context-management-context-restore

Use when working with context management context restore

Quality

21%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/context-management-context-restore/SKILL.md

Quality

Content

35%

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, structured but monolithic document that mixes genuinely useful code and workflows with substantial fluff. Guidance is only partly actionable because the code relies on undefined helpers, and workflows lack validation checkpoints; progressive disclosure is undermined by inline detail and a non-existent reference path.

Suggestions

Cut the Context Overview, Integration Patterns, and Future Roadmap sections and trim the repeated Use/Do-not-use title phrases to respect the token budget.

Make the Python examples self-contained by defining the helper functions or replacing them with concrete library calls, so the code is copy-paste ready.

Add explicit validation/feedback-loop checkpoints into Reference Workflows (e.g. validate restored context against the current codebase, retry on mismatch), and fix the resources/implementation-playbook.md reference to point at a real bundle path.

Dimension	Reasoning	Score
Conciseness	The body is padded with sections Claude does not need to act (Context Overview, Integration Patterns, Future Roadmap with 'Quantum-inspired vector search algorithms'), and the Use/Do-not-use sections repeat the verbose title verbatim.	1 / 3
Actionability	The bash usage examples are concrete, but the Python samples call undefined helpers (VectorDatabase, rank_and_filter_contexts, calculate_composite_score, prioritize_components) and read as pseudocode rather than executable code.	2 / 3
Workflow Clarity	Reference Workflows list numbered steps, but there are no validation checkpoints or fix-and-retry feedback loops despite context merging/conflict-resolution being a risky operation.	2 / 3
Progressive Disclosure	Sections are organized, but everything (eight retrieval strategies, full code, workflows) is inline in one monolithic file; the only reference, resources/implementation-playbook.md, is weakly signaled and no such bundle file exists.	2 / 3
	Total	7 / 12 Passed

Description

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 placeholder-quality trigger phrase: it provides only a 'when' clause wrapped in redundant jargon, with no statement of what the skill does. It fails the what/when completeness bar and lacks natural, distinguishable trigger terms.

Suggestions

Add concrete actions the skill performs (e.g. 'retrieve, rank, and rehydrate project context from a vector store') to address specificity and the missing 'what'.

Replace the redundant 'context management context restore' phrasing with natural terms a user would say, such as 'restore context', 'rehydrate memory', or 'resume a project'.

Tighten the trigger to a clear niche (e.g. 'Use when resuming a long-running multi-agent project and rehydrating its stored context') to reduce overlap with other context skills.

Dimension	Reasoning	Score
Specificity	The phrase "Use when working with context management context restore" names a domain but states no concrete actions at all, matching the vague/abstract anchor rather than the 'names domain and some actions' level.	1 / 3
Completeness	It gives an explicit 'when' ("Use when working with...") but omits 'what does this do' entirely, so the what/when pair is missing one half.	1 / 3
Trigger Term Quality	"context management context restore" is redundant jargon a user would not naturally say; it lacks the natural trigger keywords users would actually voice.	1 / 3
Distinctiveness Conflict Risk	"context restore" gives it a somewhat specific niche, but the generic phrasing could still overlap with other context-management skills rather than being clearly distinct.	2 / 3
	Total	5 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/context-management-context-restore/SKILL.md
Commit: a3068b7

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.