speaking

Speaking ops: invites, keynotes, panels, Gmail/calendar, conferences.

Quality

63%

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/speaking/SKILL.md

Quality

Content

77%

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 and well-sequenced with real commands and a validation loop, but it is a single inline document with embedded time-sensitive dates and no progressive disclosure into reference files.

Suggestions

Move the per-opportunity file template and sheet-sync header mapping into a referenced file (e.g. references/template.md) to improve progressive disclosure.

Isolate time-sensitive date ranges (e.g. the current year window for gog queries) into a single variable or noted section so they update in one place rather than across multiple commands.

Dimension	Reasoning	Score
Conciseness	The body is lean and free of concepts Claude already knows, but time-sensitive dates ('after:2026-01-01', '2026-12-31T23:59:59Z') are embedded inline in commands rather than isolated, which the guideline penalizes.	2 / 3
Actionability	Provides fully executable gog commands with exact flags, precise sheet ranges, real file paths, and a copy-paste opportunity template.	3 / 3
Workflow Clarity	Multi-step processes are numbered, and the batch sheet-sync includes an explicit validation checkpoint ('After writing, re-read the range and verify row count plus no podcast/press name hits').	3 / 3
Progressive Disclosure	Well-organized into clear sections with no nested references, but at over 50 lines everything is inline in one file (sheet headers, per-opportunity template, sync rules) that could be split into referenced files.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 a terse fragment that names the domain and key artifacts but omits explicit actions and any 'Use when' trigger. It is distinguishable but could be confused with general mail/calendar skills.

Suggestions

Add a 'Use when...' trigger clause, e.g. 'Use when tracking or responding to Peter's speaking invitations, keynotes, panels, or conference opportunities.'

Replace the noun list with concrete actions, e.g. 'Tracks, evaluates, and syncs speaking opportunities (invites, keynotes, panels, firesides) across Gmail, Calendar, and the conferences sheet.'

Add common trigger terms users would say — 'speaker', 'talk', 'fireside', 'CFP' — to improve natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete items ('invites, keynotes, panels, Gmail/calendar, conferences') but uses nouns rather than explicit actions, so it is not a comprehensive action list.	2 / 3
Completeness	Hints at what ('Speaking ops') but provides no 'Use when...' trigger clause, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Includes natural terms a user might say ('keynotes, panels, conferences') but misses common variations like 'speaker', 'talk', 'fireside', or 'CFP'.	2 / 3
Distinctiveness Conflict Risk	The speaking/conference niche is fairly distinct, but 'Gmail/calendar' could overlap with generic email or calendar skills.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: steipete/agent-scripts
Path: skills/speaking/SKILL.md
Commit: bb36883

Reviewed: about 13 hours 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.