first-reader

Beta readers for any draft, run by simulating how a real reader experiences it, moment by moment. A skim gate, a no-lookahead timed read producing an attention transcript with quit points, a recall test of what a reader remembers the next day, and a trust ledger of the implied author. Use when the user asks for a beta read, beta readers, test readers, human review, reader review, to read something like a human, to be a first reader, whether a piece holds attention or will actually get read, for a quick read of whether a busy skimmer would even open a post, what readers will remember or take away tomorrow, where readers stop reading or bounce, or why a draft still feels off or hollow after anti-slop or humanizer edits. Final gate before publishing; reports where the reading broke; never rewrites.

Quality

92%

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

Quality

Content

85%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 well-engineered, highly actionable multi-step workflow with strong validation gating and clean one-level-deep references to real bundle files. Its only weakness is conciseness: the conceptual framing and rationale sections add padding that Claude does not need.

Suggestions

Tighten the opening two paragraphs and 'Why the discipline matters' by cutting conceptual exposition (e.g. the forager metaphor) and keeping only the operational discipline — the no-lookahead rationale can be stated in one line.

Collapse repeated contamination reminders into a single upfront rule referenced by later steps, rather than restating the contamination risk at steps 2, 5, and 6.

Trim the 'Adapting to your environment' section to a compact capability matrix (subagents / page publishing / turn budget) plus the one-line user-facing disclosure, removing narrative restatement.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the opening framing ('A human reader is a forager building a gist model under time pressure...') and the 'Why the discipline matters' section restate conceptual background Claude largely already knows and could be trimmed without losing instructional value.	3 / 5
Actionability	Provides copy-paste-ready commands with full argument patterns (e.g. 'feed.py serve <draft> --run <run-dir> --readers keen,skeptic --persona ... --ready-file <run-dir>/feed.json', 'feed.py next --log "needle=<-2..+2> expected... got..."', 'scripts/ask.py <run-dir> <reader> "<question>"'), covering the common cases concretely.	5 / 5
Workflow Clarity	Steps 0–7 are clearly sequenced with explicit validation checkpoints (contamination gating — 'only after the timed reads are complete', 'Only now read the draft in full, once, at step 6'), recall-judgment gates, quit detection, and an error-recovery adaptation path; this is a read-only skill so the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	The body is a clear overview pointing one level deep to real, verified files (references/personas.md, references/room.md, references/report.md, references/interview.md) and scripts, each clearly signaled with 'Read…', 'per…', and 'as … specifies'; content is appropriately split rather than inlined.	5 / 5
	Total	18 / 20 Passed

Description

100%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, third-person description that concretely enumerates the skill's four instruments and provides an exhaustive 'Use when...' clause of natural trigger phrases. It clearly distinguishes itself from adjacent editing/audit skills. No improvements needed.

Dimension	Reasoning	Score
Specificity	Names the domain and four concrete instruments ('a skim gate, a no-lookahead timed read producing an attention transcript with quit points, a recall test of what a reader remembers the next day, and a trust ledger of the implied author'), giving comprehensive coverage of actions rather than vague language.	5 / 5
Completeness	Explicitly answers both what ('Beta readers for any draft, run by simulating how a real reader experiences it') and when ('Use when the user asks for a beta read, beta readers, test readers...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural phrasing a user would actually say ('beta read', 'beta readers', 'test readers', 'whether a piece holds attention', 'where readers stop reading or bounce', 'why a draft still feels off or hollow'), including synonyms and casual variants.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (simulated beta-reading of prose drafts) with distinct triggers and explicit boundary cues ('Final gate before publishing', 'never rewrites'), minimizing overlap with audit or editing skills.	5 / 5
	Total	20 / 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: Shubhamsaboo/awesome-llm-apps
Path: agent_skills/first-reader/SKILL.md
Commit: 4bf51ab

Reviewed: 1 day 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.