Name: deep-work
Rating: 73.6 (1 reviews)
Author: alirezarezvani

deep-work

Use when someone wants to plan a deep work day, time-block their calendar or task list, budget or cut shallow work, protect focus hours, track deep-work sessions and streaks, run an end-of-day shutdown ritual, or says "/deep-work" or "/time-block". Classifies tasks deep vs shallow, builds an energy-first time-blocked schedule that refuses deep demand past the 4-hour ceiling, batches shallow work into at most two windows, and logs focus sessions against a weekly target.

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

The canonical home for this skill is deep-work in alirezarezvani/claude-skills

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.

The body is highly actionable with a well-sequenced, validation-backed workflow and lean code examples. The main defect is progressive disclosure: all referenced bundle files (3 scripts, 3 references, 2 assets) are absent from the working directory, breaking the otherwise good navigation.

Suggestions

Ship the referenced bundle files (scripts/shallow_work_auditor.py, scripts/time_block_planner.py, scripts/focus_session_logger.py, references/*.md, assets/*.md) or remove the broken links so navigation is not broken.

Trim rhetorical padding in the intro and Rules sections (e.g. "A calendar full of reactions is not a plan", "measured, not felt") to improve token efficiency without losing guidance.

Add an explicit fix-and-re-run loop for the OVER-BUDGET and refusal cases (e.g. "if OVER-BUDGET: cut/batch/delegate items, then re-run the auditor") to make the error-recovery feedback loop fully concrete.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable commands and a tight scripts table, but the intro and Rules sections carry rhetorical padding ("A calendar full of reactions is not a plan", "the trained daily ceiling", "measured, not felt") that could be trimmed without losing information.	4 / 5
Actionability	Copy-paste-ready commands are given for each step (e.g. `python scripts/time_block_planner.py --start 08:30 --end 17:00 --lunch 12:30 --task ...`), with the common cases covered and a table mapping each script to its role.	5 / 5
Workflow Clarity	A clear 4-step sequence (classify/budget → block → log → shutdown) with explicit validation checkpoints — OVER-BUDGET (exit 2), the 4-hour deep cap refusal, and shallow-overflow refusal that names what to defer or drop — and a referenced shutdown checklist.	5 / 5
Progressive Disclosure	Structure and signaling are excellent (one-level-deep references, each with a clear description), but the actual bundle is empty: ./scripts/, ./references/, and ./assets/ contain none of the 8 referenced files, so the navigation links are broken.	3 / 5
	Total	17 / 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.

The description is strong across all dimensions: it states concrete capabilities, opens with an explicit "Use when" trigger clause covering many natural phrasings, and carves a distinct niche. No vague fluff or over-claims are present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Classifies tasks deep vs shallow", "builds an energy-first time-blocked schedule that refuses deep demand past the 4-hour ceiling", "batches shallow work into at most two windows", "logs focus sessions against a weekly target" — with comprehensive coverage and no vague filler.	5 / 5
Completeness	Explicitly answers both: the "when" via a leading "Use when someone wants to plan a deep work day, time-block their calendar..." clause, and the "what" via concrete capability statements (classify, schedule, batch, log).	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including synonyms and slash commands: "plan a deep work day", "time-block their calendar or task list", "budget or cut shallow work", "protect focus hours", "track deep-work sessions and streaks", and "/deep-work" or "/time-block".	5 / 5
Distinctiveness Conflict Risk	Clear niche — one person's attention across a day/week with a 4-hour deep ceiling, deep/shallow classification, and a shutdown ritual — with distinctive triggers that minimize overlap with generic time-blocking or task skills.	5 / 5
	Total	20 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 5 missing	Warning
referenced_paths_exist	Referenced path issues: 18 missing	Warning

	Total	13 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/deep-work/SKILL.md
Commit: 19392f7

Reviewed: ~3 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.