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

75%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.

The body is highly actionable with complete executable commands and a clear data structure, and it is well-organized for a single-purpose skill. Its main weakness is mild redundancy around the human-summary feature and some explanatory mechanics that could be trimmed.

Suggestions

Consolidate the --human-summary material into one section to remove the triple restatement across 'When to Use', 'Usage', and 'Human Summary'.

Trim the 'How It Works' gist-mechanics explanation, which largely restates what Claude can infer from the commands.

Add brief guidance on when to choose each output flag (e.g., --entries vs --header vs --system) so the single-action workflow is fully sequenced.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable commands and a compact interface spec, but the --human-summary capability is restated across 'When to Use', 'Usage', and 'Human Summary', and 'How It Works' explains gist mechanics Claude could infer, fitting the 'mostly efficient but could be tightened' anchor.	3 / 5
Actionability	Provides copy-paste-ready executable commands for every flag, concrete jq pipeline examples, and a complete TypeScript interface covering the common cases, matching the 'fully executable, copy-paste ready' anchor.	5 / 5
Workflow Clarity	The core action (run fetch-session.mjs with the appropriate flag) is unambiguous and the operation is read-only so no validation cap applies, but the doc lists flags without sequencing when each output is preferred, leaving minor checkpoint/guidance gaps versus the 5 anchor.	4 / 5
Progressive Disclosure	Well-organized into clear sections (When to Use, How It Works, Usage, Data Structure, Example) with no nested references and all content inline; with no bundle files present the structure is good, though the interface/entry-type reference could justify a separate file, keeping it just below 5.	4 / 5
	Total	16 / 20 Passed

Description

62%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.

The description is specific and distinctive with concrete actions and a clear niche, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness and leaves trigger-term coverage at a mid level.

Suggestions

Add an explicit trigger clause such as 'Use when the user provides a pi-share URL or asks to load/summarize a buildwithpi or shittycodingagent session.'

Include natural synonym triggers users might say (e.g., 'pi session', 'buildwithpi transcript', 'coding agent session replay').

Consider folding the long domain list into the trigger clause to keep the opening sentence leaner while preserving discoverability.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Load and parse session transcripts', 'Fetches gists, decodes embedded session data, and extracts conversation history' — with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the fully comprehensive 5.	4 / 5
Completeness	The 'what' is clear (load, parse, fetch, decode, extract) but there is no explicit 'Use when...' trigger clause; per the rubric a missing explicit trigger caps completeness at 3, matching the 'clear what, when weakly implied' anchor.	3 / 5
Trigger Term Quality	Relevant keywords like 'session transcripts', 'conversation history', and the specific domain names are present, but common natural variations and an explicit trigger phrasing are missing, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Targets a clear niche — pi-share session transcripts from named domains (shittycodingagent.ai, buildwithpi.ai, buildwithpi.com, pi.dev) — with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	15 / 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: mitsuhiko/agent-stuff
Path: skills/pi-share/SKILL.md
Commit: 13bc8f8

Reviewed: 9 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.