. It is an exemplary lean SKILL.md body for a single-purpose tool-delegation skill.

Dimension	Reasoning	Score
Conciseness	The ~25-line body is lean with every sentence carrying non-obvious information (JSONL error events, lack of tool-approval prompts, credential handling); there is no padding and no explanation of concepts Claude already knows.	5 / 5
Actionability	Fully executable commands are given throughout — `command -v pi`, `pi --mode json --no-session "<prompt>"`, and `--tools read,grep,find,ls` — plus a concrete read-only example; the only implicit detail (JSONL parsing mechanics) is knowledge Claude already has.	5 / 5
Workflow Clarity	The three-step sequence has explicit validation checkpoints with failure branches: availability check ("If it is missing, stop and ask"), output validation ("inspect error events; process exit alone is insufficient"), and auth failure handling — matching the anchor-5 pattern of clear sequence with explicit validation and error-recovery paths.	5 / 5
Progressive Disclosure	Under 50 lines with no need for external references (none exist in the bundle), and content is organized into two clear, well-scoped sections (Run, Authentication And Permissions), which per the rubric's simple-skill guidance merits a 5.	5 / 5
	Total	20 / 20 Passed

Description

82%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 concise, third-person description that clearly answers both what the skill does and when to use it, with a distinctive trigger term. Its only weakness is thin action coverage — "repository tasks" is generic and no specific task types are enumerated.

Suggestions

Replace the generic "for repository tasks" with 2-3 concrete task types (e.g., "for code analysis, refactoring, or bug fixes in a repository") to lift specificity from anchor 3 to 4.

Add one or two natural user phrasings to the trigger clause, such as "ask Pi to" or "use Pi on", to broaden trigger term coverage.

Optionally mention the non-interactive/sessionless guarantee in the trigger context (e.g., "when the user wants Pi run as a one-shot task") to sharpen the when-clause further.

Dimension	Reasoning	Score
Specificity	"Run Pi non-interactively for repository tasks" names the domain and one concrete action (sessionless invocation), but "repository tasks" is generic and the description does not list several specific actions, so it sits at anchor 3 rather than 4.	3 / 5
Completeness	Both parts are explicit: the what is "Run Pi non-interactively for repository tasks" and the when is a concrete trigger phrase — "Use when the user asks to delegate analysis or implementation to Pi" — which is more specific than the anchor-4 example, matching anchor 5.	5 / 5
Trigger Term Quality	"delegate analysis or implementation to Pi" and "Run Pi" are natural phrases users would say, giving good keyword coverage (Pi, delegate, analysis, implementation, repository tasks), though common variations like "ask Pi" or "use Pi to fix" are missing — anchor 4, not 5.	4 / 5
Distinctiveness Conflict Risk	"Pi" is a distinctive niche term and the trigger "delegate analysis or implementation to Pi" is unambiguous, so it is clearly distinguishable from other skills with minimal conflict risk.	5 / 5
	Total	17 / 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
Revision: 2c274a4

Reviewed: 9 days ago

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.

code-mate-pi

Table of Contents

Is this your skill?