continuous-learning

Auto-extract patterns from coding sessions, track corrections, and build reusable knowledge with confidence scoring

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/continuous-learning/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete templates, numeric thresholds, and well-sequenced workflows, but it is somewhat verbose due to redundant example formats and makes no use of external reference files for progressive disclosure.

Suggestions

Consolidate the overlapping example formats (YAML entry, session-learnings block, correction log, reinforcement block) into one canonical template plus brief variations to reduce redundancy.

Move the detailed confidence-scoring rubric and knowledge-base directory layout into a reference file (e.g. CONFIDENCE.md) referenced from SKILL.md to improve progressive disclosure.

Keep the inline content focused on the core workflow; the example session log and correction log could be trimmed to one illustration each.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the same entry format is restated in several overlapping shapes (YAML entry, session-learnings markdown, correction log, reinforcement block) that could be consolidated.	2 / 3
Actionability	Guidance is concrete and copy-paste ready: an exact YAML entry schema, a confidence table with specific numeric deltas (+0.10, −0.15, −0.20), explicit file layout, and numeric status thresholds.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (Session Wrap-Up Protocol 1–6, Correction Tracking 1–5) and the confidence-adjustment rules form a built-in feedback loop; the task is non-destructive so the destructive-validation cap does not apply.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the skill is a monolithic single file well over 50 lines with no external references to offload detail, so progressive disclosure stays at the mid level.	2 / 3
	Total	10 / 12 Passed

Description

60%

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 action-oriented about what the skill does, but it omits any 'when to use it' trigger guidance, leaving completeness and trigger-term quality capped at the mid level.

Suggestions

Add an explicit 'Use when…' clause naming natural triggers, e.g. 'Use when reflecting on a coding session, capturing corrections, or building a reusable knowledge base from past work.'

Include common user-facing keyword variations ('learn from my mistakes', 'track what worked', 'review session learnings') to improve trigger-term coverage.

Sharpen distinctiveness by foregrounding the confidence-scoring mechanism, which is the feature that separates this skill from generic memory skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Auto-extract patterns from coding sessions, track corrections, and build reusable knowledge with confidence scoring' — paralleling the score-3 anchor that lists several specific actions.	3 / 3
Completeness	It clearly answers 'what' (extract patterns, track corrections, build knowledge, score confidence) but never answers 'when' — there is no 'Use when…' clause, which the guidelines cap at 2.	2 / 3
Trigger Term Quality	Terms like 'coding sessions', 'corrections', and 'patterns' are somewhat natural, but coverage of common variations is thin and there is no explicit trigger phrasing a user would actually say.	2 / 3
Distinctiveness Conflict Risk	The pattern-extraction-with-confidence-scoring niche is fairly specific, but 'build reusable knowledge' is generic and the absence of explicit triggers means it could overlap with general memory/learning skills.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rohitg00/awesome-claude-code-toolkit
Path: skills/continuous-learning/SKILL.md
Commit: ebdf1d5

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.