feedback-learning

Classify and record explicit corrective feedback without turning skills or instructions into append-only knowledge dumps.

Quality

64%

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/feedback-learning/SKILL.md

Quality

Content

75%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 body is a well-structured, token-efficient instruction skill with concrete destinations, a copy-paste inbox template, explicit validation, and a compaction checklist. All four dimensions land at 4 — strong and actionable, with only minor tightening and a slightly longer-than-minimal length keeping it off the top anchor.

Suggestions

Tighten the abstract 'Goal' section into a single concrete sentence so the body is lean throughout and conciseness can reach anchor 5.

Expand step 6 ('Validate') into an explicit validate→fix→retry feedback loop (e.g., 'If a link is broken or a destination mismatches, fix and re-check before recording') to push workflow_clarity to anchor 5.

Consider moving the inbox format template and compaction rules into a short reference file referenced from SKILL.md to bring the main file under the simple-skill threshold and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — a decision table, tight numbered steps, and a compact template with no concept-padding — with only minor spots (the abstract 'Goal' section) that could be trimmed, placing it above anchor 3 but below the exemplary anchor 5.	4 / 5
Actionability	It gives concrete, executable guidance — exact paths (`.github/learnings/<area>.md`), a feedback-kind→destination decision table, a copy-paste inbox template, and hard limits (ten topics, 8 KB, 90 days) — with the 'Generalize carefully' step remaining somewhat abstract, so just below anchor 5.	4 / 5
Workflow Clarity	A clear six-step sequence ends in an explicit 'Validate' checkpoint (step 6) and the compaction section is a checklist with a feedback loop, satisfying the destructive/batch validation requirement; it is just short of anchor 5's fully explicit error-recovery loop.	4 / 5
Progressive Disclosure	The skill is a single self-contained file, well-sectioned (Goal, Workflow, inbox format, Reading learnings, Compaction), with content appropriately inline; at ~100 lines it exceeds the <50-line simple-skill exception that would otherwise allow a 5, so it sits at anchor 4.	4 / 5
	Total	16 / 20 Passed

Description

53%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 concrete and distinct, naming two specific actions and a clear niche with a negative guardrail. Its main weakness is the absence of an explicit 'Use when...' trigger clause and natural synonyms, which leaves both completeness and trigger-term quality at the midpoint.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases, e.g. 'Use when a user corrects an approach, rejects a pattern, or asks the agent to learn from feedback.'

Include natural synonyms users actually say ('remember this', 'don't repeat that', 'learn from this correction') alongside 'corrective feedback' to broaden trigger-term coverage.

List one or two more concrete actions (e.g. 'classify, route, and record') to lift specificity from two actions toward several.

Dimension	Reasoning	Score
Specificity	Names the domain ('corrective feedback') and two concrete actions ('Classify', 'record'), matching anchor 3; it does not list 'several' actions, so it falls below anchor 4.	3 / 5
Completeness	It gives a clear 'what' (classify and record corrective feedback) but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	'corrective feedback' is a relevant keyword, but the description omits common natural variations users actually say ('remember this', 'don't do that again', 'learn from this'), matching anchor 3.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche and adds a distinguishing negative constraint ('without turning skills or instructions into append-only knowledge dumps'), with only minor overlap risk against generic 'remember this' behaviors — above anchor 3 but not the exemplary distinctness of anchor 5.	4 / 5
	Total	13 / 20 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: posit-dev/positron
Path: .github/skills/feedback-learning/SKILL.md
Commit: b0258bc

Reviewed: 5 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.