context-management-context-restore

Use when working with context management context restore

1.70x

Quality

35%

Does it follow best practices?

Impact

87%

1.70x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/context-management-context-restore/SKILL.md

The canonical home for this skill is context-management-context-restore in sickn33/agentic-awesome-skills

Quality

Content

42%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 covers a lot of ground with code examples and structured sections, but it is padded with buzzwordy prose and fluff, its code is not directly executable, and its workflows lack real validation checkpoints. Progressive disclosure is undermined by an inlined monolith and a broken reference path.

Suggestions

Remove the Role Statement, Context Overview, Integration Patterns, and Future Roadmap sections, which restate concepts Claude already knows or add speculative fluff.

Make the code examples executable by defining or stubbing the helper functions they call, or explicitly mark them as illustrative pseudocode.

Add concrete validation steps and feedback loops to the reference workflows (e.g., a verify command and a retry-on-failure path), since context restoration is a batch-sensitive operation.

Either create the referenced "resources/implementation-playbook.md" (and place it under references/) or remove the dangling reference, and move the bulk of the strategy/code detail into that file so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with padded prose (Role Statement, Context Overview) and fluff such as the "Future Roadmap" listing "Quantum-inspired vector search algorithms" and "Self-healing context reconstruction" that add no actionable value.	2 / 5
Actionability	Concrete Python and bash examples are provided, but the code calls undefined helpers (VectorDatabase, rank_and_filter_contexts, calculate_composite_score, prioritize_components, load_component, estimate_tokens) making it illustrative rather than copy-paste executable.	3 / 5
Workflow Clarity	Two numbered reference workflows exist, but validation is only mentioned abstractly ("Validate context against current codebase") with no checkpoint command or feedback loop, and a potentially batch restoration operation without explicit verification caps clarity at 3.	3 / 5
Progressive Disclosure	Section headers provide some structure, but ~175 lines of strategies, code, and workflows are inlined while the single reference to "resources/implementation-playbook.md" points to a path that is not present in the bundle (no references/scripts/assets directories exist).	3 / 5
	Total	11 / 20 Passed

Description

28%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 minimal and circular: it restates the skill name as its trigger without explaining what the skill does or offering natural user phrasing. It is distinguishable from unrelated skills but weak on every other axis.

Suggestions

Add a concrete "what" clause listing specific actions, e.g. "Recovers and reconstructs project context across multi-agent workflows; rehydrates semantic memory from vector stores."

Replace the doubled jargon "context management context restore" with natural trigger phrases a user would actually say, such as "resuming a paused project", "restoring agent context", or "rehydrating project memory".

Combine what and when into a single explicit sentence modeled on the good examples (capability list + "Use when ...").

Dimension	Reasoning	Score
Specificity	The description "Use when working with context management context restore" names the domain but provides no concrete actions, only the generic verb "working with".	2 / 5
Completeness	It offers only a circular "Use when" trigger that restates the skill name and gives no "what" description of capabilities, matching the anchor where only a weak "when" is present without a "what".	2 / 5
Trigger Term Quality	The doubled jargon phrase "context management context restore" is technical and awkward rather than a phrase a user would naturally say; no natural synonyms or variations are present.	2 / 5
Distinctiveness Conflict Risk	The phrase points at a specific niche (context restoration) but the broad "context management" framing could still overlap with general context/memory skills.	3 / 5
	Total	9 / 20 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/context-management-context-restore/SKILL.md
Commit: 57c135b

Reviewed: 3 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.