CtrlK
BlogDocsLog inGet started
Tessl Logo

code-review

Review pull requests in the Trackdub public core (trackdubllc/Trackdub). Use for Copilot code review, PR review, architecture checks, dependency-direction violations, model/license safety, fake readiness, runtime planner routing, and honest test evidence. Prefer this skill whenever reviewing diffs, pull requests, or suggesting review comments in this repository.

70

Quality

86%

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

88%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.

This is a well-crafted instruction skill: dense with repo-specific, falsifiable rules, an explicit review order, automatic stops, concrete example comments, and a merge gate. Detail is properly delegated to authoritative repo documents rather than duplicated. The only minor issues are one small invariant stated in two places and checklist density that could be split into a reference file.

DimensionReasoningScore

Conciseness

The body is almost entirely lean, imperative rules with no concept explanations or padding. The only trimmable redundancy is the readiness invariant stated twice ('Treats provider registration, download, stage run, skip, or success as the same readiness state' in Automatic review stops vs 'Provider registered ≠ model downloaded ≠ stage ran ≠ stage skipped ≠ stage succeeded' in Checklist focus), matching the 'minor instances that could be trimmed' anchor rather than a perfect level 5.

4 / 5

Actionability

Guidance is fully concrete for an instruction-only skill: exact file paths ('docs/legal/THIRD_PARTY_NOTICES.md', 'src/.../bundled-models.manifest.json', 'tests/Trackdub.TestDoubles/'), exact type and member names ('StageRunRecord.Start(...)', 'StageNames.*', 'IRuntimePlanner', 'Directory.Packages.props'), an ordered priority list, and five ready-to-use example comments. Everything Claude needs to execute is specified with no missing key details.

5 / 5

Workflow Clarity

The multi-step process is explicitly sequenced: gather required context (with a fallback procedure when MCP tools are unavailable and instruction to note unverifiable TS-* context), review in a stated priority order, treat automatic stops as findings, write falsifiable comments, and gate on the explicit 'Merge bar' checklist. Sequence, checkpoints, and checklists for a complex process are all present, matching the level 5 anchor.

5 / 5

Progressive Disclosure

No bundle files exist, and the skill appropriately defers detail to well-signaled, one-level-deep repo files ('REVIEW.md', 'AGENTS.md', '.github/pull_request_template.md') with exact paths. Structure and organization are good, but at ~105 lines of dense inline checklist content, portions (e.g., the per-area checklists) could arguably live in a reference file — a minor organization gap that fits the level 4 anchor rather than the cleanly split level 5.

4 / 5

Total

18

/

20

Passed

Description

83%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: it states what the skill does, when to use it, and scopes it to a single repository with explicit exclusions. It uses third-person voice with concrete trigger phrases. The main residual risks are heavy domain jargon in the capability list and generic review terms that could overlap with general review skills outside this repository.

DimensionReasoningScore

Specificity

The description names the action ('Review pull requests') and several concrete review capabilities: 'architecture checks, dependency-direction violations, model/license safety, fake readiness, runtime planner routing, and honest test evidence'. It lists several specific actions but the domain-specific jargon leaves minor coverage gaps, fitting the 'several specific actions; minor gaps' anchor rather than the fully comprehensive level 5.

4 / 5

Completeness

It explicitly answers both questions: what ('Review pull requests in the Trackdub public core... Use for Copilot code review, PR review, architecture checks...') and when ('Prefer this skill whenever reviewing diffs, pull requests, or suggesting review comments in this repository'). The 'when' clause uses explicit, concrete trigger phrases, matching the level 5 anchor exactly.

5 / 5

Trigger Term Quality

Natural user phrases are present: 'Copilot code review, PR review', 'reviewing diffs, pull requests, or suggesting review comments'. This is good keyword coverage with real-world synonyms, though common variations like 'code review comments' or 'request changes' phrasing are missing, placing it just below the comprehensive level 5.

4 / 5

Distinctiveness Conflict Risk

The description carves a clear niche (one repository, 'trackdubllc/Trackdub') and even states an exclusion boundary ('Private Avalonia desktop shell and gated licensing... belong in trackdubllc/Trackdub-gated'). However, generic triggers like 'PR review' and 'code review' overlap with general-purpose review skills outside this repo, so it fits 'mostly distinct; minor overlap risk' rather than the minimal-conflict level 5.

4 / 5

Total

17

/

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
trackdubllc/Trackdub
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.