large-workspace-handling

To partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.

Quality

48%

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 ./instructions/r2/core/skills/large-workspace-handling/SKILL.md

Quality

Content

50%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 skill is concise and reasonably well-structured, but its guidance is largely abstract — it lists what to assign to subagents without executable commands, concrete templates, or explicit validation checkpoints for its batch/destructive-style operations.

Suggestions

Add concrete executable guidance: a template prompt for dispatching a subagent (with the scope paths, goal, context, and output format fields filled in as an example) rather than only enumerating the fields to include.

Insert explicit validation checkpoints and an error-recovery loop in the workflow — e.g. after subagents complete, list the pass/fail criteria and what to do when verification fails (re-scope, re-dispatch, or escalate).

Turn KB skill name-drops ('ACQUIRE init-workspace-discovery/SKILL.md FROM KB') into clearly signaled references with paths so the dependency chain and navigation are unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is terse and assumes Claude's competence — mostly bullet directives with no padding or re-explanation of basic concepts, though a few sub-bullets could be tightened further.	4 / 5
Actionability	It gives high-level hints (assign scope paths, goal, context, output format) but no concrete executable commands, code, or precise templates; the guidance describes rather than instructs and is missing the specific steps to execute.	2 / 5
Workflow Clarity	A rough sequence is present (prep -> grep CODEMAP -> scope -> dispatch -> verify), but it has validation gaps; verification is mentioned only as a final 'spawn another set of subagents' step without explicit pass/fail checkpoints or error-recovery loops, and it is a batch operation.	3 / 5
Progressive Disclosure	Content is organized into labeled sections with clear headers, but references to other KB skills (init-workspace-discovery, reverse-engineering, load-context) are name-dropped rather than clearly signaled paths, and no bundle files exist to verify, so structure is present but navigation is underdeveloped.	3 / 5
	Total	12 / 20 Passed

Description

46%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 conveys a clear purpose and a reasonably distinct niche, but relies on technical jargon instead of natural user trigger phrases and lacks an explicit 'Use when...' clause, which limits trigger quality and completeness.

Suggestions

Add an explicit 'Use when...' clause with concrete user scenarios, e.g. 'Use when a task spans 100+ files and exceeds a single agent's context window, such as auditing or refactoring a large monorepo.'

Replace jargon ('context is insufficient', 'scoped subagent tasks') with natural trigger phrases a user would actually say, like 'workspace is too big', 'too many files', or 'split work across agents'.

List 1-2 more concrete actions to lift specificity, e.g. '...partition large workspaces into scoped subagent tasks, dispatch them in parallel, and merge their results.'

Dimension	Reasoning	Score
Specificity	Names the domain (large workspaces) and one concrete action ('partition into scoped subagent tasks'), but the action is generic without enumerating specific concrete operations like a 4-5 anchor would.	3 / 5
Completeness	It states a clear 'what' (partition workspaces into subagent tasks) and has a weak 'when' clause ('when context is insufficient'), but no explicit 'Use when...' trigger phrase with concrete user scenarios, capping completeness per the guidelines.	3 / 5
Trigger Term Quality	'large workspaces', 'context is insufficient', and 'subagent tasks' are technical jargon rather than the natural phrases a user would say; lacks common synonyms a user actually utters.	2 / 5
Distinctiveness Conflict Risk	The 100+ files and context-insufficiency framing carves a fairly distinct niche for workspace partitioning with only minor overlap risk against general delegation or context-management skills.	4 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: griddynamics/rosetta
Path: instructions/r2/core/skills/large-workspace-handling/SKILL.md
Commit: 70d401e

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.