code-fixes-triage

Turn Slack #code-fixes, CodeRabbit, Codex Review, CI, and check-status noise into a repo-and-PR action queue. Use when Jamie asks for a daily code-fixes digest, recent review-noise triage, or what needs fixing across active engineering repos.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./Skills/agent-ops/code-fixes-triage/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 content is well-structured, concise, and actionable with a clear workflow, real bundle references, and explicit failure-mode and validation guidance. The chief weaknesses are mild redundancy between the Execution Boundaries and Constraints sections and a small amount of inline material that could be pushed into the existing references.

Suggestions

Merge the overlapping 'Execution Boundaries' and 'Constraints' sections so redaction and read-mostly/classification-only rules appear once, removing the repetition that slightly drags conciseness.

Make the in-workflow validation step as explicit as the skill-validation command: state a concrete 'refresh live truth, re-check, then place in fix_now only when confirmed' sequence rather than relying on the prose Failure Mode note.

Consider moving the full output schema block into references/contract.yaml (which already declares outputs) and keeping only a compact example inline, to tighten progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no basic-concept padding, but 'Execution Boundaries' and 'Constraints' overlap (redaction and read-mostly/classification-only are restated in both), leaving minor repetition that could be tightened.	4 / 5
Actionability	Provides concrete, actionable guidance: a fix_now/monitor/informational/blocked taxonomy, named owner lanes, an inline output schema, and a runnable validation command; minor gaps remain where steps like 'refresh the live state that matters' stay slightly abstract for an instruction-only skill.	4 / 5
Workflow Clarity	A clear 7-step numbered sequence pairs classification with explicit refresh-before-fix_now checkpoints, plus a Failure Mode feedback loop that keeps un-refreshable items in blocked/source_of_truth_gaps; the dedicated Validation command targets changes to the skill rather than the triage run itself, leaving a minor in-workflow validation gap.	4 / 5
Progressive Disclosure	Well-organized sections with two clearly signaled, one-level-deep real references (references/contract.yaml, references/evals.yaml, both present) and bulk detail pushed to the bundle; some content (the full output schema and examples) stays inline where it could be referenced, a minor organization gap.	4 / 5
	Total	16 / 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.

The description is well-constructed with an explicit 'Use when' clause and concrete, domain-specific triggers, giving it strong completeness and distinctiveness. The main gap is specificity: it foregrounds a single classify-into-queue action rather than enumerating multiple concrete operations.

Suggestions

Broaden the specificity beyond 'turn noise into a queue' by naming the concrete outputs of the skill (e.g., classify items as fix_now/monitor/informational/blocked and assign an owner lane) so the action set reads as comprehensive rather than a single classification step.

Soften the persona dependency on 'Jamie asks' by adding domain trigger phrasing that any user might say, to raise trigger-term generality without losing the team-automation context.

Dimension	Reasoning	Score
Specificity	Names the domain (Slack #code-fixes, CodeRabbit, Codex Review, CI) and a concrete core action ('Turn ... noise into a repo-and-PR action queue'), but the action set centers on classification into a queue rather than multiple distinct concrete operations, matching the '1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	Clearly states the 'what' ('repo-and-PR action queue') and an explicit 'Use when Jamie asks for a daily code-fixes digest, recent review-noise triage, or what needs fixing' with concrete trigger phrases, satisfying both halves explicitly.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('daily code-fixes digest', 'review-noise triage', 'what needs fixing across active engineering repos') with good keyword coverage; the persona-specific 'Jamie asks' and missing common synonyms keep it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (triage/classification of review and CI noise before implementation) with distinct triggers; minor overlap risk with the downstream owner skills (pr-green-sweep, autofix) it routes to, but the triage-only scope keeps it mostly distinct.	4 / 5
	Total	16 / 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: jscraik/Agent-Skills
Path: Skills/agent-ops/code-fixes-triage/SKILL.md
Commit: f1f2f21

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.