common-learning-log

Append a learning entry to AGENTS_LEARNING.md when an AI agent makes a mistake. Auto-activates after a pre-write audit auto-fix, a retrospective correction loop, or a mid-session user correction. Use when: mistake, wrong, correction, my bad, agent error, learning log.

Quality

78%

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 ./.github/skills/common/common-learning-log/SKILL.md

Quality

Content

78%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 tight, well-organized instruction skill with a clear sequenced protocol and a properly factored one-level reference file. Its main weakness is the low-value 'Canonical response anchors' section, which adds tokens without actionable guidance.

Suggestions

Remove or rewrite the 'Canonical response anchors' section — it currently adds noise (and a typo) without actionable value, which is the main conciseness drag.

Add a brief post-append verification checkpoint (e.g. confirm Iteration #(N+1) header now exists) to push workflow_clarity from 4 to 5.

Dimension	Reasoning	Score
Conciseness	The body is lean — protocol, guidelines, and anti-patterns assume Claude's competence with no concept over-explanation — but the 'Canonical response anchors' block reads as filler (including a stray 'Append to AGENTSLEARNING,append' typo), keeping it just below the every-token-earns-its-place score 5.	4 / 5
Actionability	Concrete, executable guidance throughout — 'count existing ## Agent Learning Log: Iteration headers → N', 'write Iteration #(N+1) using format in [Log Entry Format]', with anti-patterns giving before/after examples — with only the minor gap that the actual entry template lives in the referenced file rather than inline.	4 / 5
Workflow Clarity	A clear 4-step sequence (detect signal → read & count → append → continue) with the header-count step acting as a correctness checkpoint and an explicit bootstrap-if-missing rule; minor validation gap (no post-append verification), and the destructive/batch cap does not apply since this is append-only and explicitly non-editing.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview that offloads the full entry template to a single one-level-deep, clearly-signaled reference ([references/log-format.md], verified to exist) linked from Protocol, Guidelines, and References sections, matching the well-signaled one-level-deep anchor.	5 / 5
	Total	17 / 20 Passed

Description

78%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 focused, well-structured description that clearly states both capability and trigger conditions with natural keywords. It is comprehensive on completeness but slightly thin on enumerated concrete actions and has minor overlap risk from generic correction terms.

Suggestions

Add one or two more concrete actions (e.g. 'count existing iteration headers', 'bootstrap the file if missing') to lift specificity from 3 to 4.

Narrow the generic trigger terms ('wrong', 'mistake') or scope them to an agent-error context to reduce overlap with general correction-handling skills.

Dimension	Reasoning	Score
Specificity	Names the domain (learning log) and one concrete action ('Append a learning entry to AGENTS_LEARNING.md') plus trigger surfaces, but does not list several specific actions, matching the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action score 4.	3 / 5
Completeness	Explicitly answers both what ('Append a learning entry to AGENTS_LEARNING.md when an AI agent makes a mistake') and when ('Use when: mistake, wrong, correction, my bad, agent error, learning log' plus auto-activation triggers), matching the 'clearly and explicitly answers both with concrete trigger phrases' anchor.	5 / 5
Trigger Term Quality	Good natural-term coverage including 'mistake, wrong, correction, my bad, agent error, learning log' — 'my bad' adds a colloquial synonym — but a few common variations (e.g. 'oops', 'that's wrong', 'redo') are missing, so it sits above the generic-keyword anchor and below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (agent-mistake learning log bound to a specific file) with distinct auto-activation surfaces, but generic correction keywords like 'wrong'/'mistake' carry minor overlap risk with related feedback/correction skills, keeping it just below the minimal-conflict score 5.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: HoangNguyen0403/agent-skills-standard
Path: .github/skills/common/common-learning-log/SKILL.md
Commit: 405cdd5

Reviewed: 4 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.