CtrlK
BlogDocsLog inGet started
Tessl Logo

engineer-plugin-hooks

Build AI-IDE plugin hook elements - shared policies plus Claude Code/Codex/OpenCode/Cursor adapters for lifecycle events, blocking, audit, and context injection. Use when adding or configuring plugin hooks.

65

Quality

79%

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/flowai-engineering/skills/engineer-plugin-hooks/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 a lean, well-structured overview that defers volatile hook specifics to official docs and gives a clear sequenced workflow with per-host validation caveats. It loses only minor points for lacking copy-paste code/config examples and explicit validate-retry command loops.

Suggestions

Add one short copy-paste example of a normalized decision return shape and a host adapter snippet to lift actionability to fully executable.

Make the validation step a concrete validate->fix->retry loop with example commands per host to strengthen workflow_clarity's feedback-loop checkpoint.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, avoiding explanation of basic hook or plugin concepts; every section (Official Docs First, Workflow, Output Shape, Pitfalls) earns its place with directive, unpadded language.

5 / 5

Actionability

Provides concrete, executable guidance such as specific doc URLs, an explicit normalize-input field list, and named validation caveats, but offers no copy-paste code/config snippets, leaving minor gaps in executable detail.

4 / 5

Workflow Clarity

The six-step workflow is clearly sequenced with validation guidance per host and explicit Codex interactive-vs-non-interactive checkpoints, though validation is described as a directive rather than as a concrete validate->fix->retry feedback loop with commands.

4 / 5

Progressive Disclosure

Content is well-organized into clearly signaled sections (Official Docs First, Workflow, Output Shape, Pitfalls) with no bundle files to manage; it stays a concise overview pointing to external official docs rather than inlining spec detail, with only minor room for tighter reference signaling.

4 / 5

Total

17

/

20

Passed

Description

76%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 clearly states both what the skill does and when to use it, naming concrete host adapters and hook event types. It is slightly hindered by limited trigger-term synonyms and minor overlap with project-level hook workflows.

Suggestions

Add a few natural user-phrase synonyms (e.g. 'block a tool', 'inject context', 'audit hook events') to broaden trigger-term coverage.

Sharpen distinctiveness by contrasting plugin hooks versus project hooks directly in the description (e.g. 'for hooks shipped inside a plugin, not one-off project hooks').

DimensionReasoningScore

Specificity

Lists several concrete capabilities ('shared policies plus Claude Code/Codex/OpenCode/Cursor adapters for lifecycle events, blocking, audit, and context injection'), naming specific hosts and hook event categories, with only minor gaps in per-host coverage detail.

4 / 5

Completeness

Explicitly answers what ('Build AI-IDE plugin hook elements - shared policies plus ... adapters for lifecycle events, blocking, audit, and context injection') and when ('Use when adding or configuring plugin hooks') with a concrete trigger clause.

5 / 5

Trigger Term Quality

Includes natural terms like 'plugin hooks', 'lifecycle events', 'blocking', and 'context injection', but lacks common synonym variations and explicit user-phrase forms users would naturally utter beyond 'adding or configuring plugin hooks'.

3 / 5

Distinctiveness Conflict Risk

The 'AI-IDE plugin hook' niche with named hosts is mostly distinct and unlikely to trigger for unrelated skills, with only minor overlap risk against generic project-hook authoring workflows.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

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.