running-tend

Worktrunk-specific guidance for tend CI workflows. Adds codecov polling, Rust test commands, labels, and review criteria on top of the generic tend-* skills. Use when operating in CI.

Quality

76%

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 ./.claude/skills/running-tend/SKILL.md

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.

The content is exceptionally actionable and project-specific with strong validation in its risky workflows, scoring 5 on actionability. Its weak point is progressive disclosure: a long monolithic body that keeps detailed weekly-maintenance procedures inline rather than routing them to reference files.

Suggestions

Move the detailed Weekly Maintenance procedures (CI Pin Bumps, Agent App Integration Surfaces, MSRV & Toolchain, Statusline Cache-Check, LLM Model Names) into dedicated reference files and keep SKILL.md as an overview with one-level-deep pointers, mirroring the existing review-pr.md / nightly-cleaner.md pattern.

Tighten the discursive rationale paragraphs (the cargo-install cascade aside, the GitHub-rerun-while-in_progress explanation) to the operational rule plus a one-line reason, trimming tokens without losing the gotcha.

Promote the inlined Labels and Applying GitHub Suggestions notes into the relevant workflow sections or a short reference so the main body reads as sequenced procedures rather than a mix of prose and checklists.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence — no basic-concept padding — and every section carries project-specific traps or exact commands; not a 5 because several rationale paragraphs (e.g. why not to cargo install, the rerun-while-in_progress explanation) could be trimmed without losing the operational point.	4 / 5
Actionability	It is densely packed with copy-paste-ready commands and recipes — `cargo run -- hook pre-merge --yes`, the codecov polling loop, gh-API + jq artifacts, nix flake update — covering the common cases with only justified placeholders like <number> and <sha>.	5 / 5
Workflow Clarity	Multi-step workflows (MSRV bump, CI pin bumps, codecov investigation, statusline cache-check) have clear sequences with explicit validation and feedback loops, so the destructive/batch cap at 3 does not apply; not a 5 because some sections (applying suggestions, closing duplicates, labels) are discursive rather than sequenced.	4 / 5
Progressive Disclosure	Headers are clear and the two bundled references (review-pr.md, nightly-cleaner.md) are well-signaled in a dedicated Per-Workflow References section, but the ~400-line body inlines reference-grade weekly procedures instead of splitting them out, with only 2 of ~12 sections offloaded to reference files.	3 / 5
	Total	16 / 20 Passed

Description

75%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 clearly names a niche and lists concrete additions with an explicit Use-when clause, landing solidly at the 4-anchor across all dimensions. It stops short of 5 on completeness and distinctiveness because the trigger ("operating in CI") is generic rather than tied to worktrunk/tend specifics.

Dimension	Reasoning	Score
Specificity	"Adds codecov polling, Rust test commands, labels, and review criteria" lists several concrete actions on a named domain, matching the several-specific-actions anchor; not a 5 because the "guidance" framing stays slightly abstract rather than comprehensive.	4 / 5
Completeness	It states a clear what (worktrunk-specific additions to tend-* skills) and an explicit when ("Use when operating in CI"); not a 5 because the when is generic rather than a concrete trigger phrase tied to tend/worktrunk contexts.	4 / 5
Trigger Term Quality	Keywords "tend CI workflows", "codecov polling", "Rust test commands", and "CI" give good natural-term coverage; not a 5 because synonyms and variant phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	"Worktrunk-specific guidance for tend CI workflows" carves a clear niche distinct from the generic tend-* skills it builds on; not a 5 because the "Use when operating in CI" trigger is broad and could overlap with unrelated CI skills.	4 / 5
	Total	16 / 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: max-sixty/worktrunk
Path: .claude/skills/running-tend/SKILL.md
Commit: 6c263ed

Reviewed: 10 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.