common-session-retrospective

Analyze conversation corrections to detect skill gaps and prepare targeted skill-library maintenance tasks. Use after any session with user corrections, rework, or retrospective requests. After finding correction loops, also load +common/common-learning-log to persist mistake entries to AGENTS_LEARNING.md.

Quality

80%

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-session-retrospective/SKILL.md

Quality

Content

72%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 skill body is concise and well-structured with good progressive disclosure to a real reference file. The main weakness is workflow clarity: destructive, multi-agent repository edits lack an explicit validation/feedback loop in the protocol itself.

Suggestions

Add an explicit validation checkpoint to the Protocol (e.g. after Implement: 'Run the skill-creator lint / verify SKILL.md ≤70 lines and re-check on failure before logging') to satisfy the destructive/batch feedback-loop requirement.

Reference the Implementation Checklist from methodology.md as a required verification step in the body so the validation is not buried only in the reference.

Trim the 'Canonical response anchors' section or fold it into the References section to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but the 'Canonical response anchors' section and some guideline phrasing could be trimmed for a fully efficient token profile.	4 / 5
Actionability	Concrete, specific instructions ('record skill ID, indirect phrase used, and fix', 'Output correction count, skills changed, trigger misses found, estimated rounds saved') guide execution well, though the actual output schemas/templates live in the reference rather than inline.	4 / 5
Workflow Clarity	A clear 7-step Protocol with a maintenance gate exists, but the workflow performs destructive/batch edits across multiple agent skill dirs without an explicit validate→fix→retry checkpoint, which caps this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	SKILL.md is a concise overview that signals one-level-deep references to references/methodology.md (a real bundle file) with anchored links, keeping detail appropriately split and easy to navigate.	5 / 5
	Total	16 / 20 Passed

Description

87%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 is well-constructed: third-person, concrete, and explicit about both purpose and trigger conditions. Minor tightening of 'prepare targeted maintenance tasks' and a few extra synonyms would push specificity and trigger quality to full marks.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('detect skill gaps', 'prepare targeted skill-library maintenance tasks', 'persist mistake entries'), but 'prepare targeted maintenance tasks' stays somewhat abstract compared to fully concrete examples, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ('Analyze conversation corrections to detect skill gaps and prepare targeted skill-library maintenance tasks') and when ('Use after any session with user corrections, rework, or retrospective requests') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'user corrections, rework, or retrospective requests' are present and would plausibly be said, though a few common synonyms (e.g. 'self-learning', 'session review') are omitted from the description itself.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (skill-library retrospective / maintenance) with distinct triggers, making confusion with other skills unlikely.	5 / 5
	Total	18 / 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-session-retrospective/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.