pi-share

Load and parse session transcripts from shittycodingagent.ai/buildwithpi.ai/buildwithpi.com/pi.dev (pi-share) URLs. Fetches gists, decodes embedded session data, and extracts conversation history.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/pi-share/SKILL.md

Quality

Content

70%

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

The content is highly actionable with concrete executable commands and examples, and well-organized into clear sections. It loses points on conciseness (the inline TypeScript schema and type taxonomies could be trimmed) and on workflow clarity, where the fetch/decode flow lacks explicit validation or error-recovery checkpoints.

Suggestions

Add a brief validation/error-handling note to the fetch workflow, e.g. what to do when the gist is missing or the base64 decode fails, to earn a workflow_clarity of 3.

Trim the inline TypeScript `SessionData` interface and entry/block-type taxonomy to the fields Claude actually needs to interpret `--entries` output, or move them into a bundled reference file to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the TypeScript interface block, the full entry/block-type taxonomy, and the '--human-summary' sub-sections restate data the script already prints, adding length that could be trimmed.	2 / 3
Actionability	Provides fully executable, copy-paste-ready `node ... fetch-session.mjs` commands for every flag plus concrete `jq` examples, so Claude knows exactly what to run.	3 / 3
Workflow Clarity	The 'How It Works' steps sequence the fetch/decode flow, but there are no validation or verification checkpoints for what is effectively a network fetch + decode operation (e.g. confirming the gist exists, handling decode failure); per the guideline, missing validation in a multi-step fetch/decode workflow caps clarity at 2.	2 / 3
Progressive Disclosure	The single helper script is referenced inline with clear sections (When to Use, Usage, Human Summary, Data Structure, Example); no nested multi-level references exist, and the body is well-organized for a sub-50-reference skill.	3 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and distinctive, naming concrete actions and a narrow domain niche. It is capped at completeness 2 by the absence of an explicit 'Use when...' trigger clause, and trigger-term quality is good but somewhat narrow.

Suggestions

Add an explicit trigger clause such as 'Use when the user provides a pi-share/buildwithpi session URL or gist ID, or asks to load or summarize a pi coding-agent session transcript.'

Broaden natural-language trigger terms to include phrases users would actually say, e.g. 'session transcript', 'coding agent session', 'conversation history', rather than relying mostly on domain URLs.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Load and parse session transcripts', 'Fetches gists, decodes embedded session data, and extracts conversation history' — naming the specific data sources and decoding step.	3 / 3
Completeness	Clearly answers 'what does this do', but lacks an explicit 'Use when...' trigger clause; the 'when' is only implied via the URL/domain enumeration. Per the guideline, a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	Includes the natural terms 'session transcripts' and domain URLs users would paste, but the trigger vocabulary is narrow (no 'pi-share session', 'coding agent transcript', or 'conversation history' as user-spoken phrases).	2 / 3
Distinctiveness Conflict Risk	The named domains (shittycodingagent.ai, buildwithpi.ai, etc.) and pi-share branding create a clear, narrow niche unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 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: mitsuhiko/agent-stuff
Path: skills/pi-share/SKILL.md
Commit: d265b8e

Reviewed: 5 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.