CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

learn

Provides autonomous project pattern learning by analyzing the codebase to discover development conventions, architectural patterns, and coding standards, then generates project rule files in .claude/rules/. Use when user asks to "learn from project", "extract project rules", "analyze codebase conventions", "discover project patterns", or wants to auto-generate Claude Code rules for the current project.

68

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A well-structured orchestration skill with a clear five-phase workflow, strong validation checkpoints, and highly actionable concrete guidance. The main weakness is redundancy: the When-to-Use section and worked examples duplicate the description and inline templates, inflating token cost without adding guidance.

Suggestions

Trim the 'When to Use' section and trigger-phrase list, which restate the frontmatter description almost verbatim; keep one or the other.

Cut or shorten Example 1, which replays the Phase 4 presentation and Phase 5 persistence templates already specified inline; keep Example 2 as the only worked example since it demonstrates the distinct deduplication scenario.

Consolidate 'Best Practices' and 'Constraints and Warnings', which overlap (e.g., review-before-saving vs. never-save-without-confirmation), into a single section to reduce token cost.

DimensionReasoningScore

Conciseness

The body is mostly efficient procedural guidance, but the 'When to Use' section and trigger-phrase list restate the frontmatter description, and Example 1 replays the Phase 4/5 presentation and confirmation templates nearly verbatim (~65 lines of Examples that largely duplicate inline formats). It is tighter than the padded anchor 2 but clearly could be tightened beyond anchor 4.

3 / 5

Actionability

Fully executable guidance throughout: copy-paste bash commands for context assessment, a verbatim Task-tool delegation prompt, explicit validation thresholds (impact >= 4, evidence from at least 2 files), exact AskUserQuestion choices, and a concrete kebab-case filename example. Specific examples cover the common cases, matching anchor 5.

5 / 5

Workflow Clarity

Five clearly sequenced phases with explicit validation checkpoints (finding validation, deduplication against existing rules, user confirmation gate before any write, conflict check with diff before writing) and an explicit error-recovery loop (replace/merge/skip on conflict). The batch-write validation requirement is fully satisfied, matching anchor 5.

5 / 5

Progressive Disclosure

A single-file skill (no references/, scripts/, or assets/ exist) with well-organized sections, clear headers, and no nested references, making navigation easy. At ~230 lines, content like the Examples section could be split into a separate reference file, which keeps it at anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

83%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.

A strong description that explicitly covers both what the skill does and when to use it, with concrete, natural trigger phrases in proper third-person voice. The main gaps are a few missing trigger synonyms and minor overlap risk with project-onboarding skills like init.

DimensionReasoningScore

Specificity

Lists several concrete actions ('analyzing the codebase to discover development conventions, architectural patterns, and coding standards, then generates project rule files in .claude/rules/') with a specific output path, but omits the findings-presentation and user-approval step, leaving minor gaps in coverage. It exceeds the 1-2 actions of anchor 3 but is not the comprehensive coverage of anchor 5. Third person voice ('Provides...') is used correctly.

4 / 5

Completeness

Clearly answers both 'what' (analyzes the codebase to discover conventions/patterns/standards and generates rule files in .claude/rules/) and 'when' (an explicit 'Use when user asks to...' clause with five concrete trigger phrases). This matches the anchor-5 example structure exactly.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say ('learn from project', 'extract project rules', 'analyze codebase conventions', 'discover project patterns', 'auto-generate Claude Code rules') with good variation. A few common terms are missing (e.g., 'learn codebase', 'understand project conventions'), so it fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche (autonomous pattern learning producing .claude/rules/ files) with distinct triggers, but phrases like 'analyze codebase conventions' and 'auto-generate Claude Code rules' have minor overlap risk with closely related skills such as project-init or code-analysis skills. Mostly distinct rather than minimal-conflict, so anchor 4 fits better than 5.

4 / 5

Total

17

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

giuseppe-trisciuoglio/developer-kit

Path

plugins/developer-kit-core/skills/learn/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.