CtrlK
BlogDocsLog inGet started
Tessl Logo

context-management-context-save

Use when working with context management context save

49

1.31x
Quality

25%

Does it follow best practices?

Impact

91%

1.31x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/context-management-context-save/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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 long, sectioned overview heavy on abstract conceptual description and light on executable guidance: code examples are stubs calling undefined functions, workflows lack validation, and the single referenced file does not exist. It is broadly a level-2 effort across all dimensions.

Suggestions

Cut conceptual padding (Role/Purpose, Context Management Overview, Advanced Integration Capabilities, Future Roadmap) and keep only guidance Claude would not already know.

Make code examples executable by defining the helper functions or replacing them with real, runnable logic.

Add validation/verification checkpoints to the capture workflows (e.g. verify context fingerprint integrity before archiving) and either create resources/implementation-playbook.md or remove the broken reference.

DimensionReasoningScore

Conciseness

The body mixes useful concrete material (code, JSON schema) with substantial conceptual padding Claude already knows ('An elite context engineering specialist focused on comprehensive, semantic, and dynamically adaptable context preservation') and buzzword sections like 'Advanced Integration Capabilities' and 'Future Roadmap'.

2 / 3

Actionability

Code examples are present but call undefined functions (extract_project_metadata, semantic_compression, advanced_vector_compression), making them pseudocode/stubs rather than executable, and the numbered workflows are abstract directions without commands.

2 / 3

Workflow Clarity

Workflows list a numbered sequence ('1. Analyze project structure, 2. Extract architectural decisions...') but contain no validation checkpoints or feedback loops for context-capture/batch operations, capping clarity at 2 per the rubric.

2 / 3

Progressive Disclosure

No bundle directories (references/scripts/assets) exist, and the one body reference to resources/implementation-playbook.md points to a non-existent file; content is monolithically inline with section headers but nothing appropriately split out.

2 / 3

Total

8

/

12

Passed

Description

0%

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 a near-empty tautology: it restates the skill name as a trigger and says nothing about what the skill does or what natural terms a user would say. It fails specificity, trigger quality, completeness, and distinctiveness alike.

Suggestions

Replace the description with concrete capabilities, e.g. 'Capture, serialize, and retrieve project context across sessions; generate context fingerprints and semantic embeddings. Use when preserving or restoring project state, handoffs, or multi-session context.'

Add natural trigger terms a user would actually say (e.g. 'save context', 'project handoff', 'context snapshot', 'session context').

State explicitly what the skill does AND when to use it, rather than repeating the skill name.

DimensionReasoningScore

Specificity

The description 'Use when working with context management context save' names no concrete actions at all — it is purely a trigger phrase with zero capability verbs, matching the vague/abstract anchor ('Helps with documents').

1 / 3

Completeness

Although a 'Use when...' clause exists, it is tautological and the 'what does this do' half is entirely missing — both halves are weak, so it does not reach the level-2 'has what' bar.

1 / 3

Trigger Term Quality

'context management context save' is redundant, jargon-like, and unnatural; no user would say this when they need the skill, matching the 'no natural keywords' anchor.

1 / 3

Distinctiveness Conflict Risk

'context management' is extremely generic and would plausibly overlap with many other skills, matching the 'very generic; would conflict with many skills' anchor.

1 / 3

Total

4

/

12

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
sickn33/antigravity-awesome-skills
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.