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

76%

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

77%

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-sequenced, actionable orchestration contract with explicit review gates and remediation feedback loops. Its main weaknesses are duplicated instructions that bloat the token budget and a monolithic structure with no progressive disclosure into reference files.

Suggestions

De-duplicate the .gitignore/.ignore instructions: state them once and reference back, rather than repeating the full block in both 'Core Contract' and 'Deepwork File'.

Consolidate the anti-micro-phase guidance so it appears once instead of being restated across 'Core Contract' and 'Planned Phase Reviews'.

Consider moving the 'Designer Handoff Guardrail' detail and the deepwork-file template guidance into reference files so SKILL.md reads as an overview with one-level-deep pointers.

Dimension	Reasoning	Score
Conciseness	The imperative bullet style is lean and assumes competence, but the .gitignore/.ignore instructions are duplicated across 'Core Contract' and 'Deepwork File', and the anti-micro-phase guidance is restated in 'Planned Phase Reviews'.	2 / 3
Actionability	Guidance is concrete and copy-paste ready for an instruction skill: exact paths ('.slim/deepwork/'), literal gitignore entries, named agents (@oracle, @designer, @fixer, @librarian) with specific responsibilities.	3 / 3
Workflow Clarity	The 'Required behavior' list is a clearly sequenced pipeline with explicit validation checkpoints (per-phase Oracle review gates, final validation) and a feedback loop (triage findings into one remediation pass, validate, conditionally re-review).	3 / 3
Progressive Disclosure	Sections are well-headed, but the skill is a monolithic single-file contract with no overview-to-reference split; the designer guardrail and file-template detail are inline rather than factored into bundle files.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 clearly carves out a distinct high-cost orchestration niche with explicit positive and negative trigger guidance, answering both what and when. It is slightly held back by abstract, role-level phrasing rather than concrete enumerated actions and by missing some common user phrasings.

Dimension	Reasoning	Score
Specificity	It names the domain ('orchestrator workflow for large, high-risk, multi-phase coding efforts') and the review-gate mechanic, but describes a role rather than listing multiple concrete actions like the score-3 anchor.	2 / 3
Completeness	It answers what (a high-cost orchestrator workflow) and gives explicit when guidance both positively ('for large, high-risk, multi-phase coding efforts...') and negatively ('Do not activate for routine multi-file changes').	3 / 3
Trigger Term Quality	'large, high-risk, multi-phase coding efforts' and 'routine multi-file changes' are reasonably natural, but common user phrasings ('big refactoring', 'large migration', 'high-risk change') are missing.	2 / 3
Distinctiveness Conflict Risk	The high-cost orchestration niche with review gates is distinct, and the explicit 'Do not activate for routine multi-file changes' exclusion keeps it from conflicting with ordinary coding skills.	3 / 3
	Total	10 / 12 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: 1c0e1f4

Reviewed: about 8 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.