CtrlK
BlogDocsLog inGet started
Tessl Logo

engram-plugin-thin

Adapter boundary rules for plugin integrations. Trigger: Changes in plugin scripts/hooks for Claude, OpenCode, Gemini, or Codex.

63

Quality

73%

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 ./skills/plugin-thin/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is admirably lean and well-organized for a simple instruction skill, but its guidance stops short of fully actionable specifics and the verification checklist is not wired into an explicit feedback loop.

Suggestions

Name the shared contract in rule 4 (e.g. link or identify the contract file/type) and add a minimal concrete example of a thin adapter so the guidance is copy-paste ready.

Turn the Compatibility Checklist into an explicit feedback loop: "Run each check; if any fails, fix the adapter and re-run all checks before considering the change complete."

DimensionReasoningScore

Conciseness

The body is lean throughout — terse bullet rules and a checklist with no explanation of concepts Claude already knows, so every token earns its place.

3 / 3

Actionability

Rules 1 and 2 give concrete specifics ("parse input, call API/tool, return" and the `store/server/mcp` Go paths), but rule 4's "Reuse a shared contract" leaves the contract unnamed and no executable example of a thin adapter is shown, leaving key details missing.

2 / 3

Workflow Clarity

The Compatibility Checklist supplies verification items, but the numbered Boundary Rules are principles rather than a sequenced process and there is no explicit validate-fix-retry feedback loop, so checkpoints are present but incomplete.

2 / 3

Progressive Disclosure

The skill is under 50 lines, needs no external references (none of references/scripts/assets are present), and is organized into clearly labeled sections (When to Use, Boundary Rules, Compatibility Checklist), meeting the simple-skill bar for full marks.

3 / 3

Total

10

/

12

Passed

Description

75%

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 answers both what and when with an explicit trigger and a distinct niche, but it leads with jargon and does not enumerate concrete actions, capping specificity and trigger-term quality at the mid level.

Suggestions

Replace the jargon-led opener with concrete actions, e.g. "Keep plugin adapters thin when editing hooks/scripts for Claude, OpenCode, Gemini, or Codex: parse input, call the API/tool, and return."

Add natural user-facing trigger variations such as "plugin hooks", "adapter scripts", or "agent integration setup" so the description matches phrasings a user would actually say.

DimensionReasoningScore

Specificity

The phrase "Adapter boundary rules for plugin integrations" names the domain clearly but states a concept rather than listing multiple concrete actions, so it sits at the 'names domain and some actions' level rather than the 'multiple specific concrete actions' level.

2 / 3

Completeness

It states what the skill provides ("Adapter boundary rules for plugin integrations") and gives an explicit trigger clause ("Trigger: Changes in plugin scripts/hooks for ..."), satisfying both the 'what' and 'when' with an explicit trigger.

3 / 3

Trigger Term Quality

"Changes in plugin scripts/hooks for Claude, OpenCode, Gemini, or Codex" supplies relevant, fairly natural trigger keywords, but the leading term "Adapter boundary rules" is technical jargon and common natural variations are not covered.

2 / 3

Distinctiveness Conflict Risk

The combination of "adapter boundary rules" plus the named agents (Claude, OpenCode, Gemini, Codex) carves a clear, narrow niche with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

10

/

12

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
Gentleman-Programming/engram
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.