CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pi-extension-authoring

Build, debug, and maintain Pi extensions safely. Use when editing ~/.pi/agent/extensions, joelclaw/pi/extensions, pi-tools extensions, or any code that uses the Pi ExtensionAPI, hooks, tools, commands, widgets, session replacement, reload, custom messages, or extension package updates.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

90%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 dense, high-signal skill that captures genuinely non-obvious operational knowledge about Pi extension authoring with executable validation commands and a complete session-safe code pattern. The main gaps are minor: a few unsequenced imperatives in the Validation section and no explicit failure-recovery loop connecting validation output to the Common fixes table.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: rules capture non-obvious, project-specific facts (stale ctx after session replacement, 'pi.addTool() is gone', lazy optional dependencies, Bun's minimum-release-age lag) with no concept explanations or padding. Legacy package info is properly flagged as deprecated-style notes ('older installs used @mariozechner/pi-coding-agent'), satisfying the time-sensitive-information exception.

5 / 5

Actionability

Commands are copy-paste ready (bun --check, PI_OFFLINE=1 pi --help with an rg filter, pi update, npm install -g, smoke-test invocations) and the TypeScript pattern is executable apart from deliberately named user-substitution points (buildMessageWithoutCapturedPi, <extension-name>). Specific API names (ctx.newSession(), withSession, pi.registerTool(), createRequire()) and a symptom→cause→fix table cover the common cases comprehensively.

5 / 5

Workflow Clarity

There is a clear ordering ('Run the cheap gates first') with explicit validation checkpoints (rg over pi --help output, which -a pi / pi --version / pi list verification, smoke tests) and a Common fixes table that serves as error recovery. It falls short of 5 because some steps ('Clean untracked npm lockfiles...', the Bun symlink guidance) appear as unsequenced imperatives and validation failures are never explicitly looped back into the fixes table.

4 / 5

Progressive Disclosure

Sections are well-organized (Canonical surfaces, Rules, pattern, Validation, Common fixes) with no nested references and everything one level deep. However, at ~135 lines with no bundle files, all detail (package-update commands, the full code pattern) is inlined in SKILL.md where the rubric expects an overview pointing to detailed materials, so it is not a clear anchor-5 split.

4 / 5

Total

18

/

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 that clearly and explicitly states both what the skill does and when to use it, with concrete path and API triggers that make it highly distinguishable from other skills. The only meaningful gap is that the 'what' clause stays high-level (build/debug/maintain) and a few natural trigger phrases are absent.

DimensionReasoningScore

Specificity

'Build, debug, and maintain Pi extensions safely' lists several concrete actions, matching the anchor-4 example ('Extracts text from PDF files, fills forms, converts pages to images'). Not 5 because the actions stay at a single level of depth with no sub-capabilities named in the 'what' clause; not 3 since three distinct verbs plus a safety qualifier exceed the '1-2 concrete actions' anchor.

4 / 5

Completeness

Explicitly answers both questions: 'what' ('Build, debug, and maintain Pi extensions safely') and 'when' ('Use when editing ~/.pi/agent/extensions, joelclaw/pi/extensions, ... or any code that uses the Pi ExtensionAPI, hooks, ...'). This mirrors the anchor-5 good example's structure with concrete trigger phrases, so the explicit 'Use when' cap does not apply.

5 / 5

Trigger Term Quality

Good natural-term coverage: 'extensions', 'hooks', 'tools', 'commands', 'widgets', 'session replacement', 'reload', 'custom messages', plus concrete path triggers like '~/.pi/agent/extensions'. A few natural terms a Pi user might say are missing (e.g., 'pi coding agent', 'startup warnings', 'skill conflicts'), keeping it below the comprehensive-synonym anchor 5 and clearly above the generic anchor 3.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers: everything is scoped to Pi extensions via named paths, repos, and the Pi ExtensionAPI, so it is unlikely to fire for unrelated skills. There is no generic language that would overlap with general extension/plugin or tooling skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

joelhooks/joelclaw

Path

skills/pi-extension-authoring/SKILL.md

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.