CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agent-context-isolation

Agent Context Isolation

Quality

60%

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 ./.claude/skills/agent-context-isolation/SKILL.md
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.

The body is well-structured, actionable, and concise, providing concrete RIGHT/WRONG examples, a clear pipeline pattern, and verification via tests. Its main limitation is the absence of any referenced bundle files for deeper material, which keeps progressive disclosure just shy of the top anchor.

DimensionReasoningScore

Conciseness

The body is efficient with tight RIGHT/WRONG code comparisons and minimal padding, though the 'Why This Matters' section and 'Source' notes add a small amount of non-essential explanation.

4 / 5

Actionability

Concrete, copy-paste-ready commands are provided throughout (run_in_background=true, ls -la, bun test, find ... -mmin -5, wc -c), with only minor templating gaps like '<agent-type>' placeholders.

4 / 5

Workflow Clarity

Rules are clearly sequenced with a stuck-agent detection checklist and a verification step ('Run the test suite directly: bun test'), plus a multi-stage file-based pipeline diagram; only minor explicit validation checkpoints are absent.

4 / 5

Progressive Disclosure

Content is well-organized into clearly headed sections with no external bundle files present and no nested references; it is slightly over 50 lines so it sits just below the simple-skill满分 case.

4 / 5

Total

16

/

20

Passed

Description

25%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 is essentially just a skill title with no concrete actions, no trigger terms, and no explicit 'when to use' guidance, making it unlikely to surface at the right moment. It needs to be rewritten as a full sentence naming capabilities and trigger conditions.

Suggestions

Rewrite the description as a sentence stating concrete actions, e.g. 'Prevent agent output from polluting the main context window by using background agents with file-based coordination.'

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when spawning subagents, running long background tasks, or when context budget is constrained.'

Include synonyms and concrete trigger terms users would actually say (subagents, background tasks, TaskOutput, context pollution) to improve discovery and distinctiveness.

DimensionReasoningScore

Specificity

The description is just the title 'Agent Context Isolation', which names the domain but lists no concrete actions, matching the 'names the domain but actions are minimal or generic' anchor.

2 / 5

Completeness

It provides only a vague 'what' (isolation) and no 'when' / 'Use when...' guidance, matching the anchor for a vague what with no when.

2 / 5

Trigger Term Quality

'Agent Context Isolation' is a technical label rather than a phrase a user would naturally say; it offers only one generic keyword and lacks natural trigger phrasing.

2 / 5

Distinctiveness Conflict Risk

As a bare title it is very broad and could overlap with related agent-management skills, fitting the 'very broad; high overlap risk' anchor rather than a more specific one.

2 / 5

Total

8

/

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

parcadei/Continuous-Claude-v3

Path

.claude/skills/agent-context-isolation/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.