speaking

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

Quality

72%

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

88%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 content is a strong operational skill: highly actionable commands, exact data-source references, explicit verification steps around status changes and batch sheet writes, and tight scoping rules. The only weaknesses are mild — slight redundancy between priority-language and status-meaning lists, stale-prone hardcoded dates in example commands, and inline reference material (sheet headers, file template) that could be split out.

Dimension	Reasoning	Score
Conciseness	The body is dense with operational facts — commands, paths, headers, rules — and never explains concepts Claude already knows. Minor tightening is possible: the "Priority language" and "Useful status meanings" lists overlap somewhat, and example commands embed time-sensitive dates (e.g. "after:2026-01-01", "2027 budget") that will go stale, keeping it below anchor 5.	4 / 5
Actionability	Guidance is fully executable: copy-paste-ready gog commands with flags and the exact sheet range and ID, the enumerated sheet headers from "Invitations!A1:Q1", a per-opportunity markdown file template, and concrete numbered steps for adding an opportunity. Not below 5 — the commands and template cover the common cases directly.	5 / 5
Workflow Clarity	Multi-step processes are explicitly sequenced with validation checkpoints: a numbered Verification procedure required before changing status, a numbered add-an-opportunity sequence, and for the batch sheet write an explicit post-write check ("re-read the range and verify row count plus no podcast/press name hits") with a recovery rule ("Overwrite stale podcast/press rows"). The batch operation has both a checkpoint and a fix path, matching anchor 5.	5 / 5
Progressive Disclosure	A single-file skill with no bundle files, organized into six clear, well-scoped sections that make navigation easy. It sits at anchor 4 rather than 5 because some reference-shaped content — the 17-column sheet-header inventory and the per-opportunity file template — is inlined in SKILL.md and would be more discoverable in a reference file as the skill grows.	4 / 5
	Total	18 / 20 Passed

Description

56%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 appropriately concise and keyword-rich with good natural trigger terms and a distinct niche, but it is a fragment rather than a sentence: it lists objects without stating any actions and omits any explicit "when to use this" guidance. Rewriting it as a third-person sentence pairing 2-3 concrete capabilities with a trigger clause would move it from mediocre to strong.

Suggestions

State concrete actions instead of only nouns, e.g. "Tracks, evaluates, and responds to speaking invitations (keynotes, panels, firesides) across Gmail, Google Calendar, and the conference opportunities sheet."

Add an explicit trigger clause: "Use when a speaking invite, keynote request, panel, or conference opportunity arrives, or when triaging Peter's speaking calendar."

Include a few missing synonyms users would naturally say — "talks", "summits", "firesides" — to round out trigger coverage without adding length.

Dimension	Reasoning	Score
Specificity	The description is a noun inventory — "invites, keynotes, panels, Gmail/calendar, conferences" — that names the speaking-ops domain but contains no verbs or concrete actions (track, evaluate, respond, sync). It matches anchor 2 ("Names the domain but actions are minimal or generic") rather than 3 because not even 1-2 specific actions are stated.	2 / 5
Completeness	A recognizable "what" is present (managing speaking opportunities across invites, keynotes, panels, Gmail/calendar), but there is no "Use when..." or equivalent trigger clause, which caps completeness at 3 per the judging guidelines. Not 4 because the "what" itself is fragmentary — the actual operation (tracking, evaluating, responding) must be inferred.	3 / 5
Trigger Term Quality	"invites, keynotes, panels, conferences, Gmail/calendar" plus "Speaking" are natural terms a user would say when needing this skill. It falls short of anchor 5 because common variations like "talks", "summits", "firesides", or "CFP" are absent.	4 / 5
Distinctiveness Conflict Risk	"Speaking ops" with keynotes, panels, and conference invites is a clear niche unlikely to trigger the wrong skill. Only minor overlap risk exists with generic calendar/email-management skills via the "Gmail/calendar" wording, keeping it below 5.	4 / 5
	Total	13 / 20 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: 3f8c6a3

Reviewed: 2 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.