CtrlK
BlogDocsLog inGet started
Tessl Logo

filesystem-context

Use for file-based context management, dynamic context discovery, and reducing context window bloat. Offload context to files for just-in-time loading.

52

Quality

58%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/filesystem-context/SKILL.md

The canonical home for this skill is filesystem-context in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

50%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 actionable with concrete code and well-sequenced patterns, but it is padded with conceptual explanation Claude does not need, lacks validation checkpoints in its workflows, and inlines detail that should be split into the missing reference files. Trimming conceptual prose and providing the referenced bundle files would lift the lowest dimensions.

Suggestions

Cut or condense the conceptual prose ('Core Concepts', static-vs-dynamic explanations, 'four predictable ways') to assume Claude's knowledge and reduce the body toward lean pattern specs.

Add explicit validation/feedback-loop steps for risky patterns — especially self-modification, where guardrails are mentioned but not specified — to raise workflow clarity above 3.

Either create the referenced 'Implementation Patterns' file under references/ and link it one level deep, or remove the dangling internal reference, so progressive disclosure is backed by real bundle structure.

DimensionReasoningScore

Conciseness

The ~300-line body devotes multiple paragraphs to concepts Claude already knows ('The filesystem provides a single interface...', 'Context engineering can fail in four predictable ways...', static-vs-dynamic explanations), which is noticeably verbose with several padded sections rather than just minor trimming, sitting above 1 but below 3.

2 / 5

Actionability

Concrete Python (handle_tool_output, remember_preference), YAML plan schemas, directory layouts, and grep commands give mostly executable guidance, but helpers like write_file, extract_summary, and load_yaml are undefined so it is not fully copy-paste ready, placing it above 3 and below 5.

4 / 5

Workflow Clarity

Patterns are coherently sequenced as Problem/Solution/Implementation with Practical Guidance and Guidelines sections, but there are no explicit validation checkpoints or feedback loops for the operations described (e.g., the self-modification pattern notes guardrails are needed without specifying them), matching 'sequence present but checkpoints missing'.

3 / 5

Progressive Disclosure

Good header/subheader structure exists, but all pattern detail is inlined in a single ~300-line document and the lone internal reference ('Implementation Patterns') points to no actual bundle file (no references/ directory exists), matching 'some structure but content that should be separate is inline and references not clearly backed'.

3 / 5

Total

12

/

20

Passed

Description

67%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 specific and includes an explicit trigger clause covering both what and when, but its trigger terms lean technical rather than natural and it has minor overlap with adjacent context/memory skills. Tightening language toward user-spoken phrasing would raise the trigger-term and completeness scores.

DimensionReasoningScore

Specificity

Lists several specific actions ('file-based context management', 'dynamic context discovery', 'reducing context window bloat', 'offload context to files') rather than a single generic verb, but they are abstract capabilities rather than fully concrete operations, so it sits above 3 and below 5.

4 / 5

Completeness

Both a clear 'what' and an explicit 'Use for...' 'when' clause are present with concrete trigger phrases, but the 'when' is a capability list rather than rich user-situation triggers, placing it above 3 and below the fully explicit 5 anchor.

4 / 5

Trigger Term Quality

Keywords like 'context management', 'context window bloat', and 'just-in-time loading' are relevant but skew technical; common natural phrasings a user would say are largely missing, matching 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

The filesystem-context-engineering niche is mostly distinct, with only minor overlap risk against the closely related memory-systems and context-optimization skills it itself names, matching 'mostly distinct; minor overlap risk'.

4 / 5

Total

15

/

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
administrakt0r/AI-Agents-Safe-Coding-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.