CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

manage-cde

Manage Harness Cloud Development Environments (CDE) via MCP. Configure on-demand development environments with pre-installed tooling, design standardized workspace templates for teams, set up auto-hibernation and cost controls, and manage environment lifecycle. Use when asked to set up cloud dev environments, create workspace templates, configure remote development, or manage CDE lifecycle and costs. Trigger phrases: cloud dev environment, CDE, remote development, workspace template, dev environment, gitpod, codespace, auto-hibernation, developer workspace, ephemeral environment.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/claude/skills/manage-cde/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

46%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 well-organized and clearly sequenced, and its troubleshooting section is a nice touch, but it stops short of being executable: beyond the initial harness_list scoping call, none of the actual CDE operations name an MCP tool or give commands, and no validation checkpoints exist in the workflow. Generic per-role tooling lists also spend tokens on knowledge Claude already has.

Suggestions

Name the actual MCP tools (with parameter blocks like the harness_list example) for the core operations: creating/updating environment templates, configuring auto-hibernation, and setting cost caps, so the skill is executable end to end.

Add validation checkpoints and feedback loops after configuration steps — e.g., verify a provisioned environment starts within the target time and confirm a template applied correctly before finishing.

Trim the per-role tool lists (backend/frontend/full-stack/devops) to the Harness-specific configuration values, dropping generic tooling knowledge Claude already has.

DimensionReasoningScore

Conciseness

The body is mostly efficient, well-structured bullets, but the per-role template lists restate knowledge Claude already has — e.g., "Frontend Developer: Node.js runtime, package manager, Browser dev tools, component library, Hot-reload and preview server" and "kubectl, Helm, Terraform, cloud CLIs" — so it fits 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the leaner level above.

3 / 5

Actionability

Only one executable instruction is given ("Call MCP tool: harness_list" with parameters); the core operations — creating environment templates, configuring auto-hibernation, setting cost caps — are described as checklists of things to decide but never name an MCP tool or provide concrete steps to execute. This matches 'minimal concrete guidance; high-level hints but missing the specific steps to execute' more than the 'some concrete guidance but incomplete' level above.

2 / 5

Workflow Clarity

Steps 1–4 (Establish Scope → Identify Task → Configure On-Demand Environments → Create Workspace Templates) form a clear sequence, but there are no validation checkpoints (no verify-environment-provisioned or confirm-template-applied step) and batch provisioning of environments/templates lacks feedback loops, which fits 'steps listed but validation gaps'.

3 / 5

Progressive Disclosure

There are no bundle files and the ~115-line body is cleanly sectioned (Instructions, Examples, Performance Notes, Troubleshooting) with content appropriately placed in a single file; only the role-template lists and troubleshooting sections are borderline candidates for splitting out. This fits 'good structure; most content is appropriately placed; minor organization gaps' rather than the reference-signaling ideal of a 5.

4 / 5

Total

12

/

20

Passed

Description

96%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.

This is a strong description: it states concrete capabilities in third person, explicitly answers both what the skill does and when to use it, and provides a comprehensive list of natural trigger terms including synonyms. The only notable weakness is that brand-name triggers (gitpod, codespace) could pull in requests intended for those specific products rather than Harness CDE.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Configure on-demand development environments with pre-installed tooling, design standardized workspace templates for teams, set up auto-hibernation and cost controls, and manage environment lifecycle" — giving comprehensive coverage of the skill's capabilities, matching the top anchor rather than the 'several specific actions, minor gaps' level below.

5 / 5

Completeness

Both questions are explicitly answered: the 'what' via concrete capability statements and the 'when' via "Use when asked to set up cloud dev environments, create workspace templates, configure remote development, or manage CDE lifecycle and costs" plus a dedicated concrete trigger-phrase list, exactly matching the top anchor.

5 / 5

Trigger Term Quality

An explicit trigger list covers natural terms and synonyms users would say: "cloud dev environment, CDE, remote development, workspace template, dev environment, gitpod, codespace, auto-hibernation, developer workspace, ephemeral environment". Coverage is comprehensive for this domain; file extensions are not applicable, so the 'a few natural terms missing' level below does not fit.

5 / 5

Distinctiveness Conflict Risk

The skill occupies a clear Harness-CDE niche, but the trigger terms "gitpod, codespace" would also match requests about GitHub Codespaces or Gitpod itself, creating minor overlap risk with closely related skills. This fits 'mostly distinct; minor overlap risk' rather than the 'minimal conflict risk' of a 5, while being well above the overlap-prone lower anchors.

4 / 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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

harness/harness-ai

Path

plugins/claude/skills/manage-cde/SKILL.md

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.