CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

load-context

To load the most current project context; MUST during prep.

Quality

64%

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 ./instructions/r2/core/skills/load-context/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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, token-efficient instruction skill: mode detection is decision-test driven, each branch has a clear sequence, and hard blocking gates with failure handling are explicit. The only weakness is that a few steps defer to artifacts (workflows, bootstrap rules) without saying where they are found.

Suggestions

Tell the reader where 'the most matching workflow' and 'bootstrap rules' are located (path or source), since the skill currently instructs loading content it never points to.

Specify what 'search/discover the tool if needed' means concretely (e.g., which command or directory to search) so the MCP-mode steps are fully executable.

DimensionReasoningScore

Conciseness

The body is lean and efficient with zero padding: every line carries non-obvious operational detail (mode detection markers, tool names, file paths, blocking-gate rules) and assumes Claude's competence throughout.

5 / 5

Actionability

Concrete detection tests ("If `RUNNING AS A PLUGIN` is in context", "`get_context_instructions` tool is available") and specific file paths ("Read `docs/CONTEXT.md` and `docs/ARCHITECTURE.md` in full") make most guidance executable, but steps like "Identify and load the most matching workflow" and "search/discover the tool if needed" give no pointer to where workflows or the tool live — minor gaps.

4 / 5

Workflow Clarity

Three mode branches are clearly sequenced with explicit checkpoints: "blocking gate — do not proceed until complete", "DO NOT proceed to any action until all prep steps are confirmed complete", and a failure-recovery loop ("If anything fails or is unclear — stop and ask user"). Validation and error handling are explicit.

5 / 5

Progressive Disclosure

Well-organized single-file structure with clear mode sections and no nested references (a sub-50-line skill with no external files needs little else), but "the loaded bootstrap rules" and "the most matching workflow" point to content with no signal about where it resides — a minor navigation gap.

4 / 5

Total

18

/

20

Passed

Description

25%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 short but fails at its job: it states a vague capability with no concrete actions, no natural trigger phrases, and no user-facing 'use when' guidance. 'MUST during prep' reads as an internal instruction to Claude rather than a description that helps a user or model decide when to invoke the skill.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases (e.g., 'Use when starting a task in this workspace, before planning or executing anything') — the missing 'Use when' clause currently caps completeness at 3.

Enumerate the concrete actions the skill performs (e.g., 'detects plugin/MCP/adhoc mode, runs prep steps, loads the matching workflow') instead of the single generic phrase 'load the most current project context'.

Differentiate from other context-loading or onboarding skills by naming the distinctive mechanisms (blocking prep gate, workflow matching) rather than the generic term 'project context'.

DimensionReasoningScore

Specificity

"load the most current project context" names the domain but provides only a single generic action with no concrete capabilities enumerated, matching the 'names the domain but actions are minimal or generic' anchor.

2 / 5

Completeness

The 'what' is vague ("load the most current project context") and "MUST during prep" is an internal directive rather than an explicit user-facing 'Use when...' trigger, so both halves are weak. The missing 'Use when' clause also caps this dimension at 3.

2 / 5

Trigger Term Quality

Terms like "load", "context", and "prep" are generic; no natural phrases a user would actually say when needing this skill, matching 'one or two generic keywords; missing the natural phrases users say'.

2 / 5

Distinctiveness Conflict Risk

"project context" is very broad and would overlap with virtually any context-loading, onboarding, or documentation skill, matching 'very broad; high overlap risk with many similar skills'.

2 / 5

Total

8

/

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

griddynamics/rosetta

Path

instructions/r2/core/skills/load-context/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.