release-tweets

Release tweets: draft/copy/post from changelog, tags, npm/appcast, artifacts.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/release-tweets/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.

A lean, highly actionable instruction skill: concrete tweet shapes, hard character limits, gated posting behavior, and a validation checklist that covers the common launch, beta, and hotfix cases. Structure and sequencing are strong; the only trims available are a small redundancy between the grounding rules and the quality checklist, and optionally externalizing the examples.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (it never explains what a tweet or changelog is) and every section carries guidance, but "No unverified claims" in Quality Pass repeats the grounding rule from "Ground The Copy", and the three full examples could be tightened to two. That puts it at 'minor instances that could be trimmed' rather than the every-token-earns-its-place level.	4 / 5
Actionability	Guidance is fully concrete and executable for a copy-writing skill: an exact tweet format, hard character budgets ("under 280", "160-220 raw characters"), specific commands (`pbcopy`, the local `bird`/`xurl` workflow), and three copy-ready example tweets covering launch, beta, and hotfix cases. This matches the anchor for complete, specific guidance covering the common cases.	5 / 5
Workflow Clarity	The workflow is clearly sequenced — verify release evidence, draft, count characters, then run the explicit "Quality Pass" checklist before presenting as final — with the risky outward-facing action (posting) gated ("Do not post... unless the user explicitly asks") and followed by verification of the posted URL. The quality-pass checklist provides the validation/feedback loop the top anchor requires.	5 / 5
Progressive Disclosure	There are no bundle files, and the body is organized into well-labeled sections (Ground The Copy, Launch Tweet Shape, Beta/Hotfix, Threads, Posting, Quality Pass, Examples) with no nested or dead references. At ~100 lines with a ~30-line Examples section, the examples could reasonably live in a separate file, so it sits just below the clear-split top anchor.	4 / 5
	Total	18 / 20 Passed

Description

66%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 terse, third-person description that names concrete actions and distinctive release-engineering triggers without padding. Its one structural weakness is the missing explicit "when to use" clause, which caps completeness and leaves natural trigger phrases like "launch tweet" or "X announcement" out of the description itself.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks for a release tweet, launch tweet, X announcement, or release thread for a shipped version."

Include the natural synonyms already present in the body ("launch tweet", "X/Twitter announcement", "release thread") so the description alone carries the trigger vocabulary.

Consider mentioning the beta/hotfix framing capability, since correction-release tweets are a distinct use case a user might invoke by name.

Dimension	Reasoning	Score
Specificity	"draft/copy/post from changelog, tags, npm/appcast, artifacts" names several concrete actions plus grounding sources, matching the 'lists several specific actions; minor gaps' anchor. It falls short of 5 because capabilities the body covers (threads, beta/hotfix framing) are absent from the description, and above 3 because it lists more than 1-2 actions.	4 / 5
Completeness	The "what" is clear (draft/copy/post release tweets from release evidence), but there is no "Use when..." clause or equivalent explicit trigger guidance in the description, which caps completeness at 3 per the judging guidelines. The "when" is only weakly implied by the topic noun "Release tweets".	3 / 5
Trigger Term Quality	"release tweets", "changelog", "npm", "appcast" are natural phrases a user would say, giving good keyword coverage. Not 5: common variants the body itself uses ("launch tweet", "X announcement", "thread", "social copy") are missing from the description.	4 / 5
Distinctiveness Conflict Risk	The niche is clear (release copy grounded in changelog/tags/npm/appcast evidence) with distinct technical triggers, so it is mostly distinguishable from sibling skills. Minor overlap risk remains with a generic social-media posting or tweet-writing skill, keeping it at anchor 4 rather than 5.	4 / 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: steipete/agent-scripts
Path: skills/release-tweets/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.