CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

context-management-context-restore

Use when working with context management context restore

Quality

32%

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 ./.agent/skills/context-management-context-restore/SKILL.md

The canonical home for this skill is code-refactoring-context-restore in Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI

SKILL.md
Quality
Evals
Security

Quality

Content

11%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 hollow shell: generic abstract instructions, promotional overview prose, and a reference architecture pointing at 12 files that are absent from the bundle. No concrete, executable guidance is delivered anywhere in the skill as shipped. It reads as an auto-generated stub rather than a usable skill.

Suggestions

Ship the referenced bundle files (sub-skills/*.md, resources/implementation-playbook.md) or replace the dangling links with inline content — currently every file reference in the body points to a nonexistent path.

Replace the abstract Instructions with a concrete, sequenced workflow (e.g., for project resumption: retrieve context via semantic search -> filter and rank by relevance -> rehydrate session state -> validate integrity -> merge and resolve conflicts), with an explicit validation checkpoint before acting on restored context.

Delete the empty '## Core Requirements and Arguments' header and cut the Role Statement and Context Overview filler; redirect those tokens toward executable guidance such as representative commands or a worked resumption example.

DimensionReasoningScore

Conciseness

Several padded sections: the 'Role Statement' is persona fluff, 'Context Overview' is marketing prose ('sophisticated memory management system', 'seamless continuity'), the phrase 'context restoration: advanced semantic memory rehydration' is repeated verbatim three times, and '## Core Requirements and Arguments' is an empty header with no content. Roughly half the body is non-actionable filler, matching 'noticeably verbose; several unnecessary explanations or padded sections'.

2 / 5

Actionability

The Instructions are pure abstraction — 'Clarify goals, constraints, and required inputs', 'Apply relevant best practices and validate outcomes' — with no code, commands, or specific steps anywhere. The only concrete pointer, 'resources/implementation-playbook.md', does not exist in the bundle, so no executable guidance is actually delivered.

1 / 5

Workflow Clarity

No step sequence exists: the Instructions are unordered generalities, and the two named workflows ('Workflow 1: Project Resumption', 'Workflow 2: Cross-Project Knowledge Transfer') appear only as dangling link titles with no steps or validation checkpoints. This matches 'steps missing or incoherent; no sequence'.

1 / 5

Progressive Disclosure

The body has well-signaled one-level-deep references (a 12-entry module index), but scored against the actual bundle structure: no referenced file exists — all 11 './sub-skills/*.md' links and 'resources/implementation-playbook.md' are dangling — so navigation leads nowhere and no progressive content is delivered. The section/index structure is real (better than a monolithic wall or nested references), but the disclosure path is entirely unbacked.

2 / 5

Total

6

/

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, grammatically awkward when-clause that names no capabilities and few natural trigger phrases. It neither tells Claude what the skill does nor provides the vocabulary a user would use to invoke it, and it risks triggering for unrelated context-management tasks.

Suggestions

Add a concrete capability statement in third person, e.g., 'Recovers and rehydrates project context across sessions using semantic vector search, relevance ranking, session state reconstruction, and context merging.'

Fix the garbled phrase and include natural trigger synonyms: 'restore context', 'context restoration', 'session resumption', 'rehydrate memory', 'resume a paused project'.

Make the 'when' clause specific rather than generic: 'Use when resuming a paused project, reconstructing prior session state, or transferring knowledge between projects.'

DimensionReasoningScore

Specificity

'Use when working with context management context restore' contains no action verb or capability statement at all — it names a garbled domain noun ('context management context restore') inside a when-clause but never says what the skill does. Anchor 2 requires a named domain plus a generic action (e.g., 'Processes PDF files'); even that minimal action is absent here.

1 / 5

Completeness

Only a 'when' clause is present ('Use when working with...'); the description never states any capability, so 'what does this do' is entirely unanswered. This is a near-verbatim match to anchor 2's example 'Use when working with documents'.

2 / 5

Trigger Term Quality

Only two domain tokens appear ('context management', 'context restore'), and the natural phrases a user would actually say — 'restore context', 'context restoration', 'resume session', 'session resumption', 'rehydrate memory' — are missing. 'Context restore' is an ungrammatical ordering, and 'context management' is a broad term shared by many other skills.

2 / 5

Distinctiveness Conflict Risk

Context restoration / semantic memory rehydration is a real niche, so the description is not entirely generic, but the broad 'context management' term combined with a garbled domain phrase and no capability list leaves real overlap risk with memory-management, summarization, or compaction skills.

3 / 5

Total

8

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 11 missing

Warning

Total

14

/

16

Passed

Repository

Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI

Path

.agent/skills/context-management-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.