CtrlK
BlogDocsLog inGet started
Tessl Logo

agentic-labeler

Labels issues and pull requests in the dotnet/maui repository with `area-*` and `platform/*` labels ONLY, based on technical content and platform-file conventions. Used by the gh-aw agentic-labeler workflow and available for batch evaluation and interactive Copilot CLI usage.

60

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/agentic-labeler/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 body is a well-structured, highly actionable rulebook with concrete label mappings, tie-breakers, and a label-verification checkpoint for batch safety. Its main weaknesses are redundant repetition of the Tizen and prohibition rules (conciseness) and the absence of an explicit step-ordered workflow or an apply-label tool reference.

Suggestions

State the Tizen exclusion and the other-label prohibition once each in the Scope section and reference them briefly elsewhere, cutting roughly a dozen redundant lines.

Add a short numbered workflow (fetch labels -> determine area -> determine platforms -> verify candidate labels exist -> apply) to make the sequence and validation checkpoint explicit.

Name the tool/command used to actually apply a label (e.g., the add/update-label MCP tool) so the final action step is executable.

DimensionReasoningScore

Conciseness

The body is mostly efficient rule statements with no concept padding, but it could be tightened: the Tizen exclusion is repeated in four places ('Scope', platform-notes, issue rules, 'What NOT to do') and the full other-label prohibition list appears nearly verbatim in both 'Scope' and 'What NOT to do'. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened'.

3 / 5

Actionability

Concrete, directly executable guidance: a file-pattern-to-label mapping table, exact label names, tie-break examples (e.g., 'TabbedPage.tizen.cs -> area-controls-tabbedpage'), and named MCP tools (list_label, get_label). Minor gap: no tool or command is given for actually applying a label, keeping it just below fully copy-paste ready.

4 / 5

Workflow Clarity

A clear implied sequence exists (label discovery with pagination caveat -> area rules -> platform rules -> noop conditions) and an explicit verification checkpoint is present ('verify it exists with the `get_label` tool'), satisfying the validation requirement for a batch labeling skill. The sequence is never explicitly ordered as steps, matching 'clear sequence with most checkpoints present; minor validation gaps'.

4 / 5

Progressive Disclosure

The skill is a single self-contained file (no references/, scripts/, or assets/ exist) with well-organized, clearly headed sections covering scope, discovery, rules, and prohibitions. Structure is good and content appropriately placed, though at ~120 lines the rule tables are borderline monolithic and could be split, matching the 'good structure; minor organization gaps' anchor.

4 / 5

Total

15

/

20

Passed

Description

70%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, distinctive description that clearly states what the skill does and its exact label scope, but it lacks an explicit 'Use when...' trigger clause, leaving the invocation condition only weakly implied. Adding natural trigger phrases (e.g., 'Use when labeling issues or PRs in dotnet/maui, triaging, or applying area/platform labels') would raise completeness.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases such as 'Use when labeling or triaging issues and pull requests in dotnet/maui, or when applying area-* or platform/* labels'.

Include common user synonyms like 'triage', 'categorize', or 'classify' alongside 'labels' to broaden natural trigger-term coverage.

Optionally enumerate one or two more concrete capabilities (e.g., inferring platform labels from changed files) to lift specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

The description names concrete actions ('Labels issues and pull requests... with `area-*` and `platform/*` labels ONLY, based on technical content and platform-file conventions') with specific label families and derivation basis. It lists several specifics rather than a generic verb, but stops short of comprehensive multi-action coverage, so it sits between anchors 3 and 4.

4 / 5

Completeness

The 'what' is clear and specific, but there is no 'Use when...' clause; usage is only weakly implied by 'Used by the gh-aw agentic-labeler workflow and available for batch evaluation and interactive Copilot CLI usage', which describes consumers rather than when Claude should invoke it. Per the guideline, missing explicit trigger guidance caps this at 3.

3 / 5

Trigger Term Quality

Natural terms users would say are present ('labels', 'issues', 'pull requests', the repo name), giving good keyword coverage. A few common synonyms like 'triage', 'categorize', or 'classify' are missing, matching the 'a few natural terms missing' anchor.

4 / 5

Distinctiveness Conflict Risk

The description is pinned to a single repository (dotnet/maui), two exact label families (`area-*`, `platform/*`), and a named workflow, forming a clear niche with minimal conflict risk with other skills.

5 / 5

Total

16

/

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
dotnet/maui
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.