deepwork

High-cost orchestrator workflow for large, high-risk, multi-phase coding efforts with meaningful dependencies and review gates. Do not activate for routine multi-file changes.

Quality

74%

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 ./src/skills/deepwork/SKILL.md

Quality

Content

81%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 a well-structured orchestrator workflow with strong sequencing, explicit validation gates, and concrete reusable artifacts (gitignore rules, attempt-tracking strings). It is efficient and actionable, with only minor conciseness and progressive-disclosure refinements possible given there is no reference bundle to offload detail into.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence about orchestration concepts, avoiding tutorial padding; a few sentences restate the same scheduling discipline across sections and could be tightened, but it is not verbose.	4 / 5
Actionability	It gives concrete, executable guidance (exact .gitignore/.ignore entries, a deepwork-file path pattern, a literal Oracle re-review attempt string to reuse, specific delegation roles), with only minor gaps where steps remain procedural prose rather than copy-paste commands.	4 / 5
Workflow Clarity	The multi-phase process is clearly sequenced (setup -> planning -> phase execution -> gate/commit -> completion) with explicit validation checkpoints, bounded remediation feedback loops, and re-review attempt tracking for a destructive/high-risk coordination workflow.	5 / 5
Progressive Disclosure	Content is well-organized into clear sections with a single local progress-file reference pattern and one-level-deep file references; there are no external bundle files to defer to, and some inlined detail (e.g. the full .gitignore rules) could arguably live separately, so it stops short of a 5.	4 / 5
	Total	17 / 20 Passed

Description

67%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 specific, third-person, and includes explicit anti-trigger guidance that reduces conflict risk, but it leans on a negative framing of when to use rather than a concrete positive 'Use when...' trigger phrase. Trigger-term coverage is decent but misses the natural synonyms a user would say. Overall a solid, slightly above-midpoint description.

Suggestions

Add a positive 'Use when...' clause with concrete natural trigger phrases (e.g. 'Use when tackling a large risky refactor, a cross-cutting architecture change, or a multi-phase migration with review gates').

Include everyday synonyms users actually say (e.g. 'big refactor', 'risky migration', 'coordinated multi-phase change') alongside the formal phrasing.

Dimension	Reasoning	Score
Specificity	The description names the domain ('large, high-risk, multi-phase coding efforts with meaningful dependencies and review gates') and several concrete behaviors (orchestrator workflow, scheduling, phased review), with only minor gaps in operational specificity.	4 / 5
Completeness	It states what the skill does ('High-cost orchestrator workflow for large, high-risk, multi-phase coding efforts') and gives explicit when-not-to-use guidance ('Do not activate for routine multi-file changes'), but the positive 'when to use' trigger is implied rather than phrased as a 'Use when...' clause.	4 / 5
Trigger Term Quality	It uses some natural phrasing ('multi-phase coding efforts', 'routine multi-file changes') but lacks the everyday trigger words a user would actually say (e.g. 'big refactor', 'risky migration', 'coordinated change'), and the strongest trigger guidance is framed negatively.	3 / 5
Distinctiveness Conflict Risk	The clear 'Do not activate for routine multi-file changes' boundary and the niche framing as a high-cost orchestrator distinguish it from ordinary coding skills, with only minor overlap risk against general planning or multi-file edit skills.	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: alvinunreal/oh-my-opencode-slim
Path: src/skills/deepwork/SKILL.md
Commit: 3222930

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.