CtrlK
BlogDocsLog inGet started
Tessl Logo

engineer-ai-ide-plugin

Design and build complete AI-IDE plugins bundling skills, MCP tools and hooks with packaging, manifests, marketplaces and per-IDE validation. Use when the user wants to create, design or package a multi-component plugin. Not for a standalone skill.

69

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

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 orchestration skill with a clear sequenced workflow, concrete manifest/path guidance, and built-in validation steps. The main gap is that exact executable commands are deferred to external official docs rather than supplied inline, which slightly limits actionability.

Suggestions

Add a few concrete, commonly-needed commands inline (e.g. a representative manifest-validation or plugin-install command per major IDE) so Claude has copy-paste-ready starting points before fetching docs.

Tighten the 'Official Docs First' section — the 'fetch only the sections needed' and 'do not spawn subagents' guidance is restated; consolidate to remove redundancy.

Make the per-step validation checkpoints more explicit as validate->fix->retry feedback loops (e.g. 're-run the host validator until it passes before emitting install files') to lift workflow clarity toward a 5.

DimensionReasoningScore

Conciseness

Lean, directive guidance that does not over-explain basics Claude already knows; the docs-first message is restated a few times and could be tightened slightly.

4 / 5

Actionability

Names concrete paths and manifests (e.g. .claude-plugin/plugin.json, .app.json, .mcp.json, skills/<name>/SKILL.md) and gives an ordered workflow, but defers exact install/validator commands to official docs rather than providing them inline.

4 / 5

Workflow Clarity

Clear 8-step sequenced workflow with validation as an explicit step (host validators, MCP probes, trusted-session checks); minor validation-detail gaps remain, and the destructive/batch cap is not triggered because validation is present.

4 / 5

Progressive Disclosure

No bundle files exist; the single body is well-organized into clear sections with clearly signaled, one-level-deep external doc URLs. Minor organization gaps keep it just below a 5.

4 / 5

Total

16

/

20

Passed

Description

92%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 strong, specific description with concrete actions, explicit trigger guidance, and a clear boundary clause. Trigger-term coverage is the only mild weakness, missing some natural synonyms and IDE-specific phrasings.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — bundling skills/MCP tools/hooks, packaging, manifests, marketplaces, per-IDE validation — giving comprehensive coverage of the plugin-engineering domain.

5 / 5

Completeness

Explicitly answers both what ('Design and build complete AI-IDE plugins bundling...') and when ('Use when the user wants to create, design or package a multi-component plugin'), plus a negative boundary clause.

5 / 5

Trigger Term Quality

Good natural-keyword coverage ('create, design or package a multi-component plugin', 'plugin', 'AI-IDE', 'marketplaces'), but a few natural synonyms and IDE-specific terms a user might say are missing.

4 / 5

Distinctiveness Conflict Risk

Clear multi-component-plugin niche with distinct triggers and an explicit 'Not for a standalone skill' boundary that minimizes conflict with single-element skills.

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.