CtrlK
BlogDocsLog inGet started
Tessl Logo

review

Use when reviewing a PR/MR by URL or the local working-tree diff — runs multi-perspective parallel agents (bug scanner, CLAUDE.md compliance, test coverage, plan alignment, git history, sibling MR/epic coherence) with confidence scoring and optional draft inline comments on the MR. Triggers for `/devflow:review` or any "review this PR/MR" request.

71

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

The canonical home for this skill is review in AndreJorgeLopes/devflow

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A well-structured, actionable multi-phase review pipeline with strong workflow clarity and good progressive disclosure through sibling-file references. The main gaps are mild cross-phase rule redundancy and reliance on sibling files (AGENTS.md, TEMPLATES.md, requirements.json) that are not bundled with the skill.

Suggestions

Consolidate restated rules (Source-of-Truth hierarchy, pagination, re-flag/RAISED-RESOLVED-FIXED) into a single 'Important rules' section and reference it from the relevant phases instead of repeating.

Bundle the referenced sibling files (AGENTS.md, TEMPLATES.md, requirements.json) in a references/ or assets/ directory so the one-level-deep navigation points to real, verifiable artifacts.

Inline the minimal agent `subagent_type` mapping or a one-line fallback summary so dispatch is executable without first reading AGENTS.md.

DimensionReasoningScore

Conciseness

The body is largely lean — direct bash commands, tables, and no padding about basic concepts — but several rules are restated across phases (Source-of-Truth hierarchy in Phase 1d and 'Important rules'; pagination and re-flag rules likewise), which could be consolidated.

4 / 5

Actionability

Provides concrete executable guidance — exact `gh`/`glab`/`git` commands, named MCP tools, regex patterns, pagination flags, and file-priority ordering — with minor gaps such as the `subagent_type` mapping being deferred to AGENTS.md.

4 / 5

Workflow Clarity

A clearly sequenced Phase 0–6 pipeline with explicit validation checkpoints (preflight STOP on missing required dep, mandatory pagination, cross-check status table, confidence scoring before output, AskUserQuestion confirmation gate before posting draft comments), satisfying the feedback-loop expectation for batch/destructive actions.

5 / 5

Progressive Disclosure

Bulk detail is cleanly delegated one level deep to clearly signaled sibling files ('Read `AGENTS.md`', 'Read `TEMPLATES.md`'), but those referenced files are not present in any bundle directory (references/scripts/assets absent), so the navigation structure is good but the referenced artifacts cannot be verified.

4 / 5

Total

17

/

20

Passed

Description

92%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, third-person description that clearly states both what the skill does and when to invoke it, with comprehensive concrete actions and a distinct trigger. Minor room to broaden trigger-term synonyms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'multi-perspective parallel agents (bug scanner, CLAUDE.md compliance, test coverage, plan alignment, git history, sibling MR/epic coherence)', 'confidence scoring', 'optional draft inline comments' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (parallel review agents, confidence scoring, draft inline comments) and 'when' ('Use when reviewing a PR/MR by URL or the local working-tree diff'; 'Triggers for `/devflow:review` or any "review this PR/MR" request') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural terms users would say ('reviewing a PR/MR', 'review this PR/MR', 'local working-tree diff') plus the explicit `/devflow:review` trigger, but misses a few common synonyms like 'code review' or 'look at this diff'.

4 / 5

Distinctiveness Conflict Risk

Clear niche — multi-perspective PR/MR review via parallel agents — with a distinct trigger (`/devflow:review`, PR/MR URL or local diff) and minimal overlap risk with other skills.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
AndreJorgeLopes/devflow
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.