CtrlK
BlogDocsLog inGet started
Tessl Logo

context-management-context-restore

Use when working with context management context restore

41

Quality

41%

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/context-management-context-restore/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 well-structured, lean procedure for restoring project context from current evidence, with clear sequencing, embedded validation guidance, and a concrete worked example. Its main weakness is the unrelated "Compatibility and maintenance" boilerplate and an embedded date that consume tokens without aiding execution.

Suggestions

Remove or relocate the "Compatibility and maintenance" editorial section (callable IDs, AAS modification date, license notices) out of the executable skill body to reclaim tokens.

If the 2026-09-05 modification date must be retained, place it in an explicit "Deprecated/old patterns" or changelog section rather than inline in the overview.

Add one or two concrete commands to the Procedure (e.g. the git status / revision lookup a reader would run) to lift actionability from declarative to executable.

DimensionReasoningScore

Conciseness

The Procedure, Inputs and Example are lean and instruction-focused, but the "Compatibility and maintenance" section (callable IDs, "Modified in AAS on 2026-09-05", license notices) is editorial boilerplate unrelated to executing the skill, and the embedded date is time-sensitive material outside any deprecated/old-patterns section.

3 / 5

Actionability

The procedure gives concrete directives ("Report 'X passed; Y pending' until the new checks finish") plus a worked example with an expected-output shape, but the guidance remains at a declarative/procedural level with no specific commands or fully executable steps.

3 / 5

Workflow Clarity

The six numbered steps are clearly sequenced with embedded validation checkpoints (validate volatile facts against the current base, resolve conflicting notes, separate verified vs. unverified work); this is a read-and-reconstruct task rather than a destructive/batch operation, so the missing explicit validate→fix→retry loop is a minor gap rather than a cap.

4 / 5

Progressive Disclosure

The body is under 50 lines, single-purpose, has no bundle files and no need for external references, and is organized into well-labeled sections (When to Use, Inputs, Procedure, Example, Limitations), satisfying the simple-skill exception for progressive disclosure.

5 / 5

Total

15

/

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 essentially a trigger clause that restates the skill name without describing any concrete capability, leaving the crucial "what does this do" question unanswered. Its trigger phrasing is repetitive and not language a user would naturally produce, and it carries notable overlap risk with other context-management skills.

Suggestions

Lead with a concrete capability statement, e.g. "Restores and reconciles a project's working context from a saved handoff against the current checkout."

Keep the "Use when..." clause but add the natural trigger phrases users actually say, such as "resume interrupted work", "reconstruct a prior decision", or "restore project context".

Drop the doubled "context management context restore" wording so the skill reads as a distinct action rather than a restated name.

DimensionReasoningScore

Specificity

The description states no concrete capability actions at all — it only restates the skill name as a trigger clause ("Use when working with context management context restore"), with "context" awkwardly doubled, so it sits at or below the score-2 anchor which at least names a generic action like "Processes PDF files".

1 / 5

Completeness

Only a "when" ("Use when...") is present with no "what" describing what the skill actually does, matching the score-2 anchor "only 'when' is present without 'what'".

2 / 5

Trigger Term Quality

The keywords "context" and "restore" are topically relevant, but the phrasing "context management context restore" is repetitive and not a phrase a user would naturally say; natural variations like "resume my work" or "restore project context" are missing.

2 / 5

Distinctiveness Conflict Risk

"context management" is broad and the doubled "context restore" phrasing is generic, giving high overlap risk with the many memory/context-handling skills a user might instead be seeking.

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.

Validation15 / 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
sickn33/agentic-awesome-skills
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.