common-learning-log
Append a structured learning entry to AGENTS_LEARNING.md whenever an AI agent makes a mistake. Auto-activates as a composite skill when: a pre-write skill violation is detected and auto-fixed, or when the session retrospective finds a correction loop. Also triggers directly when the user corrects the AI mid-session. Use when: mistake, wrong, redo, that's not right, correction, my bad, fix that error, I made a mistake, agent error, learning log, log mistake, AGENTS_LEARNING.md (triggers: AGENTS_LEARNING.md, mistake, wrong, redo, correction, agent error, learning log)
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that excels across all dimensions. It clearly specifies the concrete action (appending structured entries to a specific file), provides extensive natural trigger terms, explicitly separates 'what' from 'when', and occupies a distinct niche unlikely to conflict with other skills. The description is slightly verbose with some redundancy between the trigger list and the 'Use when' clause, but this doesn't detract from its effectiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Append a structured learning entry to AGENTS_LEARNING.md', describes multiple activation scenarios (pre-write skill violation detected, session retrospective correction loop, user mid-session correction). Very concrete about what it does and how it activates. | 3 / 3 |
Completeness | Clearly answers both 'what' (append a structured learning entry to AGENTS_LEARNING.md) and 'when' (explicit 'Use when:' clause with multiple trigger scenarios including auto-activation conditions and direct user triggers). Both dimensions are thoroughly covered. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'mistake', 'wrong', 'redo', 'that's not right', 'correction', 'my bad', 'fix that error', 'I made a mistake', 'agent error', 'learning log', 'log mistake', 'AGENTS_LEARNING.md'. These are natural phrases a user would actually use when correcting an AI. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: logging AI agent mistakes to a specific file (AGENTS_LEARNING.md). The combination of error-logging, the specific file target, and the agent-learning domain makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise operational skill with clear workflow sequencing and appropriate progressive disclosure. Its main weakness is the complete absence of an inline example of the log entry format — the core output is entirely delegated to a reference file, which reduces immediate actionability. The anti-patterns and guidelines sections are strong and add genuine value.
Suggestions
Include a minimal inline example of a completed log entry (even 3-4 lines) so Claude can execute without reading the reference file first.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No unnecessary explanations of what a learning log is or why mistakes matter. The anti-patterns section is tight and uses concrete before/after examples. Guidelines are crisp bullet points. | 3 / 3 |
Actionability | The protocol steps are clear but the actual log entry format is deferred entirely to references/log-format.md. Without seeing the template inline or at least a minimal example, Claude cannot execute the append step without first reading another file. The counting mechanism ('count existing headers → N') is concrete, but the core deliverable (the entry itself) lacks any inline example. | 2 / 3 |
Workflow Clarity | The 4-step protocol is clearly sequenced with explicit trigger detection, a read step, an append step, and a continue step. The 'non-blocking' note and the 'append entry first' anti-pattern together form a clear ordering constraint. The 'Create file if missing' guideline handles the bootstrap edge case. | 3 / 3 |
Progressive Disclosure | The skill is a concise overview with a single, clearly signaled one-level-deep reference to the log entry format template. Content is appropriately split — the protocol lives here, the template lives in references/log-format.md. Navigation is clear and not nested. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- HoangNguyen0403/agent-skills-standard
- Commit
19a1140
- 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.