CtrlK
BlogDocsLog inGet started
Tessl Logo

delegate-to-ide

Delegate a task to another AI IDE's CLI (codex / claude / opencode / cursor-agent) through an isolated-context subagent. Triggers on "delegate to <ide>", "have <ide> do <task>", "execute <task> in <ide>", "offload to <ide>". For one-shot relay or fan-out comparison use `ai-ide-runner` instead.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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-structured, actionable routing protocol that assumes Claude's intelligence and gives concrete per-host invocation steps with an explicit error path. All four dimensions land at 4: solid but with trimmable repetition and no progressive file split.

Suggestions

Consolidate the repeated 'do not run the child CLI inline / use the subagent' warning into one canonical statement; the current intro, Step 2, and Output-contract restatements can be trimmed to a single cross-reference.

Since the body exceeds 50 lines, consider moving the per-host invocation syntax table or the Scope boundaries into a short references file and linking to it from SKILL.md to push progressive_disclosure toward a 5.

Tighten Step 1's intent-parsing prose ('Strip routing scaffolding ... so the worker passes a clean prompt') into a concrete before/after example to lift actionability.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no explaining what an IDE is), but the 'do not shell out inline / use the subagent' warning recurs three times (intro, Step 2 Cursor/Codex case, Output contract), which is trimmable repetition.

4 / 5

Actionability

Gives concrete per-host invocation syntax (Agent/Task with subagent_type=worker; @worker mention) and a copy-paste template block, with minor gaps where Cursor/Codex are routed away rather than given an executable path.

4 / 5

Workflow Clarity

A clear three-step sequence with an explicit error pass-through ('If the worker reports... pass that message through and stop') and a self-correction loop ('STOP — go to Step 2'); this is a relay, not a destructive/batch op, so the validation cap does not apply.

4 / 5

Progressive Disclosure

Well-sectioned into When-to-use, Workflow, Output contract, and Scope boundaries with no nested references and easy navigation, but at ~100 lines with no file split it sits just above the simple-skill threshold that would warrant a 5.

4 / 5

Total

16

/

20

Passed

Description

95%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 tight, third-person description that states the mechanism, enumerates natural trigger phrases, and explicitly de-conflicts against a sibling skill. The only minor gap is that the capability is a single delegation action rather than a suite of actions.

DimensionReasoningScore

Specificity

Names the concrete mechanism ('through an isolated-context subagent') and four explicit targets (codex / claude / opencode / cursor-agent), but the action set is essentially a single verb (delegate), leaving minor coverage gaps versus a comprehensive multi-action list.

4 / 5

Completeness

Explicitly answers both 'what' (delegate a task to another AI IDE's CLI via an isolated-context subagent) and 'when' (concrete trigger phrases), matching the anchor for clear what-and-when with triggers.

5 / 5

Trigger Term Quality

Enumerates four natural user phrasings ('delegate to <ide>', 'have <ide> do <task>', 'execute <task> in <ide>', 'offload to <ide>') — comprehensive synonym coverage of phrases a user would actually say.

5 / 5

Distinctiveness Conflict Risk

The closing clause ('For one-shot relay or fan-out comparison use ai-ide-runner instead') carves out a clear niche and actively de-conflicts from the sibling skill, minimizing wrong-skill trigger risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
korchasa/flowai-plugins
Reviewed

Table of Contents

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.