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.

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced review pipeline with concrete commands and strong validation checkpoints, but its progressive-disclosure design depends on sibling files (AGENTS.md, TEMPLATES.md, requirements.json) that are not present, and the body is denser than necessary.

Suggestions

Ship the referenced sibling files (AGENTS.md, TEMPLATES.md, requirements.json) or inline the minimal subset each phase needs — without them, multiple phases instruct 'Read AGENTS.md/TEMPLATES.md' with no actual content to read.

Move the full Source-of-Truth Hierarchy and cross-check status table into TEMPLATES.md and keep only the one-line rule in SKILL.md to trim the body toward a true overview.

Consolidate the Phase 1d context-gathering bullets and the 'Important rules' block, which restate several in-phase rules, to reduce redundancy.

DimensionReasoningScore

Conciseness

The body is command-dense and assumes Claude's competence, but at ~200 lines it carries elaboration (the full Source-of-Truth Hierarchy, cross-check status table, and 'Important rules') that could be delegated to the referenced sibling files; mostly efficient but could be tightened.

2 / 3

Actionability

Fully executable guidance throughout: exact 'gh pr diff', 'glab api --paginate', and 'git diff HEAD' commands, real API paths, file-priority lists, and pagination requirements — copy-paste ready.

3 / 3

Workflow Clarity

A clearly sequenced Phase 0–6 pipeline with explicit validation checkpoints — the preflight STOP rule for missing required deps, the non-interactive fallback default, the diff cap, and the NEW/RAISED-OPEN/RAISED-RESOLVED-FIXED/RAISED-RESOLVED-NOT-FIXED cross-check table provide error-recovery feedback loops.

3 / 3

Progressive Disclosure

References to AGENTS.md, TEMPLATES.md, and requirements.json are clearly signaled and one level deep, but those sibling files are absent from the bundle, so the disclosure structure is incomplete/broken rather than cleanly functional — content that is meant to be split out is missing entirely.

2 / 3

Total

10

/

12

Passed

Description

100%

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 explicitly states both capability and trigger conditions, with concrete named agents and natural trigger phrasing. No first/second-person voice, no vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in a single clause — 'bug scanner, CLAUDE.md compliance, test coverage, plan alignment, git history, sibling MR/epic coherence' plus 'confidence scoring and optional draft inline comments' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what it does ('runs multi-perspective parallel agents... with confidence scoring and optional draft inline comments') and when to use it via an explicit 'Use when...' clause plus a 'Triggers for...' tail.

3 / 3

Trigger Term Quality

Natural user phrasing is well covered: 'reviewing a PR/MR', 'review this PR/MR', and the slash-command form '/devflow:review' are exactly what a user would say.

3 / 3

Distinctiveness Conflict Risk

The consolidated multi-perspective review niche with confidence scoring and MR-draft posting is distinct, and its triggers ('/devflow:review', 'review this PR/MR') are unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.