context-management-context-restore

Use when working with context management context restore

1.70x

Quality

31%

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-claude/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

38%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 content is broad and well-sectioned but padded with conceptual filler and roadmap buzzwords, and its code is pseudocode built on undefined functions plus a non-existent CLI. The single external reference points to a missing file, so progressive disclosure fails rather than merely underperforming.

Suggestions

Cut the 'Role Statement', 'Context Overview', and 'Future Roadmap' sections and tighten each strategy to its actionable rule plus one real, runnable example.

Make the code executable by defining or importing the stubbed helpers (or replacing them with calls to a real library) so examples are copy-paste ready.

Add explicit validation checkpoints to the reference workflows (e.g. verify context signature, validate against current codebase, retry on mismatch) and either create the referenced playbook file under 'references/' or remove the broken pointer.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose, padding sections Claude does not need such as the 'Role Statement', 'Context Overview' defining what the tool is, and a buzzword-heavy 'Future Roadmap' ('Quantum-inspired vector search', 'Self-healing context reconstruction'); it is not a 3 because several sections are pure filler rather than minor over-explanation, and not a 1 because there are also concrete code and command blocks.	2 / 5
Actionability	Code blocks look executable but rely on undefined stubs (VectorDatabase, rank_and_filter_contexts, calculate_composite_score, prioritize_components, load_component, estimate_tokens) and the bash examples invoke a fictitious 'context-restore' CLI, fitting the 'pseudocode instead of executable code; missing key details' anchor; it is not a 4 because the core functions cannot run as written.	3 / 5
Workflow Clarity	The two 'Reference Workflows' list numbered steps but include no validation checkpoints or error-recovery feedback loops, even though context restoration is a validation-sensitive operation with a dedicated integrity-checks section that the workflows never invoke; it is not a 4 because checkpoints are absent or only implicit, and not a 2 because a real sequence is present.	3 / 5
Progressive Disclosure	No bundle files exist, yet the body references 'resources/implementation-playbook.md' (note the wrong 'resources/' directory) which is a broken, buried pointer, and content that clearly belongs in separate files (eight strategy sections, code, API-like parameter reference) is all inlined; it is not a 3 because the lone reference is broken and poorly signaled rather than merely imperfect.	2 / 5
	Total	10 / 20 Passed

Description

23%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 a vague trigger-only sentence that states when to use the skill but never says what it does or lists concrete capabilities, and its phrasing is unnatural. It needs an explicit 'what' clause and concrete actions to rise above a 2 on completeness.

Suggestions

Add a 'what' clause listing concrete actions, e.g. 'Recovers, ranks, and rehydrates project context from a vector store into a token-budgeted prompt.'

Rewrite the trigger in natural user language with synonyms, e.g. 'Use when resuming a long-running project, rehydrating lost context, or restoring multi-agent session state.'

Replace the redundant 'context management context restore' with distinct, conflict-resistant trigger terms so the skill is unlikely to fire for unrelated context tasks.

Dimension	Reasoning	Score
Specificity	The description 'Use when working with context management context restore' names no concrete actions at all, only a trigger clause, matching the 'entirely vague; no concrete actions' anchor; it is not a 2 because a 2 at least names a domain with minimal/generic actions, and here there are zero actions.	1 / 5
Completeness	Only a 'when' clause is present ('Use when working with...') with no statement of what the skill does, matching the 'only when is present without what' anchor; it is not a 3 because there is no clear 'what' at all, and not a 1 because an explicit trigger clause does exist.	2 / 5
Trigger Term Quality	The phrase 'context management context restore' is awkward and redundant rather than natural user language, offering one or two generic keywords while missing the natural phrasings users would actually say; it avoids a 1 because 'context restore' is at least a recognizable niche term rather than pure abstract jargon.	2 / 5
Distinctiveness Conflict Risk	'context restore' carves out a somewhat specific niche but 'context management' is broad and could overlap with related context/memory skills, fitting the 'somewhat specific but could still overlap' anchor; it is not a 4 because the trigger is not distinctive enough to minimize overlap.	3 / 5
	Total	8 / 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-claude/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.