address-feedback

Respond to an automated reviewer's findings on the current feature PR — a narrow, headless responder. Triages each reviewer finding into Clear / Ambiguous / Complex / Out-of-PRD-Scope, then acts — fixes the cause and pushes (diff-only) for Clear, posts one in-thread reply for the rest. Skips findings it already handled. Invoked headless by the dispatcher's feedback gate; the dispatcher owns the round counter and the STUCK escalation. Triggers - address-feedback, address review comments, respond to PR review, handle reviewer findings, PR feedback loop (project)

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 well-structured, actionable instruction skill with a clear sequenced workflow and excellent progressive disclosure via real reference files. Slight conciseness redundancy and an implicit error-recovery loop keep two dimensions at 4 rather than 5.

Suggestions

Fold the 'Hard nevers' list into the inline rules it restates (or trim to a one-line cross-reference) to remove the conciseness redundancy and reach the lean 5 anchor.

Make the validate→fix→retry feedback loop explicit for Clear fixes (e.g., 'after push, re-derive findings next tick; if the finding persists, reclassify as Complex') to lift workflow_clarity to 5.

Surface the one or two most-used gh commands inline from references/gh-mechanics.md so the common path is executable without opening the reference.

Dimension	Reasoning	Score
Conciseness	The body is dense and purposeful, teaching only project-specific machinery Claude would not know (the one-way model, triage buckets, suppression lists); the only over-explanation is the 'Hard nevers' section restating rules already stated inline, keeping it just below the lean 5 anchor.	4 / 5
Actionability	Provides concrete, executable guidance — exact invocation 'claude -p "/address-feedback <feature>"', specific paths like 'prds/<feature>/prd.md' and '.harness/feedback-rounds-<f>', and enumerated suppression directives — with minor gaps where exact gh commands are deferred to references.	4 / 5
Workflow Clarity	Clear numbered sequence (re-derive state, triage, act per bucket, exit) with explicit validation checkpoints via the idempotency and skip rules; falls short of 5 because the error-recovery feedback loop is implicit rather than a clean validate→fix→retry cycle.	4 / 5
Progressive Disclosure	The body is a well-organized overview that defers detail to one-level-deep, clearly signaled references — 'references/triage.md' for taxonomy/examples and 'references/gh-mechanics.md' for exact commands — both of which are real bundle files.	5 / 5
	Total	17 / 20 Passed

Description

92%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 highly specific, third-person description that concretely states both capabilities and invocation triggers with a clear distinct niche. The only mild gap is trigger-term breadth, where a few natural synonyms are absent.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the triage taxonomy — 'Triages each reviewer finding into Clear / Ambiguous / Complex / Out-of-PRD-Scope', 'fixes the cause and pushes (diff-only) for Clear', 'posts one in-thread reply for the rest', 'Skips findings it already handled' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (triage into four buckets then act per bucket) and when (invoked headless by the dispatcher's feedback gate when the reviewer has unresolved findings), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Explicit trigger list 'address-feedback, address review comments, respond to PR review, handle reviewer findings, PR feedback loop' gives good natural-term coverage with synonyms, but a few common phrasings are missing — sits above the 3 anchor, below the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear narrow niche — the headless responder half of the automated PR review cycle acting only on bot-reviewer findings — with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: tdg-ninja/context-specs-factory-ai
Path: skills/harness/address-feedback/SKILL.md
Commit: 3a7a725

Reviewed: about 19 hours 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.