CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-refactoring-context-restore

Use when working with code refactoring context restore

Quality

42%

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 ./skills/code-refactoring-context-restore/SKILL.md

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

SKILL.md
Quality
Evals
Security

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 body is a marketing-flavored monologue: padded role/overview/roadmap sections, non-executable pseudocode posing as examples, workflows without executable validation loops, and a broken reference to a nonexistent playbook file. It needs trimming to actionable core content split across real reference files.

Suggestions

Delete the 'Role Statement', 'Context Overview', 'Future Roadmap', and 'Use/Do not use this skill when' sections — they restate the description or add no actionable guidance.

Make code executable or explicitly justify the pseudocode: define or link the missing helpers (VectorDatabase, prioritize_components, estimate_tokens), and replace the invented 'context-restore' CLI examples with the real invocation path.

Create the referenced resources/implementation-playbook.md (or fix the path) and move the detailed strategy sections and input-parameter reference into it, keeping SKILL.md as a concise overview; add concrete validation commands and failure-recovery steps to Workflow 1.

DimensionReasoningScore

Conciseness

Multiple padded sections add no actionable value: 'Role Statement' ('Expert Context Restoration Specialist focused on...'), 'Context Overview' ('sophisticated memory management system designed to...'), 'Future Roadmap' ('Quantum-inspired vector search algorithms'), and boilerplate 'Use this skill when / Do not use this skill when' sections that restate the frontmatter. Several unnecessary sections matches anchor 2; not anchor 1 because genuine content (parameters, strategies, code) is present.

2 / 5

Actionability

Code blocks are non-executable stubs — VectorDatabase, rank_and_filter_contexts, prioritize_components, estimate_tokens, and load_component are all undefined — and the bash examples invoke a 'context-restore' CLI that does not exist in the bundle. Concrete structure exists but key details are missing, matching anchor 3 ('pseudocode instead of executable code'); not anchor 4 because nothing is copy-paste runnable.

3 / 5

Workflow Clarity

Workflow 1 lists a sequence and a nominal validation step ('Validate context against current codebase'), but validation is a bare phrase with no command, no error-recovery loop, and no checkpoint in Workflow 2. Sequence present with implicit checkpoints matches anchor 3; not anchor 4 because the validation steps lack any executable how or retry path.

3 / 5

Progressive Disclosure

The body inlines 175 lines of strategy material (input parameters, eight retrieval strategies, integration patterns) that belongs in reference files, and its single pointer — 'open resources/implementation-playbook.md' — targets a file that does not exist in the bundle (no resources/, references/, scripts/, or assets/ directories). Content that clearly belongs in separate files is inlined plus a broken reference matches anchor 2.

2 / 5

Total

10

/

20

Passed

Description

20%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 trigger-only and broken: it says when to use the skill but never what it does, using an unnatural jargon composite ('code refactoring context restore') that conflicts with neighboring skill domains. It needs concrete capability verbs plus natural trigger phrasing.

Suggestions

State what the skill does before the trigger, e.g. 'Restores and rehydrates project context (session state, decisions, knowledge) across agent workflows using semantic vector retrieval. Use when resuming a previous project, restoring lost session context, or transferring knowledge between projects.'

Replace the garbled composite with natural phrases users would actually type: 'restore context', 'resume project', 'context rehydration', 'session restore'.

Narrow the trigger so it does not fire on plain refactoring requests; scope it explicitly to context restoration/resumption tasks to reduce conflict with code-refactoring skills.

DimensionReasoningScore

Specificity

The description 'Use when working with code refactoring context restore' contains no action verbs describing what the skill does — only a garbled noun phrase for a domain. It falls below anchor 2 ('Processes PDF files'), which still names one generic action; here there are zero concrete actions, matching anchor 1.

1 / 5

Completeness

Only a 'when' clause is present ('Use when working with...') with no statement of what the skill does, exactly matching anchor 2's 'only when is present without what' (example: 'Use when working with documents'). Not anchor 3, which requires a clear 'what'.

2 / 5

Trigger Term Quality

The keywords 'code refactoring' and 'context restore' form an unnatural composite phrase users would not naturally say, and no synonyms or natural variations (e.g. 'restore context', 'resume session') appear. One or two generic keywords without natural phrasing matches anchor 2 rather than anchor 3's assumption of relevant natural keywords.

2 / 5

Distinctiveness Conflict Risk

The description conflates two domains (code refactoring and context restoration), creating high overlap risk with both refactoring skills and memory/context skills. It is not entirely generic (anchor 1) but is very broad with high overlap risk (anchor 2).

2 / 5

Total

7

/

20

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.

Validation — 15 / 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

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/code-refactoring-context-restore/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.