address-feedback-with-replies

Complete the Slack feedback cycle: read every thread and linked evidence, fix verified repo-owned issues, and reply in-thread with honest status, clarification questions, and release follow-up. Use when the user asks to address feedback and respond in the requested voice through the invoking user's connected Slack identity.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/address-feedback-with-replies/SKILL.md

Quality

Content

62%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 thorough, well-sequenced Slack feedback workflow with strong validation loops and concrete reply templates, but it is notably verbose through cross-section repetition and remains a long monolith with no progressive disclosure into reference files.

Suggestions

Consolidate the disposition taxonomy and eye-reaction rules into one authoritative section; reference it from elsewhere instead of restating Fixed/Shipped/In progress/etc. in the intro, Decision Gate, Workflow, and Voice sections.

Extract the disposition contract and the Slack reply voice rules into reference files (e.g. references/dispositions.md, references/voice.md) and link to them one level deep to improve progressive disclosure.

Tighten the repeated upvote and question-budget explanations into a single canonical statement to reduce token overhead while preserving the rules.

Dimension	Reasoning	Score
Conciseness	The body restates the same disposition taxonomy (Fixed/Shipped/In progress/Clarification needed/Open - no reply/etc.) and the upvote, eye-reaction, and question-budget rules across the intro, Decision Gate, Workflow, and Voice sections, producing noticeable redundancy rather than lean reference material.	2 / 5
Actionability	Guidance is concrete and executable for an instruction-only skill: exact disposition states, a copy-paste reply template ('ty for the feedback - ... this was sent from a bot.'), thread_ts usage, and a hard three-question cap, with only minor gaps in edge-case handling.	4 / 5
Workflow Clarity	An explicit 8-step Workflow is backed by validation checkpoints (re-read after posting, audit the reply ledger, verify fixes with tests, git diff --check) and feedback loops (edit/remove mistaken replies, revisit In progress), satisfying the destructive/batch validation requirement rather than triggering its cap.	5 / 5
Progressive Disclosure	Headers organize the content but the disposition contract, voice rules, and question-budget logic are all inlined in one ~250-line monolith with no reference files (none exist in references/scripts/assets), so content that would benefit from being split stays inline.	3 / 5
	Total	14 / 20 Passed

Description

83%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 strong, third-person description with an explicit 'Use when' trigger and concrete actions that clearly delineate this from the base address-feedback skill. It is near-exemplary on completeness and distinctiveness, with only slightly limited trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('read every thread and linked evidence, fix verified repo-owned issues, and reply in-thread with honest status, clarification questions, and release follow-up') but the reply framing stays somewhat abstract, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ('Complete the Slack feedback cycle... fix... reply...') and when ('Use when the user asks to address feedback and respond in the requested voice through the invoking user's connected Slack identity') with a concrete trigger phrase.	5 / 5
Trigger Term Quality	Natural terms like 'address feedback', 'reply', and 'Slack' map to what a user would say, though common synonyms and variations are limited; good but not comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The reply-in-thread and connected-Slack-identity framing carves a clear niche distinct from the related address-feedback skill, with only minor overlap risk against that sibling skill.	4 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/address-feedback-with-replies/SKILL.md
Commit: b0df876

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.