CtrlK
BlogDocsLog inGet started
Tessl Logo

run-maintenance-task

Use this skill to execute a task from the Android Agentic Maintenance Backlog. Invoke when the user provides an Asana task URL from that backlog and asks to run, start, execute, or work on it. Also invoke when the user says things like "run the next maintenance task", "work on this backlog item", or "pick up a maintenance task". Requires the Asana MCP to be configured.

76

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary instruction-style skill: every step is a concrete command, validation and failure paths are explicit, and the scope-control guidelines prevent drift. It assumes Claude's competence and adds only project-specific knowledge.

DimensionReasoningScore

Conciseness

The body is lean and imperative ('Always fetch origin before creating a worktree — never branch from local develop', 'Do not open a PR with known failures') with concrete commands instead of explanation. The few rationale asides ('this prevents another agent or engineer from picking up the same task concurrently', 'do not use gh pr create, which fails with a Projects Classic deprecation warning') convey non-obvious project-specific context rather than padding, so every token earns its place.

5 / 5

Actionability

Guidance is copy-paste ready: exact git worktree add/remove commands, './gradlew spotlessApply' / 'spotlessCheck' / ':<affected-module>:testDebugUnitTest', 'gh api repos/duckduckgo/Android/pulls --method POST', and full workflow-dispatch commands with REST API fallbacks. Placeholders like <short-desc> and <branch-name> are obvious and appropriate.

5 / 5

Workflow Clarity

The workflow is explicitly sequenced (Before you start → Implement → Verify → Open the draft PR → If stuck → Guidelines) with a validation feedback loop ('If any check fails due to your changes, fix it and re-run before proceeding') and a complete blocked-path (comment, move task back to Ready, clean up, do NOT open a partial PR). This is not a batch/destructive skill without validation, so no cap applies.

5 / 5

Progressive Disclosure

A single ~90-line instruction file with clear section headers and no bundle files; external references (CLAUDE.md commit rules, .github/PULL_REQUEST_TEMPLATE.md, the ddg-asana skill) are clearly signaled and one level deep. Nothing inlined here belongs in a separate reference file, and navigation is trivial.

5 / 5

Total

20

/

20

Passed

Description

90%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 description with explicit what/when, comprehensive natural trigger phrasing, and a clearly delimited niche. Its only weakness is that the capability summary stops at a single generic action ('execute a task') without naming the sub-steps the skill actually performs.

Suggestions

Enumerate the concrete sub-actions in the first sentence, e.g. 'implement the task in a worktree, run validation, open a draft PR, and trigger e2e suites' so the what matches anchor 5 for specificity.

Optionally note the target repository (duckduckgo/Android) in the description to sharpen the niche beyond 'Android' alone.

DimensionReasoningScore

Specificity

It names the domain ('Android Agentic Maintenance Backlog') and one concrete action ('execute a task from... that backlog'), matching the anchor for 1-2 concrete actions that are not comprehensive. It does not list several distinct actions (e.g., implement, validate, open a draft PR, trigger e2e suites), which would be needed for a 4.

3 / 5

Completeness

Both what ('execute a task from the Android Agentic Maintenance Backlog') and when ('Invoke when the user provides an Asana task URL from that backlog and asks to run, start, execute, or work on it. Also invoke when...') are explicit, with concrete trigger phrases and a stated prerequisite (Asana MCP).

5 / 5

Trigger Term Quality

Natural trigger coverage is comprehensive for this domain: 'run, start, execute, or work on it' plus quoted user phrasings ('run the next maintenance task', 'work on this backlog item', 'pick up a maintenance task') — exactly the words a user would say, including synonyms.

5 / 5

Distinctiveness Conflict Risk

The trigger conditions are tightly scoped to a named backlog plus an Asana task URL, giving a clear niche with minimal overlap risk against generic maintenance or task-management skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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
duckduckgo/Android
Reviewed

Table of Contents

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.