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.

48

Quality

52%

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/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

42%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 content is thorough and well-organized conceptually, but it is verbose, leans on pseudocode for its executable examples, lacks explicit validation checkpoints for its destructive self-modification pattern, and references a non-existent internal document. It teaches concepts more than it instructs action.

Suggestions

Cut the conceptual padding (Core Concepts, Static vs Dynamic Trade-off, and per-pattern Problem/Solution framing) to assume Claude's competence and tighten conciseness.

Make code examples executable by defining or stubbing the undefined helpers (write_file, extract_summary, load_yaml, write_yaml), or replace them with real tool calls.

Add an explicit validate-then-proceed checkpoint to Pattern 6's self-modification workflow, and either create the referenced 'Implementation Patterns' file or remove the dangling internal reference.

DimensionReasoningScore

Conciseness

The ~300-line body is noticeably verbose, with multiple padded conceptual sections (Core Concepts, Static vs Dynamic Trade-off, and the Problem/Solution prose framing each pattern) that restate context-window fundamentals Claude already knows.

2 / 5

Actionability

The grep command, YAML plan, and directory-layout examples are concrete, but the Python examples (handle_tool_output, remember_preference) call undefined helpers like write_file, extract_summary, load_yaml and write_yaml, making them pseudocode rather than copy-paste executable.

3 / 5

Workflow Clarity

Each pattern has rough Problem/Solution/Implementation structure, but no explicit validation checkpoints, and Pattern 6 (self-modification of instruction files) is destructive without an in-workflow validation step, triggering the cap at 3.

3 / 5

Progressive Disclosure

The body is well-sectioned with clear headers, but it is monolithic with all six patterns and examples inlined, and the References section names an internal 'Implementation Patterns' document that does not exist in references/ (which is empty), leaving a dangling reference.

3 / 5

Total

11

/

20

Passed

Description

62%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 answers both 'what' and 'when' with a clear trigger clause and a recognizable niche, but its vocabulary skews abstract and technical, weakening specificity and trigger-term naturalness. It is solid but not exemplary.

Suggestions

Add 1-2 concrete file operations a user would recognize (e.g., 'write large tool outputs to scratch files and grep them on demand') to lift specificity from abstract jargon to concrete actions.

Include natural user-facing trigger phrases alongside the technical ones (e.g., 'context window is full', 'too many tokens') to improve trigger-term quality.

Separate the 'what' from the 'when' more cleanly into two sentences so the trigger guidance reads as explicit rather than blended.

DimensionReasoningScore

Specificity

Names the domain and a few actions ('file-based context management', 'offload context to files for just-in-time loading') but they remain abstract and jargon-laden rather than concrete file operations, matching anchor 3 rather than the concrete-action list of anchor 4.

3 / 5

Completeness

It states what the skill does and provides an explicit 'Use for…' trigger clause, satisfying both what and when; the when is present but somewhat blended with the what and could be more concrete, fitting anchor 4 rather than the cleanly separated anchor 5.

4 / 5

Trigger Term Quality

Terms like 'context window bloat' and 'file-based context management' are relevant but technical-leaning; 'dynamic context discovery' is not a phrase users naturally say, and common synonyms/variations are missing.

3 / 5

Distinctiveness Conflict Risk

The filesystem-context-offloading niche is clearly distinguishable with distinct triggers, though it has minor overlap risk with closely related skills like context-optimization and memory-systems.

4 / 5

Total

14

/

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.